ContextForge is an open‑source gateway that federates MCP, A2A, REST and gRPC services into a single, centrally governed endpoint for AI agents and tools. It provides auth, rate‑limiting, OpenTelemetry tracing, a plug‑in system, and an admin UI, and can be run via PyPI, Docker, or Helm.

Liza is a multi-agent orchestration system for software delivery that uses behavioral contracts and adversarial review to produce production-ready code with minimal human intervention.

An open-source semantic layer that defines metrics and business logic once in code and exposes them via APIs for BI tools and AI agents.

An environment and benchmark for building and testing autonomous agents that can control Android devices across a wide variety of real-world apps.

A privacy-focused native desktop AI toolkit that unifies multiple LLM providers, local RAG, and autonomous agent workflows into one offline-capable application.

An automated A-share short-term review dashboard that combines hard sentiment indicators with a multi-agent AI system to synthesize daily market judgments.

A ComfyUI extension for MiniMax H3 that enables seamless chaining of video and audio clips by using latent-based continuity to prevent quality loss and motion and sound jumps.

A serverless Web SSH terminal based on Cloudflare Workers that allows users to manage remote servers directly from a browser with built-in SFTP and AI assistance.

A high-performance code quality analyzer for Python that helps maintain AI-generated code through structural analysis, complexity metrics, and AI agent integration.

A shared visual medium that turns Unicode text into a canvas for humans and and editable tokens for AI agents to collaborate on visual layouts.

An open agentic coding system that uses multi-agent systems to transform natural language and research papers into production-ready code.

Bindu is an open‑source framework that turns any LLM‑based agent into a secure, identity‑verified, payment‑enabled internet service. It provides built‑in mTLS, DID signatures, OAuth2 via Hydra, USDC (x402) payment enforcement, skill advertising, push notifications, and polyglot SDKs (Python, TypeScript, Kotlin). With a single `bindufy()` call you get a JSON‑RPC endpoint, optional public tunneling, and deployment helpers, making it easy to build swarms, paid APIs, or regulated B2B agent integrations.

A framework for efficient LLM inference and fine-tuning that uses CPU-GPU heterogeneous computing to run ultra-large MoE models on consumer hardware.

A tool that allows AI agents to build and maintain a persistent, interconnected markdown knowledge base (a "second brain") from chat logs and documents.

An AI-powered VS Code extension that acts as an autonomous development team, providing code generation, debugging, and codebase intelligence.

A concise domain-specific language and compiler built on TVM for developing high-performance GPU and CPU kernels like GEMM and FlashAttention across multiple hardware backends.

An open-source world simulator that generates high-fidelity, interactive video environments with real-time interactivity and long-term temporal consistency.

A tool for automatically generating themed image cards from Markdown and publishing them as notes to Xiaohongshu.

An open-source robotic arm project providing complete hardware blueprints and software stacks to lower the barrier for learning and deploying Embodied AI.

A library providing state-of-the-art parameter-efficient fine-tuning methods to adapt large pretrained models using minimal compute and storage.

A library for efficient similarity search and clustering of dense vectors, capable of handling billion-scale datasets using CPU and GPU acceleration.

A multi-platform video distribution tool that enables batch publishing and automated uploads to 8 major social media platforms via GUI, CLI, and HTTP API.

A deployment framework for running a persistent, 24/7 Claude Code agent with a real browser on your own VPS, controllable via Telegram.

Code World Model is a framework that positions a coding agent as a world brain to better understand and manipulate its operating environment.

An advanced 3D Gaussian Splatting renderer for THREE.js that enables high-performance, cross-device rendering of splat-based 3D scenes.

An open delivery harness for coding agents that turns AI-generated code into a structured software delivery loop with stateful tracking and context routing.

A library of hardware-efficient building blocks and optimized kernels for linear attention, state space models, and hybrid LLM architectures.

A lightweight bot that bridges Feishu/Lark messenger with local Claude Code or Codex CLI, enabling chat-based interaction with local coding agents.

Open Multi‑Agent (OMA) is a TypeScript framework for orchestrating dynamic teams of LLM agents inside Node.js apps. It builds a task DAG at runtime from a high‑level goal, executes the plan with optional human approvals, records the full trace for inspection or replay, and supports any LLM provider, tool gating, budgets, and OpenTelemetry integration.

A tool and field guide designed to identify and remove generic, AI-generated design patterns (AI slop) from web projects.

NCCL is a library of optimized communication routines for GPUs that enables high-bandwidth data exchange across single or multiple nodes using PCIe, NVLink, and InfiniBand.

A Python library that simplifies integration with Ollama, enabling developers to chat with, manage, and generate embeddings from LLMs locally or in the cloud.

A self-hosted infrastructure monitoring workspace for Proxmox, Docker, Kubernetes, and TrueNAS that uses AI-powered health checks to identify system failures and capacity pressure.

An open-source UI component library built on Ant Design specifically designed for creating AIGC web applications.

A tabular foundation model that provides high-accuracy classification and regression in a single forward pass, removing the need for iterative training and manual preprocessing.

A deployable starter kit for building virtual towns where AI characters socialize, featuring a JS/TS framework and support for multiple LLM providers.

A keyboard-first Markdown notes app that stores notes as plain files and features Vim motions, MCP integration for AI tools, and self-hosting options.

A desktop skill manager for AI coding tools that centralizes the installation, synchronization, and management of skills, MCP servers, and plugins across multiple AI agents.

A security evaluation framework for generative AI that provides evidence-based safety testing for LLMs, RAG apps, and AI agents.

Burn is a comprehensive deep learning framework and tensor library in Rust that unifies training and inference in a single codebase for seamless deployment across diverse hardware.

An AI coding agent optimized for minimal context token usage and high performance, featuring a fast TUI and support for numerous LLM providers.

A family of open-source speech and sound generation models providing high-fidelity TTS, multi-speaker dialogue, voice design, real-time streaming, and sound effect generation.

An open-source cryptocurrency trading bot with a visual interface that automates strategies using AI, technical indicators, and TradingView signals across 15+ exchanges.

A real-time, instruction-guided video editing system that uses autoregressive diffusion to edit live video streams or uploads as frames arrive.

An MCP server that enables AI assistants to search, create, and update content in Jira and Confluence across Cloud and Server/Data Center deployments.

EvalScope is a Python‑based, all‑in‑one evaluation framework for LLMs, vision‑language, embedding, and agent models. It runs dozens of benchmarks, provides stress‑testing (latency, throughput), supports multi‑turn agent loops with tool calling, and visualises results in an interactive web dashboard. Install with `pip install evalscope` and evaluate a model via a single CLI command or a few lines of Python.

A tool that extracts a complete design system from any live website, generating developer-ready tokens, Tailwind configs, and Figma variables.

A plugin for OpenCode that automatically reduces token usage by compressing stale conversation context into technical summaries and removing redundant tool calls.