We believe the best way to advance AI engineering is to share what we learn. Our open source work is contributed back to the communities that make this work possible.
Graph-enhanced AI skill database for the OpenClaw community
View Project →OpenClaw Graph is AlphaOne's contribution to the open source OpenClaw project — a graph database layer that fundamentally transforms how AI agents discover, relate, and invoke skills. By replacing flat skill registries with a graph-native architecture, agents gain multi-hop reasoning across skill relationships, cluster-aware discovery, and dramatically reduced token consumption.
The project demonstrates our core belief that context architecture — not model selection — is the differentiator in production AI systems. Graph databases provide the structural foundation for scoped, efficient, and relationship-aware context assembly.
Traditional AI skill registries are flat lists — the agent must scan everything to find what it needs, consuming tokens proportional to the registry size. Graph databases change the fundamental economics.
Skills are connected through typed edges — dependencies, compositions, alternatives, and cluster memberships. Instead of scanning a flat list, agents traverse relationships to find exactly what they need in logarithmic time.
Related skills are grouped into semantic clusters. When an agent needs capabilities in a domain, it retrieves the relevant cluster — getting a coherent, pre-organized context window instead of pulling individual skills and hoping they compose well.
Graph traversal enables agents to reason across skill relationships — "if I need skill A, I also need its dependencies B and C, and there's an optimized alternative D." This compositional reasoning is impossible with flat registries.
Graph queries naturally enforce scope boundaries. Agents retrieve only the subgraph relevant to their current task — no over-fetching, no token waste on irrelevant context. This is context assembly, not context accumulation.
The 229% token cost reduction comes from multiple optimization layers working together — what we call the TOON (Token-Optimized Operation Network) approach.
Graph queries return precisely scoped subgraphs instead of bulk skill dumps. Agents receive only the context they need for the current task — eliminating the token overhead of transmitting entire registries.
Graph edges encode relationships that would otherwise require verbose natural language descriptions. A single edge replaces paragraphs of context about how skills relate — compressing the context window without losing information.
Frequently accessed subgraphs are pre-materialized. Common agent workflows hit warm caches instead of executing fresh graph queries — reducing both latency and the token cost of re-computing context.
Instead of loading all skill details upfront, the graph serves summaries first and full definitions on demand. Agents decide what to expand based on initial traversal — paying token costs only for what they actually use.
We're always looking for contributors and partners who share our commitment to building better AI infrastructure in the open.
sales@alpha-one.mobi