Stars
AI agents running research on single-GPU nanochat training automatically
2026.3.31 claude code 意外把包含源码的文件上传到 npm 仓库，版本号是 2.1.88，其中 cli.js.map 文件有 57MB 的体积，claude code 的源码在该文件的 sourcesContent 字段里面，解压还原后有 70w 行代码
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
ClawHub skill for assistant — let your agent handle customer service, bill negotiations, reservations, and more.
Pine Voice — Your OpenClaw Agent Makes Real Phone Calls
Pine CLI — unified command-line interface for Pine AI
Python SDK for Pine Voice — make real phone calls, handle IVR, and get full transcripts programmatically
Python SDK & CLI for Pine Assistant — negotiate bills, cancel subscriptions, and resolve disputes programmatically
TypeScript SDK for Pine Voice — make real phone calls, handle IVR, and get full transcripts from any Node.js app
TypeScript SDK & CLI for Pine Assistant — negotiate bills, cancel subscriptions, and resolve disputes from any Node.js app
MCP server for Pine Assistant — negotiate bills, cancel subscriptions, and more from Cursor, Claude Code, or any MCP client
OpenClaw plugin for Pine Assistant — end-to-end bill negotiation, cancellations, and dispute resolution via your agent
OpenClaw plugin for Pine Voice — let your AI agent make real phone calls and get transcripts
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Our library for RL environments + evals
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Search, understand, reproduce, and improve an idea with ease
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Steering LLM Thinking with Budget Guidance
Train transformer language models with reinforcement learning.
Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Post-training with Tinker