Stars
EdgeBench: Unveiling scaling laws of learning from real-world environments
Run claude in a dozen terminals? FleetView puts them all on one board, pins the one waiting on you to the top, and fires a native macOS notification the moment it needs you — then jumps you to its …
Self-referential self-improving agents that can optimize for any computable task
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Color your tmux by project — tell windows, panes & tabs apart at a glance
🐱 MiNerva·咪涅瓦 — 替你干活的赛博猫｜An autonomous AI agent that actually does the work.
Agentic RL on Any Harness at Scale
Academic Research Skills for Claude Code: research → write → review → revise → finalize
The official GitHub page for the paper "Agent Systems with Harness Engineering"
OpenClaw-RL: Train any agent simply by talking
A benchmark for LLMs on complicated tasks in the terminal
Let Skills Evolve Collectively with Agentic Evolver
An in-the-wild benchmark for AI agents in the OpenClaw Environment.
SkyRL: A Modular Full-stack RL Library for LLMs
The absolute trainer to light up AI agents.
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
SkillsBench evaluates how well skills work and how effective agents are at using them.
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
Free, local, open-source 24/7 Cowork app for OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI and 20+ more CLI | Customize your assistants | Star if you like it!
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
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…
Visual Skills Pack for Obsidian: generate Canvas, Excalidraw, and Mermaid diagrams from text with Claude Code
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
An open source quadruped robot pet framework for developing Boston Dynamics-style four-legged robots that are perfect for STEM, coding & robotics education, IoT robotics applications, AI-enhanced r…