Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

An MCP server that lets LLM agents play Civilization VI.

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Compiles AI agent traces and truns them into reusable context.

A collection of AI agent skills for Clawdbot, Claude Code, Codex

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.

239 evaluated academic Claude/agent skills across 17 research domains (bioinformatics, data science, clinical, social-science methods, Turkish academia & more). Executable eval per skill, deterministic citation verifier, research→write→review→publish pipeline, and a skill-finder front door. Claude Code, Cursor, Codex, Gemini CLI & Copilot.