AI 开源项目

LeanKG: Stop Burning Tokens. Start Coding Lean.

[ICML 2026] GRACE-VLM: deployable INT4 Qwen3-VL via quantization-aware distillation.

Independent ground-up Rust reimplementation of SQLite with concurrent writers and information-theoretic durability

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

AI Agent 面试知识库 100 题 | 涵盖 Agent 架构、RAG、工具使用、多 Agent、记忆、规划推理、提示工程、评估、安全对齐、生产部署、框架选型

This document curates open-source projects, academic papers, capability benchmarks, and commercial solutions (international & China) in AI penetration testing, LLM red teaming, autonomous offensive agents, and vulnerability discovery—aimed at helping researchers, security engineers, and enterprise decision-makers quickly form a holistic view.

为专业创作者而生的 ComfyUI 现代化管理平台

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

Free, local, open-source LLM cost analyzer - see where your LLM bill leaks, on your machine.

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

暂无项目简介。

😎 A curated collection of real-world Minis use cases, workflows, and creative scenarios — contributed by the community

Run multiple account profiles for AI coding tools simultaneously instead of switching accounts.

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.

Opptrix — AI驱动的全球多市场投研工作台 | Open-source LLM research assistant for China A-shares. 170+ MCP tools, factor screening, backtest, watchlist & Electron desktop. TypeScript · React · Fastify monorepo.

Persistent memory for AI coding agents

Curated map of AI agent frameworks, protocols, runtimes, skills, memory, identity, security, evaluation, and commerce.

Self-hosted remote approvals + live monitoring for Claude Code / Codex — via Telegram, Feishu, or a web terminal. Any subscription or API key.

High performance multithreaded task execution and optimization engine for agents and dweb apps

The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing

Jarvis for your coding agents — the voice layer for Claude Code, Codex, OpenClaw, Hermes & any AI workflow. Your agent speaks; you talk back hands-free.

Ultimate zero-dependency compound knowledge system for AI agents. Auto-extract, classify, search, and maintain memory in plain Markdown.

A curated list of awesome LegalTech resources - open source platforms, AI models, MCP servers, companies, datasets, and tools for the global legal ecosystem.

A timeline editor for MiniMax H3 inside ComfyUI - storyboard prompts, first/last keyframes, image/video/audio references, joint audio, live sampling preview, retakes and shot chaining.