Stars
Production-grade GPU observability & control toolkit for heterogeneous compute infrastructure
AirLLM 70B inference with single 4GB GPU
Lisp in 99 lines of C and how to write one yourself. Includes 21 Lisp primitives, garbage collection and REPL. Includes tail-call optimized versions for speed and reduced memory use.
Guidelines and notes about useful tools to analyze and optimize code
Clean-room reconstruction of Pencil Blade 1.5 from static evidence, rebuilt with Cocos Creator 3.8.8 and TypeScript.
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.
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audi…
An Open Source implementation of Notebook LM with more flexibility and features
The agent that grows with you
SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi…
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Pi coding agent, as a VSCode extension
Reverse engineering NVIDIA SASS instruction dictionary, kernel audits and pattern recognition across GPU architectures.
Production-grade engineering skills for AI coding agents.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM