ag2: an open-source agentic programming framework for building and coordinating multi-agent systems
AG2 is an open-source programming framework designed for building AI agents and facilitating complex cooperation between multiple agents through a protocol-driven network.
OpenClawChineseTranslation: a localized Chinese distribution of the OpenClaw personal AI assistant platform
A fully localized Chinese distribution of OpenClaw, providing a translated CLI and Dashboard for managing a personal AI assistant platform.
browser-harness: a thin CDP harness that connects LLMs directly to a real browser for autonomous web tasks
A thin, editable CDP harness that connects LLMs directly to a real browser, allowing agents to autonomously write their own helper functions and domain skills to complete complex web tasks.
LangBot: a production-grade platform for building and deploying agentic instant messaging bots
LangBot is an open-source, production-grade platform that allows users to build, manage, and deploy AI-powered agents across multiple instant messaging platforms like Slack, Discord, and WeChat.
opik: an open-source observability and evaluation platform for AI agent tracing and LLM monitoring
Opik is an open-source LLM observability and evaluation platform that provides tracing, evaluation, and monitoring for AI agents and LLM applications.
toon: a token-efficient JSON alternative for LLM prompts that combines YAML-like structure with CSV-style tabular arrays
A compact, human-readable encoding of JSON designed to minimize token usage in LLM prompts while maintaining high retrieval accuracy.
mastra: a TypeScript framework for building and scaling production-ready AI agents and workflows
A TypeScript framework for building and scaling AI agents and applications, providing integrated model routing, graph-based workflows, and production observability.
langfuse: an open-source LLM engineering platform for observability, prompt management, and evaluation
An open-source LLM engineering platform for tracing, monitoring, and evaluating AI applications to streamline the development and development cycle.
repomix: a tool to pack entire codebases into AI-friendly formats
Repomix packs your entire codebase into a single, AI-friendly file to make it easy to feed entire repositories into LLMs for tasks like refactoring or code review.
daily_stock_analysis: an automated stock analysis system that delivers AI-generated decision dashboards via multiple messaging platforms
An automated stock analysis system that uses LLMs to aggregate market data, news, and sentiment to deliver daily decision dashboards and interactive AI agent insights across multiple global markets.
img2threejs: a procedural Three.js model generator that reconstructs objects from images via agent-led sculpting
A tool that converts a single reference image into a procedural, animation-ready Three.js model using a staged, agent-led sculpting pipeline.
Bonsai-demo: highly compressed 1-bit and ternary models enabling local vision and reasoning on consumer devices
A demo repository for running Bonsai, a family of 1-bit and ternary quantized language models that enable vision, reasoning, and tool-calling capabilities on consumer hardware.
agent-chat-ui: a Next.js chat interface for interacting with LangGraph servers
A Next.js chat interface that allows users to interact with any LangGraph server, providing a professional frontend for AI agents.
arxiv-mcp-server: an MCP server for searching, downloading, and analyzing scientific papers from arXiv
An MCP server that enables AI agents to search arXiv, download papers, retrieve LaTeX sections, and perform semantic searches on scientific literature.
img2threejs: a staged sculpting pipeline that reconstructs objects from single images into procedural Three.js code
An agentic pipeline that transforms a single reference image into a procedural, animation-ready Three.js model written entirely in TypeScript code.
off-grid-ai-mobile: a private on-device AI suite providing text, image, vision, and voice capabilities without cloud connectivity
A complete offline AI suite for mobile and Mac that provides text, image, and vision AI, and voice transcription, all running natively on-device for total privacy.
cube-studio: an all-in-one cloud-native machine learning platform
CubeStudio is an open-source, all-in-one cloud-native machine learning platform designed to manage the entire ML lifecycle, from development and training to inference, across diverse hardware and clusters.
ODS: a comprehensive local AI server stack that automates the deployment of inference, agents, and workflows
Osmantic Deployment System (ODS) is an automated installer and management stack that turns local hardware into a private AI server, including inference, agents, RAG, and workflows.
jcodemunch-mcp: a token-efficient MCP server for precise GitHub source code retrieval via tree-sitter AST parsing
An MCP server that uses tree-sitter AST parsing to enable precise, symbol-level code retrieval for AI agents, drastically reducing token costs and context pollution.
data-juicer: a modular data operating system for cleaning, synthesizing, and analyzing multimodal AI datasets at scale
Data-Juicer is a modular data processing system designed to clean, synthesize, and analyze large-scale multimodal datasets for foundation models and AI agents.
mobile: a private on-device AI suite providing text, image, vision, and voice capabilities without cloud connectivity
A complete offline AI suite for Android, iOS, and macOS that provides text, image, and vision AI capabilities entirely on-device for maximum privacy.
open-code-review: OpenCodeReview – AI‑powered, line‑accurate code review for any Git repo
OpenCodeReview is an open‑source CLI that runs AI‑driven code reviews on Git diffs or whole files. It combines deterministic file‑selection logic with a configurable LLM (Anthropic, OpenAI, or custom) to produce precise, line‑level comments. Install via npm or pre‑built binaries, configure a provider, then run `ocr review` (or `ocr scan`) to get automated reviews that are cheaper and more accurate than generic code‑review agents.
SkillOpt: an executive strategy for self-evolving agent skills that optimizes skill documents using deep-learning optimization principles
SkillOpt is a framework that treats agent skill documents as trainable states, using an optimizer model to evolve them through a rigorous training loop without modifying model weights.
MoneyPrinterTurbo: a one-stop AI short-video generator that automates scripting, asset matching, and publishing
An AI-powered short-video generation tool that automatically creates scripts, matches stock footage, and adds voiceovers and subtitles from a simple topic.
javacv: a Java wrapper for popular computer vision and multimedia libraries
JavaCV provides Java wrappers for widely used computer vision and multimedia libraries like OpenCV and FFmpeg, enabling high-performance image and video processing on the Java platform and Android.
