A Flutter plugin with commons files to implement google's standalone ml kit made for mobile platform.

A Flutter plugin to use Google's ML Kit Text Recognition to recognize text in any Chinese, Devanagari, Japanese, Korean and Latin character set.

Dart and Flutter SDK for building Model Context Protocol (MCP) servers, clients, hosts, and AI tools.

Flutter extensions for AI agent interaction via MCP — lets Claude, Copilot, and Cursor tap, scroll, type, and screenshot your app.

A Flutter plugin to use Google's ML Kit Face Detection to detect faces in an image, identify key facial features, and get the contours of detected faces.

TensorFlow Lite Flutter plugin provides an easy, flexible, and fast Dart API to integrate TFLite models in flutter apps across mobile and desktop platforms.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection.

A set of primitives for working with generative AI.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection. Android arm64-v8a native libraries.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection. Android x86_64 native libraries.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection. Android x86 native libraries.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection. Android armeabi-v7a native libraries.

Moved to flutter_edge_ai. This is the final release under the name flutter_gemma; new versions ship as flutter_edge_ai, part of Flutter Edge AI.

MCP server that lets AI agents (Claude, Copilot, Cursor) inspect and interact with running Flutter apps — tap, scroll, type, and screenshot.

Generates and displays generative user interfaces (GenUI) in Flutter using AI.

A lightweight pure Dart SentencePiece tokenizer supporting BPE (Gemma), Unigram (Llama), and Hugging Face tokenizer.json pipelines.

Dart client for the OpenAI REST APIs and realtime WebSocket/WebRTC workflows with type-safe access to GPT, image, audio, and Responses APIs.

Web platform support for sherpa_onnx using WebAssembly.

A Flutter plugin to use Google's ML Kit On-Device Translation to dynamically translate text between more than 50 languages.

Dotprompt for Dart: parse and render .prompt files (YAML frontmatter + Handlebars templates) for Generative AI.

Genkit Dart package, a Generative AI library for pure Dart client/server and Flutter apps.

Dart memory library (questions, answers, notes, people) with LLM-powered analysis and CLI integration.

A lightweight plugin that provides native wrappers for running ONNX Runtime on multiple platforms

Reusable LLM provider adapters for Fa and related projects. Pure Dart core: OpenAI-compatible, OpenRouter, Ollama, and configuration.

A Flutter plugin to use Google's ML Kit Language Identification to determine the language of a string of text.

Google AI plugin for Genkit Dart.

App-facing Flutter plugin facade and inference isolate scheduler for llama.cpp.

A Flutter plugin to use Google's ML Kit Pose Detection to detect the pose of a subject's body in real time from a continuous video or static image.

Moved to flutter_edge_ai_litertlm. This is the final release under the name flutter_gemma_litertlm; new versions ship as flutter_edge_ai_litertlm, part of Flutter Edge AI.

SIMD-based linear algebra and statistics, efficient manipulation with numeric data

Moved to flutter_edge_ai_embeddings. This is the final release under the name flutter_gemma_embeddings; new versions ship as flutter_edge_ai_embeddings, part of Flutter Edge AI.

Dart client for the Anthropic API. Provides type-safe access to Claude models with streaming, tool use, and batch processing support.

Vertex AI plugin for Genkit Dart.

Low-level Dart FFI bridge for llama.cpp.

Platform interface for the lib_llama_cpp federated Flutter FFI plugin.

Android native build and Dart registration for lib_llama_cpp.

macOS native build and Dart registration for lib_llama_cpp.

Windows native build and Dart registration for lib_llama_cpp.

Linux native build and Dart registration for lib_llama_cpp.

iOS native build and Dart registration for lib_llama_cpp.

A Flutter plugin to use Google's ML Kit Image Labeling to detect and extract information about entities in an image across a broad group of categories.

A Flutter plugin to use Google's ML Kit Object Detection and Tracking to detect and track objects in an image or live camera feed.

Flutter extensions for AI agent interaction via MCP — lets Claude, Copilot, and Cursor tap, scroll, type, and screenshot your app. Log collector integration with logger package.

Moved to flutter_edge_ai_qdrant. This is the final release under the name flutter_gemma_rag_qdrant; new versions ship as flutter_edge_ai_qdrant, part of Flutter Edge AI.

A Flutter plugin to use the ML Kit document scanner API to easily add a document scanner feature to your app.

Flutter plugin to use Google's ML Kit Selfie Segmentation API to easily separate the background from users within a scene and focus on what matters.

Unofficial Dart & Flutter SDK for the OpenAI API. Typed clients for Responses, Chat, Realtime, Videos, Batch, Fine-tuning, Vector Stores and more.

A port of the fast noise algorithms, featuring cellular_noise, cubic_noise, perlin_noise, simplex_noise, value_noise and white_noise

LiteRT (formerly TensorFlow Lite) Flutter plugin. Drop-in on-device ML inference with bundled native libraries for supported native platforms and web runtimes.

Dart and Flutter local LLM inference with llama.cpp GGUF and LiteRT-LM across native platforms and web.

Dart SDK for AG-UI protocol - standardizing agent-user interactions through event-based communication

Flutter plugin for OnnxRuntime provides an easy, flexible, and fast Dart API to integrate Onnx models in flutter apps across mobile and desktop platforms.

Give your AI Agent eyes and hands inside your Flutter app.

Cross-platform AI agent harness for Dart and Flutter: streaming provider adapters, agent loop with tools, session persistence, context compaction.

Unofficial Dart client for Google AI Gemini and Vertex AI Gemini REST APIs plus Live API WebSocket sessions.

A Flutter plugin to use Google's ML Kit Entity Extractor API to recognize specific entities within static text.

A Flutter plugin to use Google's ML Kit Digital Ink Recognition to recognize handwritten text on a digital surface in hundreds of languages, as well as classify sketches.

AI chat widget for Flutter apps targeting mobile, desktop, and web supporting text, image, and voice input.

Speech recognition, speech synthesis, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection.

The official SDK for Luciq, the Agentic Observability Platform for Mobile. Use AI agents to resolve issues faster and empower your team to focus on building what matters.

Flutter extensions for AI agent interaction via MCP — lets Claude, Copilot, and Cursor tap, scroll, type, and screenshot your app. Log collector integration with the logging package.

AI Noise Cancellation plugin for Livekit Flutter Client SDK.

OpenAI Whisper ASR (Automatic Speech Recognition) for Flutter

A lightweight, in-memory HNSW (Hierarchical Navigable Small World) vector index for Dart & Flutter. Supports fast approximate nearest neighbor (ANN) search with cosine or Euclidean similarity.

The Google Cloud client library for the Generative Language API.

A dart library for pitch detection. It implements the yin algorithm port from the tarsosDSP library by Joren Six.

VAD is a cross-platform Voice Activity Detection system, allowing Flutter applications to seamlessly handle various VAD events using Silero VAD v4/v5 models.

Dart client for the Ollama API to run LLMs locally (OpenAI gpt-oss, DeepSeek-R1, Gemma 3, Llama 4, and more).

Run Tensorflow Lite models using TFLite JS and WebAssembly on browser

On-device AI for Flutter: Apple Foundation Models, Android Gemini Nano, Windows AI Foundry, Chrome Prompt API. Text, streaming, tool calling, JSON schemas, genUI specs.

OpenAI plugin for Genkit Dart, provides seamless model integration, generative AI capabilities, and tooling support.

SQLite Vector is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database. It works seamlessly on iOS, Android, Windows, Linux, and macOS, using just 30MB of memory by default. With support for Float32, Float16, BFloat16, Int8, UInt8 and 1Bit, and highly optimized distance functions, it's the ideal solution for Edge AI applications.

A Deepgram client for Dart and Flutter, supporting all Speech-to-Text and Text-to-Speech features on every platform.

A Flutter plugin to use Google's ML Kit Face Mesh Detection.

A Flutter plugin for Picovoice's Porcupine offline wake word engine.

On-device AI for Flutter: run Gemma and other LLMs, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux. Pluggable engines, no server.

Anthropic plugin for Genkit Dart, providing Claude model integration with tool calling, multimodal inputs, and streaming support.

Flutter SDK for ElevenLabs Agent Platform. Build conversational AI applications with real-time audio communication.

Use whisper.cpp models implementation for Android and iOS

Advanced face & landmark detection, embedding and segmentation using on-device LiteRT (formerly TensorFlow Lite) models.

A Flutter plugin to use Google's ML Kit Selfie Segmentation API to easily separate the background from users within a scene and focus on what matters.

Run GGUF models on Android with llama.cpp - MIT licensed, Android-only Flutter plugin

Dartantic is an agentic framework designed to make building client and server-side apps in Dart with generative AI easier and more fun!

Dart client for the Mistral AI API - chat, embeddings, fine-tuning, agents, and more.

LiteRT-LM (.litertlm) engine for flutter_edge_ai: dart:ffi on 5 native platforms plus web, CPU/GPU/NPU, and the LiteRT embedding backend.

A Flutter plugin to use Google's ML Kit Smart Reply API to automatically generate relevant replies to messages.

Flutter plugin for Ultralytics YOLO computer vision models.

A Flutter plugin with commons files to implement Apple vision made for osx.

