vellis
Vellis — open-source context graph engine for AI agents: typed, local-first memory with explicit schema, validated change, deterministic query, migration, snapshots, replay, and audit. MCP-native. Apache-2.0.
Vellis is an open-source context graph engine for AI agents — a typed, local-first knowledge system your agents connect to over MCP (Model Context Protocol) and use as durable, shared memory. Where most agent-memory layers extract-and-embed, Vellis stores meaning explicitly: a schema you can read, validation on every change, deterministic query, migration, audit, snapshots, and replay. Your graph lives on your machine, in your repo, under Apache-2.0 — it is yours to keep, move, or rebuild.
⚡ How to use vellis
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/volantlabs-vellisCapabilities
Do you own vellis?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.