Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

OpenDeepWiki is the open-source version of the DeepWiki project, aiming to provide a powerful knowledge management and collaboration platform. The project is mainly developed using C# and TypeScrip…

LLM API 代理与日志追踪系统 - 透明观察智能体行为

大模型推理服务性能调优

AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.

llama.cpp fork with additional SOTA quants and improved performance

LLM inference in C/C++

An easy to use and powerful chaos engineering experiment toolkit.（阿里巴巴开源的一款简单易用、功能强大的混沌实验注入工具）

Luminati HTTP/HTTPS Proxy manager

A high-throughput and memory-efficient inference and serving engine for LLMs

ArcLight: A Lightweight LLM Inference Framework

⚡ Real-time monitoring dashboard for llama.cpp server — single HTML file, zero dependencies. Tracks tok/s, slots, GPU metrics.

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Connect your AI agent to the world — Web search, Social media, Crypto & On-chain data. One plugin, zero extra config.

Copy Fail (CVE-2026-31431): 9-year-old Linux kernel LPE found by Theori's Xint Code

Tongyi Deep Research, the Leading Open-source Deep Research Agent

A wiki designed for both humans and agents to read and write.

A Truman Show of a self-evolving AI coding agent. It writes its own code. Growing up in public.

Build AI Agents, Visually

开源的端到端产品级通用智能体

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or…

Production-ready platform for agentic workflow development.

Your Live2D AI Navigator for every coding mission. Synchronized with ClaudeCode, Copilot and Codex ..)

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

最好用的 V2Ray 一键安装脚本 & 管理脚本

LLM inference in C/C++