MCP integration for Genkit Dart.

Interface definitions for dartantic_ai for use in building custom providers.

A Flutter package to detect NSFW (Not Safe For Work / NUDE / adults) content and classify SAFE content without requiring assets. Easily integrate NSFW detection into your app.

A Flutter package that removes the background from images using an ONNX model.

A Flutter plugin to use all APIs from Google's standalone ML Kit for mobile platforms.

HyperSnapSDK is HyperVerge's documents + face capture SDK that captures images at a resolution appropriate for our OCR and Face Recognition AI Engines.

Dart binding for llama.cpp --- high level wrappers for both Dart and Flutter

Flutter Apple SwiftPM runtime companion package for llamadart llama.cpp and GGUF support.

The $1 Unistroke Recognizer, a 2D single-stroke recognizer, plus features like straight line recognition, the Protractor enhancement, a way to correct user's shapes, and more.

Flutter Plugin for the Google Cloud GRPC Speech-to-Text Api.

Popular data preprocessing algorithms for machine learning

Pose, person and landmark detection using on-device LiteRT (formerly TensorFlow Lite) models.

Moved to flutter_edge_ai_mediapipe. This is the final release under the name flutter_gemma_mediapipe; new versions ship as flutter_edge_ai_mediapipe, part of Flutter Edge AI.

Shared ML abstractions for the UseSmileID Flutter SDK: data models, analyzer interfaces, the scan-state machine, and the native EXIF tagger bridge.

Real-time on-device MediaPipe face detection and face mesh. 478 landmarks with iris, multi-face tracking, ARKit-style blendshapes, and 3D head pose.

A BPE tokeniser for use with OpenAI's models. It exposes APIs used for processing text using tokens.

Moved to flutter_edge_ai_speech. This is the final release under the name flutter_gemma_speech; new versions ship as flutter_edge_ai_speech, part of Flutter Edge AI.

A package for solving the Traveling Salesman Problem (TSP)

Common platform interface for the UseSmileID Flutter SDK federated face and document detection ML plugins.

Android MLKit face detection implementation for the UseSmileID Flutter SDK.

Build powerful LLM-based Dart and Flutter applications with LangChain.dart.

Dart implementation of Model Context Protocol (MCP) client. Supports protocol revisions 2024-11-05 / 2025-03-26 / 2025-06-18 / 2025-11-25 with per-version capability negotiation, OAuth 2.1, and stdio / SSE / Streamable HTTP transports.

Contains core abstractions of LangChain.dart and the LangChain Expression Language (LCEL).

Whisper.cpp Flutter plugin with Large-v3-Turbo (128-mel) support.

Hand, gesture and landmark detection using on-device LiteRT (formerly TensorFlow Lite) models

A simple library for partitioning small to medium data sets into clusters using the k-means clustering algorithm.

A lightweight, pure-Dart implementation of the DBSCAN clustering algorithm with KD-Tree optimization.

create chat bot and other bot with ChatGPT SDK Support GPT-4 , 3.5 and SSE Generate Prompt (Stream)

Machine learning algorithms, Machine learning models performance evaluation functionality

Android MLKit document detection implementation for the UseSmileID Flutter SDK.

On-device animal detection, species classification, and body pose estimation using LiteRT (formerly TensorFlow Lite).

Cat face and landmark detection using on-device LiteRT (formerly TensorFlow Lite) models.

Dog face and landmark detection using on-device LiteRT (formerly TensorFlow Lite) models.

A Flutter plugin for native on-device generative AI through Apple Foundation Models and Android Gemini Nano.

An embeddable Flutter assistant with local tools and reactive_notifier.

Universal LLM API client with Rust-powered polyglot bindings.

Lightweight on-device speech recognition via ggml. Supports Whisper, Qwen3-ASR, FastConformer, and more.

On-device, precision-first PII redaction for Dart and Flutter. Scrub emails, phones, cards, SSNs and more from text before it reaches any LLM, then restore the model's reply.

Genkit Dart plugin for local, on-device LLMs through llamadart: llama.cpp GGUF and LiteRT-LM chat, streaming, tool calling, JSON output, and embeddings.

Silero VAD ONNX voice activity detection FFI plugin for Flutter.

This is an on-device "wake word" package for Flutter. A wake word is a keyword or sentance that activates your application

A Flutter plugin for Caf.io solution for document detection. It uses advanced computer vision algorithms to identify and extract documents from photos or camera frames.

A Flutter plugin to use Apple Vision Recognize Text in an image or live camera feed.

Offline face recognition and liveness detection Flutter plugin for Android and iOS, supporting face enrollment, 1:1 verification, and face management.

Offline whisper.cpp bindings for transcription, translation, streaming, and voice activity detection in Flutter.

A Dart implementation of the Agent-Client Protocol (ACP) for building AI-powered applications.

HTTP OCR engine for dart_pdf_editor that adds a selectable, searchable text layer to scanned PDFs using a self-hosted VLM or any JSON OCR service.

Flutter plugin for offline speech recognition using the Vosk speech recognition toolkit.

Chrome Built-in AI (Gemini Nano) plugin for Genkit Dart.

Opt-in flutter_gemma engine for the OS built-in model: Gemini Nano (Android), Apple Foundation Models (iOS/macOS), Windows AI Foundry, Chrome's Prompt API on Web.

Flutter plugin for real-time eye tracking with sub-degree accuracy on web, iOS, and Android.

A Flutter plugin to use Google's ML Kit GenAI Prompt API to send custom requests to Gemini Nano.

A Flutter plugin to use Google's ML Kit GenAI Image Description API to generate descriptions of images.

A Flutter plugin to use Google's ML Kit GenAI Rewriting API to rewrite text in different styles.

A typed Dart SDK for building agents with the Claude Code CLI.

A strongly typed Dart SDK for the Agent Client Protocol.

Embedding tokenizers for flutter_edge_ai: Gemma SentencePiece and BERT WordPiece, as a registrable provider. The pipeline they feed lives in flutter_edge_ai.

A lightweight and extensible Dart library for anomaly detection in univariate and multivariate data. Includes Z-Score and LOF algorithms.

On-device speech (STT + TTS) for flutter_edge_ai via the LiteRT C API + dart:ffi. Opt-in Stt/TtsBackendProvider.

Flutter plugin for offline speech recognition using the Vosk speech recognition toolkit.

Genkit Dart plugin for flutter_edge_ai — on-device LLM inference (Gemma, Qwen, Phi, DeepSeek, and more) with streaming, tools, JSON output, and embeddings.

A Flutter package for the Gemini Live API, enabling real-time, multimodal conversations with Google's Gemini models.

Sentiment Dart is a dart module that uses the AFINN-165 wordlist to perform sentiment analysis on arbitrary blocks of text

openai support for dart including the responses api, the realtime api, and more.

Passio Nutrition AI SDK for Flutter. Supports Android and iOS.

LangChain.dart integration module for OpenAI (GPT-5, o3, Embeddings, DALL·E, etc.).

Integration package for genui and Google Cloud Generative Language API.

On-device AI for mobile & desktop: text, vision, embeddings, RAG, tool calling, STT, TTS & VAD. Run GGUF models with Metal/Vulkan acceleration. Free for commercial use.

Core abstractions for LLM (Large Language Model) interactions. Provides common interfaces, models, and utilities used by LLM backend implementations.

A mobile-first, local-first Dart library for building and evaluating stateful, tool-using AI agents with multi-provider LLM and MCP support.

FHIR R4B binding for the model-independent `cql` engine: the R4 ModelResolver and TerminologyProvider implementations that let the CQL engine execute against FHIR R4B data.

Flutter Apple SwiftPM runtime companion package for llamadart LiteRT-LM support.

Official Flutter SDK for Mugib chat sessions, voice agents, and session payload with one apiKey.

Provider-agnostic hybrid routing for Genkit — combine on-device and cloud models behind one routing policy.

A2UI (Agent-to-UI) streaming UI protocol support for Genkit Dart, provided as model middleware.

Use native Apple Foundation Models in Flutter iOS, iPadOS and macOS apps for on-device AI, structured JSON, streaming and tools. Includes speech-to-text. Local AI needs no API key.

Run Apple's on-device language model from Flutter. Streaming, tool calling, and schema-constrained structured output — private, offline, and free.

Tiktoken is a BPE tokeniser for use with OpenAI's models. It exposes APIs used for processing text using tokens.

SQLite vector search (sqlite-vec) provider for flutter_edge_ai_rag across native platforms and web.

A Flutter package for real-time Speech-to-Text, Text-To-Speech transcription, and Translation using Microsoft Azure Cognitive Services. Supports Mobile, Desktop, and Web platforms

Flutter FFI plugin for ONNX Runtime with iOS Swift Package Manager support and cross-platform Dart bindings.

A Flutter framework for cognitive testing. Contains 14 pre-defined cognitive tests and an API for creating your own.

A modular Dart library for AI provider interactions with unified interface for OpenAI, Anthropic, Google, DeepSeek, Ollama, xAI, Groq, ElevenLabs and more.

Flexible, lightweight, and easily integrable Flutter SDK for Kommunicate AI chatbot & Live Chat.

