OpenSpace
"OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving" -- Community: https://open-space.cloud/
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Aug 2026
OpenSpace is a librarian for the skill files your coding agent piles up. Version 2, released in July 2026, dropped the original self-evolving-agent pitch for something concrete: find the right skill, track whether it worked, share the ones that did, retire the ones that did not. All MIT licensed, including the community library at open-space.cloud.
Running it means Python 3.12 or newer, a pip install, and wiring an MCP server into Claude Code, Codex, OpenClaw, or nanobot. Skills and execution stay local, and the cloud is optional. The dashboard is a second install needing Node 20. You bring your own model key, so the running cost is tokens.
Solo developers with a dozen skill files do not need this, and a curated pack like slavingia/skills is a smaller commitment. It pays off once a team shares hundreds of skills and nobody can say which still work.
The catch: this comes out of an academic lab, and its Terminal-Bench 2.1 result, 65.2% cold to 78.7% warm, was run on its own harness. Self-evolving skills mean an agent rewriting its own instructions, and the restrictive policy that limits it to repairs is not the default. The shared library is still thin.
Free vs Self-Hosted vs Paid
fully freeFree
All of it. MIT licensed. The community library at open-space.cloud can be browsed without an account, and uploading or importing skills needs only a free agent key you provision from the CLI with openspace-cloud-auth bootstrap-agent-key. Every local capability (task execution, skill search, evolution) works with no cloud account at all.
Paid
No paid tier, no hosted plan, no seat pricing, no enterprise SKU as of August 2026.
Self-Hosted Costs
Python 3.12 or newer plus a pip install from the repo. The dashboard is a second install requiring Node.js 20 and its own dev server process. The real spend is LLM tokens: OpenSpace runs an agent harness plus an evolution loop that re-analyzes task traces, so an active setup burns noticeably more per task than a bare agent. You supply your own key, so that bill lands with Anthropic, OpenAI, or whoever you point it at.
When to Pay
Nothing to pay the project. Budget for model usage and cap the evolution loop if your provider bills by token.
Free and MIT licensed, cloud included. Your cost is the LLM tokens the evolution loop burns.
What to do by team size
- Solo
- free; skip it until you have more skills than you can remember
- Small team
- free; worth it once two or three people share a skill library
- Medium team
- free; the quality records are the actual reason to adopt it
- Large team
- free; deploy it privately and keep skill data in house
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
Similar Tools
Use Garry Tan's exact Claude Code setup: 15 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Self-referential self-improving agents that can optimize for any computable task
Claude Code skills based on The Minimalist Entrepreneur by Sahil Lavingia
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
Trust Signals
License: MIT License
Use freely, including commercial. Just keep the license.
Commercial use: ✓ Yes
About
- Owner
- ✨Data Intelligence Lab@HKU✨ (Organization)
- Stars
- 7,731
- Forks
- 923
Also by ✨Data Intelligence Lab@HKU✨
Explore Further
More tools in the directory
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
390.5k ★everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
267.1k ★hermes-agent
The agent that grows with you
248.8k ★Featured in The Open Source Drop #2