CosyVoice: an advanced LLM-based text-to-speech system for zero-shot multilingual speech synthesis
CosyVoice is an advanced, LLM-based text-to-speech system designed for high-quality, zero-shot multilingual speech synthesis and voice cloning.
ReadAny: a local-first AI e-book reader with RAG-powered chat and semantic search
A local-first AI e-book reader that uses RAG and semantic search to help users chat with their library and build a private knowledge base.
kelivo: a cross-platform LLM chat client with multimodal input and MCP tool integration
A cross-platform Flutter-based LLM chat client that provides a unified interface for multiple AI providers, supporting multimodal input and MCP tool integration.
OpenMontage: an agentic video production system that automates research, scripting, asset generation, and editing
An agentic video production system that uses AI agents to automate the entire video creation process, from research and scripting to asset generation and final rendering.
mlx-audio: a high-performance audio processing library for Apple Silicon supporting TTS, STT, and STS
An audio processing library optimized for Apple Silicon that provides fast local text-to-speech, speech-to-text, and speech-to-speech capabilities.
Sana: an efficiency-oriented framework for high-resolution image and video generation supporting up to 4K resolution
An efficiency-oriented framework for high-resolution image and video generation that enables 4K image creation and long-form video generation on consumer hardware.
eidos: an extensible personal data management framework with local SQLite storage and integrated AI capabilities
An extensible personal data management framework that transforms SQLite into a local, Notion-like database with integrated AI capabilities.
outlines: a library for guaranteeing structured LLM outputs via type-constrained generation
A library for guaranteeing structured outputs from LLMs by constraining generation to match specific Python types or Pydantic models.
aiden: an autonomous work engine that plans, executes, and verifies complex multi-step tasks
Aiden is an autonomous AI work engine that can plan and execute multi-step tasks by interacting with your files, terminal, browser, and various APIs.
Speech: a comprehensive toolkit for building and deploying optimized ASR, TTS, and speech-integrated LLMs
A PyTorch-based toolkit for developing and deploying Automatic Speech Recognition (ASR), Text to Speech (TTS), and Speech LLMs, featuring high-performance NVIDIA-optimized models.
ai-agent-book: an open-source book and experimental codebase for mastering AI agent design and engineering
An open-source educational resource consisting of a comprehensive book and a large collection of hands-on experiments for learning AI agent design and engineering.
council-of-high-intelligence: a structured multi-perspective deliberation framework for high-stakes decision making
A structured multi-perspective deliberation framework that uses diverse AI personas to challenge assumptions and reach high-stakes decisions through adversarial reasoning.
harbor: a CLI and companion app for effortlessly spinning up a complete local LLM stack
Harbor is a CLI and companion app that automates the deployment of a complete local LLM stack, including inference engines, web interfaces, and agentic tools.
FastVideo: a unified post-training and real-time inference framework for accelerated video generation
A unified post-training and real-time inference framework designed to accelerate video generation through sparse attention and distillation techniques.
gpustack: an open-source GPU cluster manager for AI model serving and instance provisioning
An open-source GPU cluster manager for AI model serving and instance provisioning that orchestrates inference engines across hybrid environments.
pennylane: an open-source software platform for quantum computing, machine learning, and quantum chemistry
PennyLane is an open-source software platform designed for quantum computing, quantum machine learning, and quantum chemistry, enabling users to build and implement quantum algorithms across various hardware devices.
SwanLab: a professional AI training analysis platform for metric observation and experiment tracking
An AI training analysis and observation platform that provides training visualization, automatic logging, and experiment comparison for model training teams.
khazix-skills: a collection of standardized instruction sets to extend AI agent capabilities for system utility, research, and writing
A collection of standardized AI agent skills for tasks like disk cleanup, AI news tracking, project documentation synchronization, and deep research reports.
ailia-models: a verified library of 400+ pre-trained models for high-speed cross-platform AI inference
A collection of over 400 pre-trained AI models optimized for the ailia SDK to enable high-speed, cross-platform inference across various hardware and operating systems.
forkd: a microVM sandbox runtime for AI agent fan-out that enables near-instant spawning of warmed environments
A microVM sandbox runtime for AI agent fan-out that uses snapshot copy-on-write to spawn hundreds of isolated, warmed runtimes in milliseconds.
OmniRoute: an AI gateway that aggregates hundreds of providers into a single endpoint with automatic fallback and token compression
OmniRoute is an AI gateway that aggregates hundreds of LLM providers into a single endpoint, offering automatic fallback, token compression, and unified management of free tiers.
CyberStrikeAI: an AI-native cybersecurity platform for automated security operations and attack-chain modeling
CyberStrikeAI is an AI-native cybersecurity platform that uses autonomous agents and orchestration to automate security testing, vulnerability management, and attack-chain analysis.
Olares: an open-source personal cloud OS for running AI agents and LLMs on owned hardware
Olares is an open-source personal cloud operating system that enables users to run AI agents and LLMs locally on their own hardware using Kubernetes.
self-hosted-ai-starter-kit: a Docker Compose template for quickly initializing a self-hosted local AI and low-code development environment
A Docker Compose template that bundles n8n, Ollama, and Qdrant to quickly set up a self-hosted, local AI development environment for building AI agents and workflows.
orca: an AI orchestrator for running multiple CLI agents in parallel worktrees
Orca is an AI orchestrator that allows developers to run multiple CLI agents in parallel across isolated git worktrees, featuring a desktop app and a mobile companion for remote monitoring.