PaperOrchestra is a multi-agent framework for automated AI research paper writing.

Skills for Real Engineers. Straight from my .claude directory.

Use Codex from Claude Code to review code or delegate tasks.

Lightweight coding agent that runs in your terminal

WayFlow is a powerful, intuitive Python library for building sophisticated AI-powered assistants. It is a reference runtime for Agent Spec, with native support for all Agent Spec Agents and Flows.

[ICLR 2026 Oral] BIRD-INTERACT: Re-imagines Text-to-SQL evaluation via lens of dynamic interactions.

Open Agent Spec (Agent Spec) is a framework-agnostic declarative language for defining agentic systems. It defines building blocks for standalone agents and structured agentic workflows as well as …

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Vane is an AI-powered answering engine.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

META‑AGENTIC α‑AGI 👁️✨ — Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡

GitHub's official MCP Server

Repo for data synthesis and filtering techniques of Code LLMs, covering papers, datasets, benchmarks, and papers etc.

Official style files for papers submitted to venues of the Association for Computational Linguistics

LLM inference in C/C++

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

Build production-ready AI agents in both Python and Typescript.

🙌 OpenHands: AI-Driven Development

AdalFlow: The library to build & auto-optimize LLM applications.

macOS system monitor in your menu bar

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Efficient Triton Kernels for LLM Training

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Awesome-LLM-Prompt-Optimization: a curated list of advanced prompt optimization and tuning methods in Large Language Models

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Scrapy, a fast high-level web crawling & scraping framework for Python.

Go ahead and axolotl questions

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.