Stars
DeepSeek Harness: Everything is a Plugin.
Stealing Reasoning Traces from Proprietary LLM APIs
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
A tiny ~10K-parameter LLM router that learns which open-source model (deepseek-v4-pro / glm-5p2 / kimi-k2p6 via Fireworks) should answer each question and in what role, trained by evolution (sep-CM…
autonomous red teaming platform; multi-agent offensive-security meta-harness
A Python port of Pi’s minimalist coding agent.
Interactive live visualizer for gepa runs
A powerful and user-friendly binary analysis platform!
From isolated agents to shared work
An executable specification language with delightful tooling based on the temporal logic of actions (TLA)
Programmable chat templates for LLM training and inference.
Review-first terminal diff viewer for agentic coders
A kernel library written in tilelang
LLM speculative inference server for consumer & heterogeneous hardware
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Sonic - an OpenAI WebSocket-Mode Compatible Gateway for vLLM
🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autonomous Agent Teams with visual orchestration...
[ICLR 2026] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
AI Coding Factory. Replace your software outsourcing vendor contracts with your own AI.
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.
Background Coding Agents for Manufacturing Example Code
WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.