Stars
- All languages
- Assembly
- Awk
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Common Lisp
- Crystal
- D
- Dart
- Dockerfile
- Emacs Lisp
- Erlang
- Go
- HCL
- HLSL
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Jsonnet
- Jupyter Notebook
- Kotlin
- Lua
- MDX
- Makefile
- Markdown
- Nu
- Objective-C
- Odin
- PHP
- Perl
- Python
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Solidity
- Swift
- TSQL
- Tree-sitter Query
- TypeScript
- Vim Script
- Vue
Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.
Skills for Real Engineers. Straight from my .agents directory.
Free, open-source scouting tool for Football Manager 27 and 26, on Windows and Mac. Reads your whole save (60k+ players and staff) in seconds: real CA/PA, hidden attributes, instant filters, role r…
Build a coding agent from scratch, one harness primitive at a time. 15 chapters (ch-00..ch-14), each green on two gates.
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.
An open source soccer/football manager game
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
⛰️ LifeOS — The AI-powered Life Operating System that helps you hill climb to wherever you're going.
A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every query.
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"
A pre-built A2A Agent Executor for LangGraph Python
A UI for the A2A protocol built with Next.js and Material UI
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Sample application to demonstrate Google ADK and A2A interoperability. For informational purposes only.
Collection of leaked system prompts
Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.
CodeMachine is an open-source tool that orchestrates AI coding agents into repeatable, long-running workflows. ⚡️
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
🧱 easy, fast, programmable and local-first microVM runtime and library
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
An open-source AI coding agent that lives in your terminal.
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖
OODA Loop AI Agents - Observe, Orient, Decide, Act framework for systematic problem-solving. Built by AstroMVP to help startups ship AI products fast 🚀