A project to implement a one-dimensional Kalman filter in Dart language

Interactive AI Agent widget for Flutter. Connect to any LLM provider, register Dart-native tools, remote HTTP MCP servers, and local Node.js or Python subprocesses.

A Flutter plugin for real-time hand landmark detection on Android using Google's MediaPipe Hand Landmarker task and a JNI bridge.

Production-ready pure Dart core for Model Context Protocol (MCP). Agent execution engine, LLM adapters, MCP client transports, and tool orchestration — no Flutter dependency.

On-device agentic skills (SKILL.md + tool-calling loop) for flutter_edge_ai. Opt-in package adding text/JS/native-intent/MCP skill executors.

llama.cpp backend implementation for LLM interactions. Enables local on-device inference with GGUF models on Android, iOS, macOS, Windows, and Linux.

Typed local tools, session contracts and gateway transport for embedded assistants.

Verisoul helps businesses stop fake accounts and fraud

A Flutter package for integrating with Apple's Foundation Models framework on iOS and macOS devices. Provides session-based language model interactions with Apple Intelligence features.

Flutter voice AI plugin for on-device STT, neural TTS, speaker verification, audio playback, and native iOS/Android voice flows.

Kletso client for Dart and Flutter: sessions, realtime chat with typed surfaces, actions, context, triggers, voice and avatar state. Bring your own model key.

Xybrid Flutter SDK — run ML models on-device or in the cloud with intelligent hybrid routing and streaming inference.

Moved to flutter_edge_ai_sqlite. This is the final release under the name flutter_gemma_rag_sqlite; new versions ship as flutter_edge_ai_sqlite, part of Flutter Edge AI.

Moved to genkit_flutter_edge_ai. This is the final release under the name genkit_flutter_gemma; new versions ship as genkit_flutter_edge_ai, part of Flutter Edge AI.

Develop Scalable Dart/Flutter Nostr clients quickly and easily

Native Flutter SDK for FrontFace AI chat with lead capture and live human agent handoff support.

A Flutter binding for llama.cpp.

Propose emojis based a human-made text using NLP.

Flow UI is an open-source Flutter UI library to build production-grade Chat & AI assistant interfaces.

On-device object detection using MediaPipe EfficientDet-Lite models in LiteRT (formerly TensorFlow Lite) format. 80 COCO classes, fully offline.

Offline multilingual Laya inference for Flutter. Open an ONNX agent from cache or a local bundle, then run typed predict for choice, score, and noul questions.

Dart SDK for the Agent Client Protocol (ACP). Build clients, agents, and proxies that speak the ACP wire protocol.

Beta: Plug-and-play liveness detection for Flutter. Configure action sequences like blink and smile, capture images or video, and send verification results to your backend.

HuggingFace tokenizers for Dart over FFI. Load any tokenizer.json and get byte-exact BPE, WordPiece, and Unigram encoding, backed by the Rust crate.

Flutter FFI plugin for the Cera on-device inference engine. Ships prebuilt native libraries for Android, iOS, macOS, Linux and Windows.

Pure Dart BERT-compatible WordPiece tokenizer. Outputs input_ids, attention_mask, and token_type_ids. No Flutter or native dependencies.

A Flutter plugin to use Google's ML Kit GenAI Proofreading API to check grammar and spelling.

Turn weather data into driving safety guidance. Road surface classification, grip estimation, visibility degradation, and Monte Carlo safety scoring. Pure Dart, no Flutter dependency.

Dart client for TypeSafe AI (Jev / System One). Send state and typed questions; get structured answers. Pure Dart — works in CLI, server, and Flutter.

Flutter widgets for Kletso AI chat: launcher, chat, 30 built-in blocks, custom components, theming, notifications, voice sheet and animated avatar.

qdrant-edge on-device vector-store provider for flutter_edge_ai_rag, via the official qdrant_edge UniFFI SDK. Native platforms only.

Compact, canonical, lossless JSON codec for AI-first data exchange with self-describing record tables.

Dart client for Anpheros Platform, interoperable medical-data infrastructure — HL7 FHIR R4 records, patient consent (OAuth 2.1 / SMART on FHIR), provenance, AI context API.

Module to perform feature matching using OpenCV

Universal Model Gateway and MCP/Skill SDK with mandatory project-scoped Marona authentication.

A Flutter package for real-time Speech-to-Text transcription using Microsoft Azure Cognitive Services. Supports Mobile, Desktop, and Web platforms

Dart bindings for the Cera on-device inference engine. Runs GGUF LLMs locally through dart:ffi, with no Flutter dependency.

ExecuTorch on-device ML inference for Flutter using dart:ffi — vision models plus experimental streaming LLM. Android, iOS, macOS, Linux, Windows, Web.

Free and unlimited Google translations and TTS. Fast and private.

Provider-independent chat and embedding models with streaming, tool calling and structured output. Adapters for OpenAI-compatible APIs, Anthropic and Gemini.

Headless Flutter package for running GGUF LLMs locally on Android with streaming, conversation history, web search, device context, thinking support, benchmarking, and CPU/GPU auto-tuning.

On-device LLM inference for Flutter & Dart. Run Qwen 2.5 models locally with Metal on iOS and macOS, CPU on Android and desktop. No cloud, no API key.

Flutter FFI binding for Aria Engine. Load an Aria bundle and run complete() via package:aria_engine.

VLLM backend implementation for LLM interactions. Provides streaming chat, embeddings, tool calling, vision support, and model management.

Conformance checks and a test harness for Model Context Protocol (MCP) servers. Runs any MCP server over stdio and asserts on its behavior from package:test. Built on dart_mcp.

GenUI SDK (A2UI) integration for fl_select: ready-made CatalogItems so AI agents can render fl_select selection components in chat and get selections back as structured query data.

Dart Client for the Tavily API (a search engine optimized for LLMs and RAG).

Flutter plugin for Google's LiteRT-LM — run Large Language Models on-device with CPU, GPU (OpenCL) or NPU acceleration. Supports Gemma, Qwen, Phi, DeepSeek and more.

A Flutter plugin for Picovoice's Cheetah Speech-to-Text engine

Native Rust FFI plugin for mobile_rag_engine. Provides high-performance tokenization and HNSW vector indexing for on-device RAG.

A Flutter plugin for accessing TensorFlow Lite. Supports both iOS and Android.

On-device face verification using FaceNet-style embeddings with an offline TFLite model for Flutter (Android/iOS).

The official Dart client for the INFRO API — one endpoint for text, image, video and audio models, with routing, fallbacks and estimated provider cost.

A resilient multi-provider LLM router for Flutter AI Toolkit featuring transparent failover, token cost tracking, and attempt logging.

A pure Dart BERT WordPiece tokenizer with Hugging Face tokenizer.json loading, pre-tokenized alignment, dynamic AddedTokens, Unicode offsets, and verified model fixtures.

Ultra-lightweight passive face liveness detection using native TFLite (Google Play Services on Android, TensorFlowLiteSwift on iOS) for Flutter.

iOS and macOS implementation of the flutter_whisper_kit plugin, providing on-device speech recognition and transcription capabilities using WhisperKit.

Offline frontal face detection in Flutter, with image decoding and no machine-learning runtime.

A Flutter plugin to use Google's ML Kit GenAI Speech Recognition API to transcribe audio to text.

QLaya Flutter & Dart client for the fast on-device decision engine powered by the qlaya.int8.onnx model for classification, scoring, verification, and routing tasks.

Bring native GPU-accelerated machine learning to Flutter. Train models, build transformers, and run local inference without Python or cloud APIs.

A Flutter plugin to use Google's ML Kit GenAI Summarization API to generate summaries of articles and conversations.

Turn Dart functions into LLM tools for OpenAI, Gemini, Claude and MCP. Annotate with @LlmTool to generate the JSON schema, argument validation and typed calls.

AvatarKit — real-time, audio-driven avatar rendering SDK for Flutter.

A typed graph engine for agent workflows: validation before execution, branching, parallelism, loops, budgets, human approval and resumable runs.

Provider interface specification for the AI SDK Dart port. Defines the LanguageModelV4, EmbeddingModelV2, and ImageModelV3 interfaces that all provider packages must implement.

Core AI SDK for Dart with provider-agnostic model APIs.

A bounded tool-calling agent loop with budgets, sessions and streaming, plus a planner/executor and multi-agent delegation. Budgets are required, not optional.

Local GGUF and LiteRT-LM model support for Dartantic AI using llamadart.

Code generator for llm_tool. Turns @LlmTool-annotated Dart functions into LLM tools for OpenAI, Gemini, Claude and MCP, with JSON schemas and validation.

Build local/on-device RAG in Flutter with Dart APIs, offline semantic search, HNSW+BM25 hybrid retrieval, and text-layer PDF indexing.

A Dart package for parsing .prompt files for use with LLMs.

Anthropic Claude API backend for LLM interactions. Provides streaming chat and tool calling via the Anthropic Messages API.

Retrieval-augmented generation for Dart: loading, chunking, dense and BM25 retrieval, rank fusion, re-ranking, cited answers and retrieval tools.

Foundation of the agentic AI framework: messages, JSON Schema, typed errors, cancellation, retry, an event bus, logging and tracing. Pure Dart, with no provider knowledge.

Flutter plugin for running LLM inference with llama.cpp and GGUF models on Android and iOS

Tools an AI agent can call: a typed contract, a registry, argument validation and repair, human approval for anything destructive, and execution events.

Generates a working Flutter AI agent app: a chat screen, tools, human approval, a live trace panel, and an API key kept out of the source.

Core Dart port of Agent Development Kit (ADK) runtime primitives.

Self-hostable Fluvie server: render API, AI authoring, MCP, and a documentation helper in one binary, toggled by environment variables.

LangChain.dart integration module for Ollama (run Llama 4, Gemma 3, Phi4, Mistral, Qwen3 and other models locally).

A Flutter plugin for on-device generative AI, using Apple's Foundation Models (iOS) and Gemini Nano via ML Kit GenAI (Android).

A vector store port with metadata filtering, exact in-process search with snapshots, and a Qdrant adapter. Typed Float64List arithmetic throughout.

Private, offline face-liveness verification for Flutter using MediaPipe and ONNX Runtime.

MCP protocol client primitives for ADK Dart packages.

Build AI apps with Cactus

Flutter package to generate speech from text using the Meta's mms-tts-yor model on HuggingFace API

Memory for AI agents: conversation, working, long-term and semantic stores, with keyword, embedding and hybrid recall, and summarising history strategies.

A Model Context Protocol client and server for Dart. Remote MCP tools become ordinary agent tools, over stdio, HTTP or in-process transports.

Use llm_tool with Firebase AI Logic (firebase_ai). Turns your @LlmTool functions into Gemini function declarations and runs the whole tool loop.

Flutter bindings for the agentic AI framework: the umbrella package apps depend on, a lifecycle-bound runtime, device tools, secret storage and chat widgets.

Run local Laya decision models in Flutter using ONNX Runtime.

A unified wrapper for AI APIs (OpenAI, Anthropic, Google AI, Ollama, Mistral, xAI, DeepSeek, OpenRouter) with streaming, tool calling, context management, and multimodal support.

A Flutter FFI plugin for OCR with Edge AI. Uses Apple Vision (iOS) / ML Kit (Android) for text recognition and ONNX Runtime for layout detection.

Detect blur, glare, brightness, and contrast issues in images with configurable thresholds and presets for reliable capture flows.

Pure-Dart on-device RAG for Flutter and Dart. Chunk text, embed it, search vectors and build grounded LLM prompts, fully offline. Bring your own LLM.

A Flutter package for scanning and extracting structured data from supermarket receipts using Google's ML Kit.

OpenAI's Tiktoken tokenizer for models: GPT-4, GPT-4o, GPT-4o-mini, o1, o1-mini, and o1-preview.

Native LiteRT-LM bindings for Flutter across mobile, desktop, and web.

Official Dart SDK for the Wixzel Voice API. Build AI agents that place and answer real phone calls over your own SIP trunk, from Dart and Flutter.

Realtime Decart virtual try-on for Flutter with live camera streaming, garment images, prompts, camera switching, and Android/iOS platform views.

A Flutter plugin for Picovoice's Rhino Speech-to-Intent engine

Production-ready Flutter SDK for face detection, liveness verification, and anti-spoof protection using ML Kit, TensorFlow Lite, and optional YOLOv8n-face / SCRFD-2.5G-KPS backends.

Command-line interface (CLI) toolchain and unified entrypoint for the Agent Development Kit (ADK) in Dart.

Real-time on-device Quran recitation tracking, dynamic DTW word alignment, and deterministic Tajweed rule verification engine for Flutter.

Provider-agnostic AI SDK for Dart and Flutter: one API for OpenAI, Gemini, Claude and OpenAI-compatible servers, with streaming, tools, agents and RAG.

Typed, validated structured outputs from LLMs. Build a JSON Schema in plain Dart, with validation and repair retries. Adapters for OpenAI, Anthropic and Gemini.

On-device face detection & camera effects for Socrits — face detection, landmarks, expressions, and a live overlay widget.

A flutter library to let users use their own LLM keys to access AI models

Dart port of the Microsoft Agents AI framework. Build, compose, and orchestrate AI agents backed by any ChatClient — with sessions, streaming, tool use, compaction, evaluation, and middleware pipelines.

Fluid, audio-reactive neural voice orb for Conversational AI, Gemini Live & Siri style voice agents with multi-state animations, OKLab color blending, and GPU shaders.

A Flutter plugin for integrating Nexconn Chat SDK features into your application.

Ollama backend implementation for LLM interactions. Provides streaming chat, embeddings, tool calling, vision support, and model management.

A fault injection framework for testing on-device AI models in Flutter. Simulate memory pressure, malformed inputs, and degradation to catch failures before deployment.

Fast, pure-Dart vector search & HNSW index for on-device RAG, semantic search, and embeddings with Cosine, Euclidean, SQ8 quantization, and metadata filtering.

Gaussian process regression for irregular time series: smoothed trends with uncertainty bands, forecasts and learned hyperparameters, in linear time. Pure Dart.

Dart client for the OpenAI Realtime API (beta), a stateful, event-based API that communicates over a WebSocket.

OpenAI/ChatGPT backend implementation for LLM interactions. Provides streaming chat, embeddings, and tool calling via the OpenAI API.

Flutter FFI plugin for Japanese morphological analysis using Sudachi. Tokenizes Japanese text into morphemes with POS tags, readings, and dictionary forms.

Headless chat SDK for AI-powered conversation apps. Pure Dart, no Flutter dependency. Supports streaming, plugins, and multiple transport layers.

Flutter UI controllers and prebuilt widgets for the AI SDK Dart port.

Anthropic module for LangChain.dart (Claude 4.5 Sonnet, Opus, Haiku, Instant, etc.).

LangChain.dart integration module for Google (Gemini, Gemma, VertexAI, Vector Search, etc.).

Real-time human pose detection with skeleton overlay for Flutter, plus a built-in push-up form checker and rep counter. Drop-in camera + ML Kit pose landmarks.

A Flutter package for applying AI-powered adaptive inner and outer glow effects to widgets with dynamic styling support.

Liveness-aware face action helpers for Flutter mobile apps using Google ML Kit Face Detection. Not an identity verification SDK.

A typed, provider-neutral Dart client for streaming OpenAI-compatible chat APIs with cancellation and structured errors.

Accessible Flutter widgets for streamed AI answers, Markdown, citations, tool-call progress, and response actions.

ExecuTorch on-device ML inference for pure Dart using dart:ffi — vision models plus experimental streaming LLM. Android, iOS, macOS, Linux, Windows.

Dart bindings for the OSQP quadratic programming solver.

A polished, accessible and backend-neutral multimodal prompt composer for Flutter AI applications.

The Dart client library for fal.ai model APIs. You can use it to call multiple AI models on your Dart and Flutter apps.

On-device MarianMT for Flutter via Candle + flutter_rust_bridge (Android first).

Google Gemini LlmProvider for flutter_ai: streams text, thinking, function calls, and Google Search grounding citations as flutter_ai_core AiStreamEvents.

Unofficial Dart SDK for the TypeSafe AI System One API (Jev). Typed questions and answers, retries, timeouts and typed events, built for servers.

Alan AI voice assistant SDK for Flutter to add a voice assistant or chatbot to your app.

A Flutter plugin for on-device speech recognition and transcription using WhisperKit.

On-device speech-to-text transcription using whisper.cpp. Automatic model download, streaming segment results, Android support.

Flutter plugin for offline OCR using PP-OCRv6 (PaddleOCR) with ONNX Runtime C++ inference. Supports text detection and recognition on Windows.

Flutter facade package and complete UI Kit for adk_dart core runtime on all Flutter platforms.

Token counter for popular LLMs (OpenAI GPT, Anthropic Claude, Google Gemini, Meta Llama) with multi-language support. Pure Dart, works on all Flutter platforms and Dart VM.

Typed decisions (jev-style) in Flutter: choice, noul and score answered by on-device or in-browser models of any family, or by any Decision API provider.

A pure-Dart chess engine — alpha-beta search with null-move pruning, PVS, quiescence and a transposition table. No native code; runs everywhere Dart does.

Flutter plugin that provides passive liveness detection for facial recognition systems — ensuring that the detected face belongs to a live person rather than a photo, video.

Dart client for the ChromaDB vector database API - the open-source embedding database for AI applications.

Pure Dart core for AI Agent Playground. Agent execution engine, LLM adapters, MCP clients, and tool orchestration — no Flutter dependency.

A powerful Dart SDK for interacting with OpenAI Codex CLI, providing seamless integration with AI-powered coding assistance through the Codex CLI tool.

Dart client for the OpenResponses API. Provides a unified, type-safe interface for interacting with multiple LLM providers through the OpenResponses specification.

The Google Cloud client library for the Vertex AI API.

KinesteX AI provides personal AI Fitness and Physio to your clients

Anthropic (Claude) LlmProvider for flutter_ai: streams the Messages API (text, extended thinking, tool use) as flutter_ai_core AiStreamEvents.

llama_sdk is a dart implementation of llama.cpp used by the mobile artificial intelligence distribution (maid) for local model inference.

An implementation of the Google A2A protocol and SDK for client and server development

The agent engine of the Zuraffa ecosystem: missions, sessions, tool and MCP orchestration, eval harness, and event-driven observability for building type-safe AI agents.

