Lightweight Long-Term Memory for LLM Agents.

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

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.

LLM agents as your hyperparameter optimizer.

Official Findings of EMNLP 2026 implementation of Corpus2Skill: compile a document corpus into a navigable skill hierarchy that LLM agents explore at query time, with document lookup instead of a serving-time vector-search service.

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

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.

MCE: Clone Human Souls with LLM Native Agent Skills | 基于 LLM Agent Skills 的心智克隆工程 | Agent Skills | Mind Skills | Mind Clone

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.

MCP server for the Live Tennis API — give Claude, Cursor and other LLM agents real-time tennis scores, odds and model win-probability

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Durable, searchable memory of your past agent sessions.

A framework for discovering, compiling, and validating reusable skills for scientific agents.

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex

🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.

The LLM Council works together to answer your hardest questions

Writing is thinking! WIT provides skills for scientific thinking and writing!

Learn AI and LLMs from scratch using free resources

A Python library for building AI agents that leverage the full power of Google Antigravity.

An MCP server for converting Markdown to interactive mind maps with export support (PNG/JPG/SVG).