OpenSpace
Self-evolving skill engine that teaches your AI agents to remember what works
Expert verdict
Ship
3-1The Panel's Take
OpenSpace is an open-source MCP server from HKUDS (the lab behind DeepTutor) that gives AI agents persistent, shareable memory in the form of reusable skills. When an agent completes a task successfully, OpenSpace captures the strategy as a "skill" — a structured template that future agents can query and apply directly, bypassing the need to reason from scratch. Skills are versioned, ranked by success rate, and auto-repaired when they break. The system ships with a cloud skill-sharing registry at open-space.cloud, enabling teams to share and discover skills across agents and projects. A recent update added native adapters for WhatsApp and Feishu messaging. Early benchmarks on GDPVal show a 46% reduction in token usage and 4.2x productivity gains when skill retrieval is available versus cold-start reasoning. For teams running agentic workflows at scale, OpenSpace addresses a real architectural gap: agents today are fundamentally stateless, re-solving problems they've already solved. By converting successful runs into reusable knowledge capital, OpenSpace makes agent networks genuinely compound over time — a meaningful step toward the "improving over time" property that distinguishes a true agent system from a sophisticated LLM wrapper.
Share this verdict
OpenSpace verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/openspace-hkuds-self-evolving-skill-engine-mcp-agents-token-reduction-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Similar Products
Compare OpenSpace with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/openspace-hkuds-self-evolving-skill-engine-mcp-agents-token-reduction-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/openspace-hkuds-self-evolving-skill-engine-mcp-agents-token-reduction-2026" alt="OpenSpace Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/openspace-hkuds-self-evolving-skill-engine-mcp-agents-token-reduction-2026)<iframe src="https://shiporskip.io/embed/openspace-hkuds-self-evolving-skill-engine-mcp-agents-token-reduction-2026" title="OpenSpace ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“The MCP server architecture means I can bolt this onto any existing agent stack without rewiring everything. A 46% token reduction on repeat workflows is a genuine cost win, and the auto-repair for broken skills means less maintenance overhead. HKUDS has a track record with DeepTutor — feels production-ready for v0.1.”
“Skill quality depends entirely on the quality of the tasks they derive from. If your first agent run is mediocre, you've enshrined that mediocrity as a reusable template. The 4.2x productivity benchmark needs independent replication — academic benchmarks rarely transfer cleanly to production workloads.”
“This is the compound interest of AI agents. Today it saves tokens; in 12 months, a mature skill graph trained on thousands of production runs will be a serious competitive moat. The shared registry model could evolve into an open marketplace for agent intelligence that rivals model weights in value.”
“Imagine a skill library that remembers how I like my scripts structured and applies it every time without me re-explaining my style. The memory layer for agents has been the missing piece, and this fills it elegantly — especially now that messaging adapters mean it works in my existing workflow tools.”