HKUDS/OpenSpace

"OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/

What it solves

AI agents often struggle to manage a growing library of skills, leading to poor retrieval of the right tool for a task, repeated mistakes, and a lack of of quality signals to distinguish between reliable and ineffective skills. OpenSpace provides a management layer that allows agents to retrieve, evaluate, and evolve their capabilities based on real-world outcomes.

How it works

OpenSpace acts as a skill management layer that plugs into agents via the Model Context Protocol (MCP). It implements a lifecycle for agent skills through four primary capabilities:

  • Evaluation: It tracks every execution run to monitor whether a skill was successfully applied or replaced by a fallback, using real task outcomes as evidence of quality.
  • Evolution: It allows skills to be updated (FIX, DERIVED, or CAPTURED) based on evidence, with version history and validation to ensure improvements are controlled.
  • Local-First Hub: It uses a local-first architecture where skills are executed locally, but can be discovered and imported from a cloud-based package system.
  • Agent Harness: It provides a runtime environment that captures quality records and manages tool permissions and sandboxing.

Who it’s for

Developers building AI agents (such as those using Claude Code, Codex, or OpenClaw) who need a scalable way to manage, share, and improve the skills their agents possess over time.

Highlights

  • Evidence-Driven Quality: Skills are ranked and trusted based on actual task completion rates rather than just descriptions.
  • Self-Evolution: Agents can improve their own skill library from a "cold run" to a "warm run" by learning from successful workflows.
  • MCP Integration: Compatible with any host that supports the Model Context Protocol.
  • Private Infrastructure: Supports private deployment to keep workflows and data under the user's own control.

Related

  • Project
    zjunlp/SkillNet

    SkillNet is an open‑source platform that lets you discover, generate, evaluate, analyse and route reusable AI‑agent skills. It offers a public catalogue (500 K+ GitHub‑hosted skills), a Python SDK/CLI with six operations (search, download, create, evaluate, analyze, route), a local web UI, and integration points for agents via an MCP server. The system builds a graph of skill relationships and uses LLM‑powered routing (Claude/Codex) to pick the best skills for a task, providing safety/maintainability scores and reasoning.

  • Project
    yaojingang/yao-meta-skill

    A governance and engineering system that transforms rough workflows and prompts into reusable, cross-platform AI agent skill packages with built-in evaluation and release gates.

  • Project
    chujianyun/skills

    A Chinese‑language repo that bundles dozens of reusable “Agent Skills” – small, documented plugins for Claude Code and similar LLM‑agent platforms. Skills cover wiki look‑ups, prompt optimisation, career assessments, diagram generation, document interpretation, audio‑to‑text, image watermarking, web‑scraping, and service run‑books. They are organized under `skills/`, registered in `config/skills.json`, and installed via Claude Code’s marketplace, an installer agent, or the `openskills` CLI.

  • Project
    AMAP-ML/SkillClaw

    SkillClaw is an open‑source system that sits between LLM agents and the LLM API, automatically records interactions, extracts reusable “skills”, deduplicates them, and continuously refines them. It works with many agents (Hermes, Codex, Claude Code, QwenPaw, OpenClaw, etc.) and can share a unified skill library across devices, agents, and team members via local storage, OSS, or S3.

  • Project
    agentsope/SkillAlchemy

    SkillAlchemy is an open‑source framework that automatically builds reusable, installable agent skills from vague task briefs by mining public documentation, papers, and code. It discovers hidden requirements, extracts evidence‑backed procedures, judges their scope, and packages them for LLM agents like Claude Code or Codex. Evaluated on 87 benchmark tasks, it reaches a 55.8 % pass rate, outperforming existing automated skill creators and rivaling human‑curated skills. Install via `npx skills add agentsope/SkillAlchemy` and invoke the agent to generate a skill.