Provider-neutral tool calling for flutter_ai: declare tools with executors, run tool calls into results, and expose web search as a tool. Pure Dart.

Flutter package for real-time AI voice conversations via Gemini Live (mic, speaker, barge-in).

High-performance tensor preprocessing library for Flutter/Dart. NumPy-like transforms pipeline for ONNX Runtime inference.

A production-ready Flutter SDK for real-time on-device face liveness detection and face verification using ML Kit and TFLite.

Advanced cross-platform eye tracking and gaze detection for Flutter. Supports Android, iOS, Web, Windows, macOS, and Linux with real-time performance.

Route requests to registered tools with Jev as a bounded decision layer. Pure Dart, with no LLM and no Flutter dependency.

A premium floating AI chat bubble widget for Flutter. Easily embed a chatbot assistant powered by Gemini, OpenAI, Claude, DeepSeek, and OpenRouter with custom styling, streaming, and navigation.

Model Context Protocol (MCP) integration for flutter_ai: connect to MCP servers over Streamable HTTP and expose their tools as flutter_ai tools that flow through the agent loop.

eNROLL is a compliance solution that prevents identity fraud and phishing. Powered by AI, it reduces errors and speeds up identification, ensuring secure verification.

FlowBrain Core — Judgment & Knowledge core for the MakeMind ecosystem. Two cooperating subsystems: Knowledge (5 facades over a 4-layer Fact/Skill/Profile/Philosophy structure plus Ops) and Agent (worker / manager / reviewer agents with 4-axis fork, conversation, growth tracking).

ONNX Runtime inference and embedding models for dense text retrieval.

Privacy-first, on-device AI SDK for Flutter. Run LLMs, STT, TTS, and VAD directly on device with no data leaving the device.

A flutter package for creating and training chatbot on botnoi.ai using botnoi developer platform api.

Idiomatic Dart transliteration of the swisseph-rs Rust API — typed, stateless, isolate-safe Swiss Ephemeris bindings via FFI.

Speech-to-text contracts and models for flutter_ai: a batch-first SpeechToText interface, transcript models, and a callback adapter for pluggable engines.

An LLM-based test generation tool that generates Dart test cases for uncovered code using Google Gemini to improve code coverage.

A production-ready Flutter package for integrating multiple AI providers (OpenAI, Gemini, Claude, etc.) with a unified API.

FFI implementation of minigpu. A library that brings multiplatform GPU compute to Dart and Flutter using WebGPU and Google Dawn.

A Flutter plugin to access on-device Gemini Nano models via Android AI Core. Enables offline inference and privacy-first text generation.

Stream an LLM's structured output as it arrives: tolerant partial JSON that fills the typed object token by token. Decodes SSE, with OpenAI, Anthropic and Gemini extractors.

A Flutter package for PDF reading, text extraction, TTS audio playback, offline summary generation, and reading progress tracking.

AI-powered Git commit message generator that whispers the perfect commit message for your changes

Flutter runtime binding for AI-driven app inspection and interaction via Flutter Copilot.

Interactive AI Agent Playground widget for Flutter. Connect to any LLM provider, register Dart-native tools, remote HTTP MCP servers, and local Node.js or Python subprocesses.

type-safe toolkit for building AI-powered features in dart or flutter projects, giving you access to 400+ models across providers through a single unified API.

Flutter plugin for offline speech recognition using the Vosk speech recognition toolkit.

Flutter bindings for Google's Agent Development Kit (ADK) for Kotlin — build on-device and cloud AI agents with tool calling, from Dart.

AI-driven customer service UIKit for Tencent Cloud Desk (customer-side).

ONNX Runtime backend for RunAnywhere Flutter SDK. On-device Speech-to-Text, Text-to-Speech, and Voice Activity Detection.

AWS API client for Amazon Rekognition (generated from SDK API specification).

Dart package for Large Language Model integration with Model Context Protocol (MCP). Multi-provider LLM access (Claude / OpenAI / Gemini / Vertex / Bedrock / Cohere / Mistral / Groq / Together / Custom), MCP client + server orchestration, and Contract Layer adapters for the mcp_bundle ecosystem. Compatible with MCP spec 2024-11-05 / 2025-03-26 / 2025-06-18 / 2025-11-25.

Google mlkit scanning for flutter plugin , supports Android and IOS.

Google Generative AI provider for the AI SDK Dart port.

On-device content and text moderation for Flutter: image/video NSFW and chat toxicity, powered by the native Nosmai SDK.

Integration of OpenAI API using Flutter framework, ChatGPT and more

Google Gemini API backend for LLM interactions. Provides streaming chat, embeddings, and tool calling via the Gemini API.

Flutter package for detecting and alerting users to nudity in images and videos before displaying them, utilizing the SensitiveContentAnalysis Framework by Apple.

A plug-and-play floating Gemini AI chat assistant for Flutter apps.

A cross-platform Flutter plugin for on-device AI/ML inference. Supports text sentiment analysis and image classification using Apple frameworks (iOS) and TensorFlow Lite (Android).

ONNX Runtime for Dart — build-time binary via native-assets hook, generalised OnnxSession API, and model-download infrastructure.

A Flutter plugin to use Apple Vision Pose Detection to detect the pose of a subject's body in real time from a continuous video or static image.

A streaming JSON parser optimized for LLM responses. Parse JSON reactively as it streams in, with path-based subscriptions and type-safe property access.

A Flutter package for face detection, liveness verification, and document scanning using TensorFlow Lite and Google ML Kit. Supports identity verification with face capture sequences and DNI document scanning for iOS and Android.

eNROLL Neo is a lightweight compliance solution that prevents identity fraud and phishing. Powered by AI, it reduces errors and speeds up identification, ensuring secure verification.

A Flutter plugin for document scanning on Android and iOS using ML Kit's Document Scanner API and VisionKit. It enables real-time edge detection, auto-cropping, and high-quality image output. Ideal for building mobile scanning solutions.

On-device neural TTS engine for Flutter. Supports Kitten, Kokoro, Supertonic, and System OS TTS via native ONNX Runtime.

Ready-made device tools for Flutter AI agents — clipboard, sandboxed files, HTTP, and system info tools that plug straight into flutter_agentic.

Semantic memory for Flutter AI agents — embeddings, on-device vector search, and long-term recall that plugs into flutter_agentic.

Stateful agent graphs for Flutter — nodes, conditional edges, cycles, checkpointing, and human-in-the-loop. LangGraph-style orchestration for flutter_agentic.

Apple Intelligence for Flutter: on-device image generation streamed as it is made, plus a native text field with Writing Tools and Genmoji.

A pure-Dart ONNX inference runtime for transformer, vision, audio, and generative models. No FFI; runs on web, WebAssembly, Flutter, and Dart.

A widget that detects face gestures.

A library for fourier transformations using the Cooley-Tukey algorithm

Flutter plugin for on-device AI inference powered by MediaPipe GenAI. Run large language models directly on iOS and Android with optimized performance.

On-device, provider-agnostic input/output safety for Dart & Flutter AI apps: PII redaction, prompt-injection and secret detection, output validation.

Train a wake word for any language with TTS, run it on-device in Flutter. The same frozen ONNX models as the wakekit npm package — no cloud, no network call.

Pure-Dart RAG (retrieval-augmented generation): chunking, embeddings, vector search, and context building. Zero dependencies, bring your own embedding model.

A Flutter package for scanning and extracting information from business cards offline using ML Kit.

A Dart wrapper for smoldot-light, providing a lightweight Polkadot/Substrate client implementation via Rust FFI bindings

Multi-provider AI SDK for Dart/Flutter with Anthropic Messages API-compatible interface. Supports Anthropic, DeepSeek, and more.

AI Powered Face Verification (Face Embedding & Comparison)

MCP stdio sidecar exposing ext.sleuth.* VM service extensions to AI clients.

Talk to ChatGPT from Flutter with no API key and no account, using the anonymous Android endpoint.

Flutter SDK for the Find AI chat assistant. Drop-in widget with floating, drawer and embedded modes, SSE streaming, and signed-mode visitor auth.

A Flutter plugin for liveness detection with randomized challenge response method

Flutter plugin for the exath-engine: a complex-native math evaluator with computer algebra (diff, factor, solve, integral, linear algebra), prebuilt for every platform.

LLM-based translation generator for Flutter ARB files

Official Dart SDK for the Wixzel Phone API. AI voice agents that place and answer real phone calls over your own SIP trunk, from Dart and Flutter.

A comprehensive GPU tensor library for Dart and Flutter, designed to leverage the power of webgpu across platforms for efficient tensor operations.

The MCP server for slang to allow working with LLMs more efficiently.

TensorFlow Lite Flutter plugin provides an easy, flexible, and fast Dart API to integrate TFLite models in flutter apps across mobile and desktop platforms.

qartvm (pronounced 'kar-toom') is a Quantum Computing Simulation package for Dart & Flutter

On-device agentic skills (SKILL.md + tool-calling loop) for flutter_gemma. Opt-in package adding text/JS/native-intent/MCP skill executors.

The cxgenie Flutter Package seamlessly integrates https://cxgenie.ai cutting-edge Conversational AI and NLP capabilities into Flutter apps.

