Stars
DeepSeek Harness: Everything is a Plugin.
Synthetic data generation, post-training, and E2B benchmark evaluation infrastructure.
Official repository for "ReDesign" (ECCV 2026).
The roadmap of long-horizon agents
Vulnerable app with examples showing how to not use secrets
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
EdgeBench: Unveiling scaling laws of learning from real-world environments
An open source trusted cloud native registry project that stores, signs, and scans content.
Measuring and evolving with the frontier of agent work
A benchmark for general-purpose terminal-use agents.
Assign issues to Claude Code, Codex, Cursor, and 17 more coding agents like teammates — open-source and self-hostable.
Qwen-AgentWorld: Language World Models for General Agents
Terminal-Lego: What Makes Interaction Trajectories Effective for Training Terminal Agents?
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
Kimi Code CLI — The Starting Point for Next-Gen Agents
Benchmarking Agents on Real-World Terminal Tasks
Terminal session recorder, streamer and player 📹
an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
This is the repo for the paper TerminalTraj: Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments
Learning Agentic Policy from Action Guidance
[SIGGRAPH 2026] MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation