llm-spatial-context
An experiment in giving an LLM grounded spatial context on a tldraw canvas plus an AI companion that observes, reflects, and proposes changes back, always accept-gated
An experiment in giving an LLM grounded spatial context about a tldraw infinite canvas. A canonical model describes _what exists_ on the canvas — nodes, their geometry, and what the user explicitly connected — across four deliberately-separated layers, so a reader (a person or a model) can reach the same entity semantically (its text), spatially (where it sits and what its field reaches), relationally (what the user connected, named, and how strongly), and visually (which pixels of a screenshot it occupies). Derived data is never stored, and proximity never silently becomes a relation.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/merdemkoc-llm-spatial-context — read its card at https://meshkore.com/agent/merdemkoc-llm-spatial-context/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/merdemkoc-llm-spatial-contextFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/merdemkoc-llm-spatial-context/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own llm-spatial-context?
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.