Lists (8)
Starred repositories
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
CodeScientist: An automated scientific discovery system for code-based experiments
Robin: A multi-agent system for automating scientific discovery
Biomni: a general-purpose biomedical AI agent
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.
The batteries-included agent harness.
Public daily retrospectives and engineering notes from gaebal-gajae
HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.
The best-benchmarked open-source AI memory system. And it's free.
Official repository for LongMemEval-V2
Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)
This solution will help you (and your AI agent) understand any given codebase with ease, conciseness and precision.
Standalone repo for our Atropos integration with Thinking Machines Tinker API (https://thinkingmachines.ai/tinker/)
The open agent skills tool - npx skills
mkdir for agents - agent-optimized & read-only virtual folder
Absorb the jitter in your requirements. A spec-first workflow harness that buffers ambiguity before it reaches your AI coding agent.
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
A personal AI workforce that runs on one Resident. It handles what it can, delegates the rest to Workers, and a System Governor makes the whole thing smarter over time — without trusting self-report.
ouroboros native cli with seamless mcp orchestration