Labsco
structured-sh logo

emem.dev

from structured-sh

real world, traceable spatial memory for fact verification about the world.

πŸ”₯πŸ”₯πŸ”₯βœ“ VerifiedFreeQuick setup
#memory

emem

emem is a signed, content-addressed spatial memory for AI agents β€” every place-time on Earth resolves to a verifiable fact, read over MCP or REST, no keys, every answer an ed25519 receipt verifiable offline.

Every patch of ground has a 64-bit address (cell64, ~9.55 m at the equator). A fact is keyed by Cell Γ— Band Γ— Tslot and signed by the responder over the BLAKE3 of its canonical CBOR, so the same content id returns byte-identical bytes from any conformant responder and any client verifies the receipt offline. Reads need no auth. For a single-shot answer to a free-text question, call emem_ask: it routes the question to a place, recalls the relevant bands, and runs the applicable algorithms in one call. For a fast, deterministic single-fact read, the locate β†’ recall β†’ verify_receipt chain is the lower-latency path (ask materializes the full topic and can be slower on a cold place). Every spatial call accepts a cell64, a place name, or lat+lng. Canonical surface: 81 MCP tools, 93 documented /v1 paths, 160 algorithms, 46 source schemes.

Connect

  • MCP endpoint: JSON-RPC 2.0 over Streamable HTTP; 81 tools (10 core, 71 extended). Point a client here, no key.

  • OpenAPI 3.1: full machine contract for the /v1 REST surface.

  • Agent card: self-describing card with primitives, band taxonomy, and tool descriptors.

  • Agent card (alias): same card at the conventional discovery path.

  • Quickstart: step-by-step playbook from locate to a verified fact.

  • MCP descriptor: well-known MCP server descriptor for auto-discovery.

Primitives

  • recall: POST cell Γ— bands β†’ signed facts; auto-fetches from open-data upstream on a miss and signs the result. Pass include:["freshness"] for an advisory per-fact Q(Ξ”t) staleness score, or include:["edges"] for typed temporal edges.

  • ask: POST free-text question (+ place) β†’ topic-route β†’ recall β†’ applicable algorithms, in one call.

  • find_similar: POST cell or embedding Γ— k β†’ top-K cosine neighbours over a foundation embedding.

  • verify_receipt: POST a receipt (optionally + the facts you rely on) β†’ {valid, signer}; rebuilds the preimage, checks the signature, and content-addresses any supplied facts against the receipt so a tampered value fails.

  • fact by cid: GET a bare fact_cid β†’ the signed fact bytes; the canonical "I have a fact_cid, what is it" dereference (immutable, cacheable).

  • verify (browser): in-browser ed25519 receipt verifier; no callback to the responder.

  • hunt: POST event Γ— region β†’ ranked hotspots; 12 event keywords (algal_bloom, deforestation, wildfire, flood_extent, …).

  • state: POST cell β†’ dense signed state vector (one encoder, or the full 1792-D cube).

  • memory search: POST query β†’ BGE-768 semantic search over the writable agent-memory layer.

  • memory contradictions: POST β†’ multi-attester contradiction scoring per band kind.

  • memory bundle: POST β†’ a signed, content-addressed bundle of facts (memb:<bundle_cid>).

  • triple_consensus: POST cell β†’ Clay + Prithvi + Tessera change-agreement at one cell; honest inconclusive when an encoder is absent.

  • region_similarity: POST two regions β†’ cosine between their mean GeoTessera embeddings in [-1, 1].

  • tessera_field: POST bbox β†’ a dense Tessera 128-D embedding field for a region, rendered as a colour raster (REST only; a picture, not a signed fact).

  • region_archetype_map: POST bbox β†’ that embedding field clustered into k land-cover archetypes (deterministic k-means) with a legend (REST only).

  • explain: POST an ask response β†’ an UNSIGNED Gemma-4 plain-language reword (signed:false; the signed receipt remains the ground truth).

Reference

  • agents.md: integration guide and ontology for consumer agents.

  • skills.md: composed recipes (locate+recall, find_similar+verify, recall_polygon+solve) as a flat cookbook.

  • reference: the read surface β€” client setup, endpoint tables, primitives summary, the 12-event hunter table.

  • topics: the 27 topic routes that ask uses to map a question to bands.

  • algorithms: 160 composition recipes (flood_risk, walkability, eudr_compliance, …).

  • errors: the structured error codes and their resolution hints.

Optional

  • llms-full.txt: the full machine-readable bundle (this file plus agents.md, spec, and skills) in one fetch β€” larger; prefer this file for a lean ingest.

  • registries: manifest CIDs for the band, algorithm, source, and topic registries.

  • whitepaper: architecture and math (cell64, CID, receipt preimage, memory tokens).

  • gallery: live coverage map, per-place scenes, and the protocol diagrams.

  • demos: runnable end-to-end demos (ask-the-earth, find-similar, recall-polygon, signed-answer).

  • humans: interactive console where every /v1/* call prints in a live log pane.