A Flutter implementation of DialogFlow improved. Get your chatbots ready in no time.

On-device OCR for Flutter, powered by PaddleOCR + Paddle Lite (Android/iOS) and paddleocr-js (web).

Direct access to on-device ML accelerators (Apple Neural Engine / Core ML on iOS, LiteRT GPU delegate, NNAPI and XNNPACK on Android) for fast native inference.

Provider-agnostic chat controller for flutter_ai: wraps any LlmProvider with optimistic send, cancellation, regeneration, and frame-batched streaming.

Model Context Protocol (MCP) server for pub.dev, Dart SDK, and Flutter. Gives AI agents live package search, API docs, AST source slices, and breaking change diffs.

A local-first project intelligence layer for Flutter codebases. Give AI a real understanding of your Flutter project.

Convert any 2D image into a live 3D parallax scene with on-device depth estimation. Inspired by iOS depth effects.

Object-Oriented Prompting framework for defining AI agent prompts, roles, workflows, and tools as type-safe Dart objects.

Pipwave AI Agent SDK provides a predesigned graphical user interface (GUI) for user to undergo the AI agent process.

DISCONTINUED. Renamed to dart_pubdev_mcp — install that instead. Model Context Protocol (MCP) server for pub.dev. Gives AI agents structured access to search, compare, evaluate, and inspect Dart and Flutter packages.

A Flutter AI package supporting cloud (Gemini) and offline local models — clean API, streaming, smart defaults, and built-in prompt engineering.

The Universal LLM Chatbot package is a comprehensive solution that enables developers to integrate various AI services seamlessly into Flutter applications. With this package, you can harness the power of cutting-edge language models and image generation capabilities from renowned AI providers such as OpenAI, Anthropic, Gemini, and more, all within a single, unified interface

A library that brings multiplatform GPU compute to Dart and Flutter, using WebGPU directly with a Dawn backend.

Retrieval Augmented Generation for Agentic

A Dart test harness for LLM evals: assertion checks over model outputs, an optional LLM-as-judge, and cached responses so CI stays deterministic.

A Dart implementation of the BM25 ranking algorithm for full-text search

Flutter plugin for Pipecat — build real-time voice and multimodal AI agents with type-safe Dart bindings over the native iOS and Android client SDKs.

Pure Dart domain contracts for local AI inference and model lifecycle management, with immutable JSON models and runtime-independent interfaces.

The Groq Dart SDK enables developers to use Groq's api. Groq is on a mission to set the standard for GenAI inference speed, helping real-time AI applications come to life today.

High-performance offline object detection plugin using PP-PicoDet + NCNN with native camera, anti-spoof, and GPU acceleration.

A Flutter plugin for offline background removal in images, ideal for enhancing photo editing capabilities within mobile apps.

On-device speech for Apple Silicon: Parakeet-TDT and Whisper speech-to-text and PocketTTS text-to-speech, built on the mlx array framework via mlx-c.

A Flutter plugin that integrates Google Edge AI (MediaPipe Tasks Vision) to perform fast and offline face detection directly on Android devices.

The AI-Powered Intelligence Layer for Flutter. FEX provides autonomous QA, security pentesting, self-healing code, and architecture evolution.

MCP server for AI agents to inspect and control running Flutter apps through VM Service and Flutter Copilot.

Stream-oriented infrastructure for building and querying LLM training datasets.

A dart binding for llama.cpp library, bringing AI to dart world.

Unified interface for talking to LLMs (Claude, OpenAI, Gemini) from Dart/Flutter: multi-provider, streaming, tool calling, structured outputs.

Time-series analysis for Dart: ARIMA, SARIMA and SARIMAX on the ctsa C library via FFI, automatic order selection (autoArima) and pure-Dart forecasting primitives.

On-device face detection, tracking, active liveness challenges, and an injectable 1:1 face-recognition / anti-spoof pipeline for Flutter. Detection/tracking/liveness work with zero bundled AI models (native ML Kit on Android, Vision framework on iOS). Recognition and passive anti-spoofing are model-driven and loaded from a developer-supplied asset path at initialize() time.

A decoder for the 4dgs container format: 4D gaussian splat scenes with native audio in a single seekable file. Streamed and indexed read paths, pure Dart.

Flutter plugin for offline speech recognition using the Vosk speech recognition toolkit.

Official Flutter SDK for Voyant APIs - NSFW image detection, text analysis, and email services with secure HMAC authentication.

A Flutter package for building AI-powered applications with pluggable online and offline model engines, default Gemini and flutter_gemma support, connectivity-aware switching, and streaming responses.

Supervised fastText classifiers in pure Dart: reads .bin and quantized .ftz models and runs inference. Language identification with lid.176 included.

The platform interface for minigpu. A library that brings multiplatform GPU compute to Dart and Flutter using WebGPU and Google Dawn.

A Flutter library for deterministic execution of exported adaptive policies, recommendations, traces, and session-aware runtime analytics.

On-device face detection and text recognition for Flutter, powered by Google ML Kit. Process still images or a live camera stream on Android and iOS.

An unofficial Dart client for NAVER CLOVA face and celebrity recognition APIs.

Official Dart and Flutter SDK for AILabTools AI image APIs, including background removal, image upscaling, portrait editing, and more.

Plugin for managing Yolov5, Yolov8 and Yolov11 accessing with LiteRT (TensorFlow Lite) Support object detection and segmentation on Android. iOS, Working in progress.

A lightweight and elegant Flutter library for TensorFlow Lite image classification.

LangChain.dart integration module for Mistral AI (Mistral-7B, Mixtral 8x7B, embeddings, etc.).

Ai Wrapper

AI Library to create efficient Artificial Neural Networks. Pure Dart + SIMD, portable to native, JS/Web, Wasm and Flutter, with optional Metal, CUDA and WebGPU acceleration.

A pure Dart computer vision and image processing library for real-time pixel manipulation, convolutions, and ML pre-processing.

A Flutter/Dart SDK for OpenAI API by LitaVar.

Dart client for the MisarReach outreach and lead-generation API: async lead finder, CRM pipeline, multi-channel campaigns, AI sales agent, retries and SSE streaming.

Privacy-first, on-device NSFW image and video scanning for Flutter using CoreML and LiteRT. Includes NsfwGuardWidget for automatic UI blurring.

A customizable, modern AI Chat UI library for Flutter supporting Google Gemini, OpenAI, Claude, Ollama, dynamic light/dark themes, and chat history persistence.

Version-aware AI coding guidelines and multi-agent wiring for Dart and Flutter: composes guidance from resolved versions, wires up dart mcp-server, and its own rules MCP server.

High-performance, production-grade Flutter plugin for on-device local LLM inference using llama.cpp via Dart FFI and Native Assets.

A package that uses Gemini to detect sensitive content (text/images).

A Flutter package for AI-powered image analysis with Gemini and future multi-provider support.

A GPU-accelerated streaming pipeline for Dart and Flutter. Define directed stage graphs that route Tensors and host data through WGSL compute shaders with typed I/O ports, resource management, and real-time constraints.

A Flutter plugin for the OpenRouter API - unified access to hundreds of AI models including OpenAI, Anthropic, Google, and more.

LangChain.dart third-party integrations that don't have a dedicated package.

A robust, reactive streaming tag parser for LLM streams that isolates thought, code, or custom blocks chunk-by-chunk in real-time.

Flutter image processing toolkit with filters, geometric transforms, watermarking, ML-powered detection (objects, faces, text, pose), and AR hooks.

High-quality multilingual text-to-speech engine for Flutter. Supports 31 languages with multiple voice styles. Powered by Supertonic 3.

Offline speech recognition for Flutter powered by whisper.cpp.

On-device face recognition for Flutter using MobileFaceNet embeddings and cosine matching, with multi-angle enrollment storage and anti-spoofing hooks.

A Dart library for seamless Groq Cloud API integration. Easily build AI-powered applications leveraging Groq's cutting-edge language models.

A Flutter plugin for interacting with Apple's Foundation Models framework, providing on-device AI capabilities.

Genkit provider for Apple's on-device Foundation Models.

A versatile command-line PDF translator that uses Gemini or a local Ollama instance for translation.

Hardware-accelerated pose detection using MediaPipe PoseLandmarker with GPU/NPU acceleration. Detects 33 body landmarks.

Pure Dart offline facial recognition engine for Flutter & Dart.

This plugin is a simple js engine for flutter using the `quickjs` project. Plugin currently supports all the platforms except web!

A Flutter plugin for liveness detection with randomized challenge response method

Unified AI provider integration for Flutter - OpenAI, Google AI, xAI, Android native TTS with consistent API.

A Flutter plugin to use Apple Vision Hand Detection to detect a single hand and fingers in an image or video stream, and identify key distal features.

A Flutter plugin for real-time speech-to-text using Google Cloud Speech-to-Text API via gRPC streaming.

A Flutter FFI plugin for openWakeWord, providing efficient on-device wake word detection.

Build Flutter GenUI sessions backed by Genkit models, remote Genkit flows, and hybrid local/remote AI routes.

Offline-first AI framework for Flutter. Resident LLM inference, local RAG, and autonomous agents with a Material 3 Chat UI.

