- All languages
- ANTLR
- Ada
- AngelScript
- Assembly
- Awk
- C
- C#
- C++
- CSS
- Clojure
- Common Lisp
- Cuda
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- Erlang
- F#
- F*
- G-code
- Go
- Groff
- Groovy
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Jupyter Notebook
- Kotlin
- Lean
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Mathematica
- Mermaid
- OCaml
- Objective-C
- Objective-C++
- OpenQASM
- PDDL
- PHP
- Pascal
- Perl
- PowerShell
- Pug
- Python
- Q#
- R
- ReScript
- Red
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Scheme
- Shell
- Svelte
- Swift
- TeX
- Toit
- TypeScript
- Vim Script
- Zig
Starred repositories
A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
Experimental web-based simulator for exploring metastable behaviors in distributed systems
Official code for the paper: "Multi-User Large Language Model Agents"
你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
将冰冷的离别化为温暖的 Skill,欢迎加入数字生命1.0!Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
[EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
Fara-7B: An Efficient Agentic Model for Computer Use
Code repo for paper: Effective Strategies for Asynchronous Software Engineering Agents
One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Self-referential self-improving agents that can optimize for any computable task
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
Give your AI agent access to your live Chrome session — works out of the box, connects to tabs you already have open
Fast, Sharp & Reliable Agentic Intelligence
AgentIR is a retriever specialized for Deep Research agents.
EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.