Highlights
- Pro
Starred repositories
Towards a More Autonomous Agent System
A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks
DeepSeek Harness: Everything is a Plugin.
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc…
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Production ready toolkit to run AI locally
🙌 OpenHands: AI-Driven Development
An End-to-End Infrastructure for Training and Evaluating Various LLM Agents
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
[FSE'2026] SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
A simple yet powerful agent framework that delivers with open-source models
[NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents
Renderer for the harmony response format to be used with gpt-oss
Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
A General, Accurate, Long-Horizon, and Efficient Mobile Agent driven by Multimodal Foundation Models
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environment…
AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.
A PyTorch native platform for training generative AI models
PyTorch native quantization for training and inference
slime is an LLM training framework for RL Scaling.
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.