AI Integration Toolkit for Flutter. Multi-provider support (OpenAI, Gemini, Claude), streaming chat UI, smart widgets, and AI-powered components. Build AI features in minutes.

One Dart interface for Claude, OpenAI, and Gemini: list models, complete, chat, and stream.

Package for interacting with the OpenAI APIs

A Flutter SDK to interact with the AssemblyAI API for audio transcription

Provider-agnostic generative AI: one set of contracts for text, image, video, speech, sound-effect, and music generation across many providers.

Drop-in chat scrolling widget for AI chat apps with correct reversed-list behavior, dynamic padding, and auto-scroll management.

Flutter plugin integrating MCP server, client, and LLM into a unified agent system with background, notification, lifecycle, secure storage, and scheduling support.

Offline PaddleOCR PP-OCRv6 text detection and recognition for Flutter on Android and iOS, powered by ONNX Runtime.

A Dart SDK for interacting with Claude Code, providing seamless integration with AI-powered coding assistance through the Claude Code CLI.

On-device Qwen3-ASR speech-to-text for Flutter: offline and live-streaming transcription powered by a pure Rust engine. No cloud, no server.

Flutter package for Dialogflow CX, V2 and V2beta using gRPC. A faster integration with the Dialogflow API and also the possibility to do audio streaming.

OpenAI-compatible LlmProvider for flutter_ai: streams Chat Completions (text, tool calls, finish reasons) as flutter_ai_core AiStreamEvents over an injectable HTTP client.

A Flutter plugin for face liveness detection with configurable tasks (Smile, Blink, Motion). Uses ML Kit for face detection.

Pipecat + Daily

CapCut-style video editor for Flutter with free on-device AI: voice AI Edit, AI Shorts, captions, noise cancellation, cut-out, transitions and FFmpeg export.

Aiuta Virtual Try-On Solution for Apparel and Fashion Businesses.

Encode/decode/count the tokens for your ChatGPT prompt(sentence/words).

Download model snapshots or single files directly from Hugging Face repositories with resume, overwrite, extension filters, and CLI support.

Model Context Protocol (MCP) monorepo ecosystem umbrella package for Flutter & Dart.

GIST chatbot widget for Flutter apps - a bottom-sheet chat panel with SSE streaming, markdown answers, and answer feedback.

A pure Dart bridge to the Google Gemini API. Lightweight, powerful, and without any Flutter dependencies.

Chaquopy plugin which uses chaquopy sdk to run the python script on flutter apps.

Dart package that use AI(Gemini) to level up your physics knowledge and chat with your Ai physicist!

A client-side OCR package for Flutter Web using Tesseract.js.

Face detection and feature extraction plugin using MobileFaceNet for Android and iOS. Provides face feature vectors (128/192 dims, auto-detected from model) for face recognition and comparison.

A high-performance local LLM plugin for macOS using Apple's MLX framework.

A Flutter package for OCR and extraction of Indian vehicle registration number plates (HSRP, BH series, Military, Commercial) using Google ML Kit.

A DeepSeek client for dart and flutter. Seamless integration of AI models for text generation and chat.

Dart package that finds relevant chemical compounds using AI(Gemini) and PubChem. Use it to level up your chemistry knowledge and chat with your Ai chemist!

A Flutter plugin for real-time edge detection and document scanning with advanced image processing capabilities.

MCP (Model Context Protocol) client for AI SDK Dart. Connect to MCP servers via Streamable HTTP or stdio, discover tools, and use them with any LLM provider.

Google Gemini SDK for Flutter. This package provides a powerful bridge between your Flutter application and Google's revolutionary Gemini AI.

A GenUI transport client for OpenRouter, supporting streaming, fallbacks, and advanced LLM parameters.

Pure-Dart engine behind Vocra: streaming voice-AI orchestration (STT to LLM to TTS) with pluggable Groq, OpenAI, Gemini, xAI, Z.ai, Deepgram, and ElevenLabs providers.

OpenAI provider for the AI SDK Dart port.

A web library for minigpu wasm. A library that brings multiplatform GPU compute to Dart and Flutter using WebGPU and Google Dawn.

A typed ACP client and adapter for local Codex processes.

Generates a typed Dart API from a Fluttorch model manifest, so shapes, dtypes and preprocessing cannot drift from the training pipeline.

A Dart library for accessing common Voicevox Core APIs using, FFI.

A Flutter barcode plugin to implement google's standalone ml kit made for mobile platform.

Flutter bridge for Android App Functions. Register typed Dart functions that Android agents such as Gemini can discover and invoke on-device.

Lightweight, asynchronous Dart & Flutter library to interact with LLMs from Cloud (OpenAI, Gemini, Groq, Sumopod) and Local APIs (LM Studio, Ollama). Features SSE streaming, auto-provider detection, and zero-config local networking.

FlexDelegate (SELECT_TF_OPS) addon for flutter_litert. Bundles the TensorFlow Lite Flex delegate native library for all platforms at build time.

LangChain.dart integration module for Chroma open-source embedding database.

Cohere provider for AI SDK Dart. Use Cohere models for text generation, embeddings, and reranking.

Mistral AI provider for AI SDK Dart. Use Mistral models for text generation and embeddings.

Groq provider for AI SDK Dart. Use Groq-hosted models for fast text generation.

Ollama provider for AI SDK Dart. Use locally-running Ollama models for text generation and embeddings.

Flutter client for the OpenAI Realtime GA API. WebRTC and WebSocket transports for low-latency voice and text conversations.

Pure Dart WordPiece tokenizer for BERT NLP models. Completely independent of Flutter.

Runtime-agnostic core for shipping PyTorch models to Flutter. Model manifests, tensor specs, drift metrics, and the backend interface.

Google Gemini SDK for Flutter. This package provides a powerful bridge between your Flutter application and Google's revolutionary Gemini AI.

A powerful Flutter package for declarative AI widgets.

Embed the Pair AI assistant widget in Flutter apps with full Android & iOS support for microphone, camera, and file uploads.

HTML editor for Flutter (WYSIWYG, rich text) with built-in speech-to-text.

A Flutter package for native text recognition using native APIs.

Azure OpenAI provider for AI SDK Dart. Use Azure-hosted OpenAI models for text generation and embeddings.

ADKflutter - Official Flutter package by 20Centra for connecting to Gemini Live API server with WebSocket support for multimodal AI interactions.

Numerical parity gates for on-device models. Replays export-time goldens and fails CI when the on-device output drifts from the reference.

Flutter FFI plugin for Hugging Face tokenizers and ONNX embedding models using ONNX Runtime.

Chivox Speech Assessment SDK

A Flutter package for validating images using Google's Gemini AI. Easily verify if images match specific classes with customizable confidence thresholds.

A highly customizable, on-device Machine Readable Zone (MRZ) hardware scanner for Flutter, powered by Google ML Kit. Scans passports effortlessly.

A flutter offline package for a fast BPE tokeniser for OpenAI models.

This is a Dart package for Cloudflare Workers AI. It currently supports Text Generation and Image Generation, Text Summarization, and Image Generation Models.

A Stateful Agentic AI Framework for Flutter enabling on-device LLM agents with ReAct loops, state recovery, custom tools, and seamless coordination.

GraphTracks API Bluesky Analytics client for Dart. Provides access to Bluesky social network analytics data through the GraphTracks API.

Offline hybrid search for Flutter (Android). HNSW + BM25, RRF-fused, with on-device ONNX query embedding — no server required.

Pure Dart inference engine for SmolLM2 language models, delivering surprisingly capable local LLM results without requiring CUDA.

Dart client library for Ant Investor Ocr Service - Optical character recognition and document processing

AI-first TOTP and HOTP CLI with text, JSON, and LON output.

A flutter library for offline speech-to-text conversion which use whisper.cpp models implementation for Android、iOS、macOS.

On-device AI runtime for Flutter. Text, vision, speech-to-text, text-to-speech, image generation, embeddings, RAG, and function calling. Metal GPU on iOS, CPU on Android. Zero cloud.

A Dart library for k-means clustering

A Flutter package by jamalihassan0307 for seamless AI chat integration. Features OpenAI, Gemini, and Claude support with type-safe implementation.

A Flutter based engine for YouTube Music API that provides music search, related, lyrics and artist songs using Python backend.

Dependency-free Dart foundation for AI chat: message models, a streaming MessageProcessor, and the provider and renderer contracts the flutter_ai family builds on.

Flutter plugin for Apple's on-device Foundation Models. Generate text, structured output, and use tools with the on-device language model.

A typed Dart API for exposing Flutter Web actions as WebMCP tools.

Dart library for DeepSeek API interaction, facilitating message exchange and response processing.

A lightweight Flutter package that integrates with OpenAI's Text-to-Speech API

A comprehensive SDK for integrating with the AIxGen platform in Flutter/Dart applications.

Flutter plugin for on-device LLM inference on Android using llama.cpp. Simplifies model management, loading, and multi-turn chat — no cloud, no API keys, fully offline.

webrtc support for openai_core and the OpenAI realtime api

On-device "related items" for Flutter — suggest similar content by meaning, fully offline, no API keys. Three-line API powered by local embeddings.

A base class for all AI providers.

A professional Face Recognition Kit with real-time detection, classroom-optimized recognition, and a role-based analytics dashboard.

