Stars
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
Hindsight: Agent Memory That Learns
🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型！A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
Highcharts JS, the JavaScript charting framework
Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI.
A programmable Mixture-of-Models router for heterogeneous LLM inference
Faster Whisper transcription with CTranslate2
The original IBM PC and other machine emulations in JavaScript
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
IronClaw is an Agent OS focused on privacy, security and extensibility
"FastCode: Accelerating and Streamlining Your Code Understanding"
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-re…
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
The open-source alternative to Claude Cowork (powered by opencode)
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up｜Star if you like it!
The framework for building with WebAssembly (wasm). Easily & securely load wasm modules, move data, call functions, and build extensible apps.
WasmEdge is a lightweight, high-performance, and extensible WebAssembly runtime for cloud native, edge, and decentralized applications. It powers serverless apps, embedded functions, microservices,…
🚀 Fast, secure, lightweight containers based on WebAssembly
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.