Stars
- All languages
- Assembly
- Astro
- Bikeshed
- Blade
- C
- C#
- C++
- C3
- CSS
- Clojure
- Crystal
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- F#
- Go
- Groovy
- HCL
- HTML
- Handlebars
- Java
- JavaScript
- Jinja
- Jsonnet
- Julia
- Jupyter Notebook
- Just
- Kotlin
- LLVM
- Lean
- LookML
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- Max
- MiniZinc
- Mojo
- Mustache
- Nim
- Nix
- Nunjucks
- OCaml
- Objective-C
- Odin
- OpenEdge ABL
- PDDL
- PHP
- PLpgSQL
- Perl
- PowerShell
- Prolog
- Python
- R
- Rocq Prover
- Ruby
- Rust
- SQL
- Scala
- ShaderLab
- Shell
- Solidity
- Starlark
- Svelte
- Swift
- TLA
- TSQL
- TeX
- TypeScript
- V
- Vim Script
- Vue
- Zig
ripgrep recursively searches directories for a regex pattern while respecting your gitignore
CheetahClaws (Nano Claude Code): A Fast, Easy-to-Use, Python-Native Personal AI Assistant for Any Model, Inspired by OpenClaw and Claude Code, Built to Work for You Autonomously 24/7.
Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.
✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024
The CLI for AI agents to control Chrome. Zero config, agent-agnostic, battle-tested.
A vector index built on TurboQuant, written in Rust with Python bindings
[ICLR 2026] Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
Data and evaluation scripts for "CodePlan: Repository-level Coding using LLMs and Planning", FSE 2024
A coding agent optimized to smaller LLMs
GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive …
Realistic examples of building evals and optimizing agents with Harbor
This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language
A fast, helpful, and open-source document parser
Smart, Fast & Lossless session compaction for Pi. No LLM calls - produces structured, transcript-preserving summaries using pure extraction and formatting.
Test harness for pi extensions — playbook-based model mocking, session testing, sandbox install verification
SkyRL: A Modular Full-stack RL Library for LLMs
Extension for pi that opens a local two-pane browser workspace for working with prompts, responses, Markdown & LaTeX documents, code files, and other common file types. Comment on and annotate resp…
🧜♀️ Pi extension that renders Mermaid diagrams as ASCII in the TUI, with width-aware output and safe handling for larger diagrams.
Real-time code feedback for pi — LSP, linters, formatters, type-checking, structural analysis
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
"RAG-Anything: All-in-One RAG Framework"
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.