Dart FP-Growth algorithm for frequent pattern mining and association rule learning, with CLI and CSV support.

A Flutter package for real-time Quranic recitation analysis with AI-powered transcription, Smart Tajweed feedback, word-by-word highlighting, and IndoPak/Uthmani font support. Features a 15-line Mushaf layout (604 pages).

azure_speech_recognition with sound null safety.

A Flutter plugin to use Google's ML Kit Digital Ink Recognition to recognize handwritten text on a digital surface in hundreds of languages, as well as classify sketches.

A Flutter client for interacting with Hugging Face's Chat Gradio interface.

A real-time facial verification feature using Google ML Kit for liveliness detection.

AiLink broadcast scale data decryption and body fat algorithm Flutter library.

A comprehensive Flutter SDK for running Large Language Models (LLMs) locally on mobile and desktop devices. Supports multiple inference engines including Gemma (TFLite) and Llama (GGUF) with integrated model discovery, download, and chat capabilities.

Provider-neutral core for the Akashi agent framework: streaming tool-loop agents, typed tools, sealed message/event unions, multi-agent and durable-execution seams. Pure Dart.

AI agents, tools, workflows, providers, memory, and runtime APIs for Flint Dart applications.

A Flutter package for integrating with DeepSeek's API. Supports chat completions, model management, and streaming.

A Flutter plugin to use Apple Vision Face Detection to find faces in an image or live camera feed.

LangChain.dart integration module for Supabase (e.g. Supabase Vector).

A Flutter SDK for integrating an AI-powered coaching experience.

A Dart package providing a unified interface for interacting with various AI models through different clients.

A server and browser based Hugging Face inference and inference endpoint API REST client

A Flutter package for Automatic Number Plate Recognition (ANPR) using TFLite models.

Caching, terminal diagnostics, redaction, and operational middleware for Genkit Dart generate calls.

A customizable chatbot built on OpenAI's GPT API, enabling personalized conversational experiences.

ONNX Runtime inference for Dart, powered by the ort Rust crate.

AI companion for Flutter apps. Drop-in chat, type-safe actions, multi-provider support, and zero-config backend deploy.

dart package for gemini api

On-device face liveness detection for Flutter using a MobileNetV2 model. Detect spoof attacks from photos and videos, no internet required.

On-device AI for mobile & desktop — text, vision, embeddings, RAG & function calling. Run GGUF models with Metal/Vulkan acceleration. Free for commercial use.

Camera-based face liveness detection with Google MediaPipe 3D face landmarker, randomized active challenges, and passive anti-spoofing.

Flutter package to facilitate facial recognition and configure steps to perform validation.

Flutter camera plugin with ML Kit face detection, liveness anti-spoofing, quality gates, and native timestamp embedding with optional GPS.

Dart bindings for Apple's MLX array framework on Apple Silicon: tensors, neural-network layers, FFT, quantization, and safetensors — via FFI to mlx-c.

Flutter framework for multi-agent AI orchestration. Build agents that use tools, chain tasks, and talk to each other. Works with any LLM provider & no backend is needed.

On-device Model2Vec text embeddings for Dart & Flutter — a self-contained Rust core via FFI and Native Assets. Fast, local, static, minimal memory.

A Flutter plugin for detecting humans in images using machine learning. Uses TensorFlow Lite for efficient on-device inference.

An advanced, local vector database for Flutter, powered by Rust and HNSW graph indexing.

A comprehensive Flutter plugin for Google AI's LiteRT (TensorFlow Lite) with advanced machine learning capabilities for both Android and iOS platforms.

A Flutter plugin to implement google's standalone ml kit made for mobile platform. Text recognition for Korean has been added from Google-Ml-Kit-plugin v0.7.2

Flutter package for AI agent UIs — AG-UI protocol, SSE streaming, chat panel, HIL forms, AI assistant, and agent run monitor. Bring your own backend.

Backlink helper package for https://www.seedance2ai.app/tools/ideogram.

Fast Fourier Transform (FFT) library that can handle inputs of any size. Includes related tools such as STFT and convolution.

Remove objects from images using machine learning (LaMa Model)

A Dart library for orchestrating multi-agent AI workflows with LM Studio integration. Create agents, manage conversations, execute Python in Docker, and coordinate multi-step pipelines.

A Flutter plugin for accessing TensorFlow Lite, fixed android embedding v2 error. Supports both iOS and Android.

Connect any LLM — Claude, OpenAI, Gemini, Ollama, or a custom proxy — to Google's genui (Generative UI) framework with one Transport.

Extensible Dart toolkit for deterministic prompt composition, localization, validation, and structured rendering.

Hyperpersonalised Mobile App Re-Engagement via Machine Learning for Flutter apps.

A Flutter package for face guidance and automatic face capture using Google ML Kit. Perfect for KYC, attendance, and identity verification apps.

y.js (https://github.com/yjs/yjs) Dart port, a CRDT implementation. CRDTs allow for local, offline editing and synchronization of shared data.

On-device text classification and sentence embeddings using fastText .ftz quantized models via Dart FFI. Verified on Android. Contributions welcome

Library that help construct neural networks (AI) with Dart.

A Flutter plugin for Caf.io solution for document detection. It uses advanced computer vision algorithms to identify and extract documents from photos or camera frames.

A simple and powerful Flutter package for on-device image classification using TensorFlow Lite models. Supports custom models, image resizing, and normalization.

Themeable Flutter widgets for AI chat: streaming markdown bubbles, tool-call cards, a composer, and optional OpenRouter/Gemini providers.

A standalone face recognition extracted from google_ml_kit_plugin.

Flutter plugin for Google ML Kit on-device vision apis. It includes barcode scanning, image labeling, text recognition and face detection.

A flutter widget that show the camera stream and allow ML vision recognition on it, it allow you to detect barcodes, labels, text, faces...

Production-ready Flutter and Dart SDK for Addis AI chat, voice, speech-to-text, and translation APIs.

Clientside token counting + price estimation for LLM apps and AI agents ported to Dart from Python package at https://github.com/AgentOps-AI/tokencost.

Flutter plugin for OnnxRuntime provides an easy, flexible, and fast Dart API to integrate Onnx models in flutter apps across mobile and desktop platforms.

A next-generation, highly customizable Flutter package designed specifically for building AI chat interfaces.

Flutter library and demo app for UDPipe 1 — NLP tokenization, POS tagging and dependency parsing across 50+ languages, with native FFI on desktop/mobile and WebAssembly on the web.

Flutter plugin for on-device text and multimodal generation using Gemini Nano via ML Kit GenAI on Android.

A flutter package project which contains a collection of OpenCV modules.

A Flutter liveness detection library powered by Google ML Kit. Detect live users with configurable probability thresholds via active face challenges.

The extendable AI toolkit for Dart, providing a clean and type-safe interface for working with AI language models, inspired by Vercel's AI SDK for TypeScript.

DeepSeek API client for Flutter with SSE streaming, reasoner model, function calling, and typed errors. BYOK.

A comprehensive toolkit for building AI-powered Flutter applications with multi-provider support, streaming responses, memory management, and extensible tool system.

Lao OCR Scanner (Lao ID Card, Passport, etc...) and Face Liveliness.

A Dart wrapper for whisper.cpp

阿里云智能对话插件的Flutter实现，支持iOS和Android平台。提供语音通话、ASR、TTS等功能。

Dart plugin for implementing Model Context Protocol (MCP) bridge. Provides tools to build MCP bridge that can expose data, functionality, and interaction patterns to LLM applications.

The flutter mediapipe plugin project.

A flutter binding for llama.cpp, which use platform channel.

Bandart (combination of "Bandits" and "Dart") is a library for bandit algorithms in Dart. It provides Bayesian Models for statistical analysis for the data..

A wrapper package for OpenAI assistant by Abel V. Massaley

Flutter plugin for Google's AI Edge SDK, enabling on-device generative AI with Gemini Nano on Android devices.

Pure-Dart OpenAI-compatible inference client for local and hosted LLM servers.

A Flutter package for face detection and recognition using Google ML Kit and TensorFlow Lite, designed for offline capability and customizable overlays.

On-device observability (cost, latency, tokens, errors) for AI/LLM calls in Flutter. Local-first & zero-config, with optional opt-in sync to your backend.

Flutter package for multi-criteria decision-making using AHP, SAW, and TOPSIS algorithms.

Porting Scikit-Learn models to Flutter

This is an unofficial ACR Cloud SDK to recognize sound and music influtter

A customizable AI chat interface for Flutter with markdown and typing animation support.

Google mlkit text recognize plugin, supports Android and IOS.

A comprehensive Flutter package for face liveness detection with ML Kit.

Dart wrapper for Anthropic AI.

On-device emotion inference from biosignals (HR/RR) for Dart/Flutter. Detects Baseline vs Stress using WESAD-trained ExtraTrees ONNX models.

A Flutter plugin for real-time chat model inference using Google's MediaPipe framework. Supports Android and iOS platforms.

Updated version of Lorenzo Calisti's powerdart Compute the Power Spectral Density (PSD) on Dart. This package runs everywhere dart runs.

A Flutter plugin to integrate ChatBot LLM. This Plugin provides a chat interface to interact with the ChatBot LLM.