Stars
The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled.
Fast, powerful, git-native ticket tracking in a single bash script. Dependency graphs, priority levels, zero setup.
Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured
Tree-sitter-powered code indexing server that gives LLM agents precise, on-demand access to symbols, implementations, callers, tests, and grep across multi-language projects - so they explore codeb…
slime is an LLM post-training framework for RL Scaling.
Debug your GitHub Actions via SSH by using tmate to get access to the runner system itself.
Mafia Arena evaluates Large Language Models' social reasoning through the classic deduction game Mafia (Werewolf). Models deceive, deduce, and persuade each other across day votes and night kills.
An open-source AI Voice Agent that integrates with Asterisk/FreePBX using Audiosocket/RTP technology
OpenTinker is an RL-as-a-Service infrastructure for foundation models
Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.
Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLMs to engage in public conversation before secretly picking a…
A turnkey OAuth & authentication system, designed for both Cloudflare Workers and Node.js
A simple framework for humans Server-first React, running on the Cloudflare platform. Simple to build. Easy to maintain.
ACE-Step: A Step Towards Music Generation Foundation Model
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Konva.js is an HTML5 Canvas JavaScript framework that extends the 2d context by enabling canvas interactivity for desktop and mobile applications.
CLI tool to add @ts-expect-errors to typescript type errors
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL