OpenSpace

OpenSpace makes agent skills self-evolving, running experiments and keeping what works based on results. Instead of static prompt files, skills are living entities that automatically select themselves, monitor their performance, and evolve based on results. Basically, Darwinian selection for agent capabilities.

Three evolution modes: FIX (repair broken skills), DERIVED (create new skills from existing ones), and CAPTURED (learn skills from successful runs). The result is a 46% reduction in token usage and 4.2x higher income compared to baseline agents in their benchmarks. Uses Qwen 3.5-Plus as the backbone LLM.

MIT licensed. Integrates with MCP servers (GitHub, Slack, etc.) and stores evolved skills in a local SQLite database you can inspect.

The catch: the benchmarks are impressive but from an academic lab (HKU). Real-world skill evolution is messier than controlled experiments. The community cloud (open-space.cloud) is new and the shared skill library is still sparse. And 'self-evolving' means your agent's behavior can change in ways you didn't explicitly approve.