Gnosem

dev.gnosem/gnosemVersion 1.0.0

Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.

Status

Responds143 msNov 14, 2026, 14:26 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:26 UTC
Latency: 143 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://gnosem.dev/mcpResponds143 msNov 14, 2026, 14:26 UTC

No sign-in

Claude Code

claude mcp add --transport http gnosem https://gnosem.dev/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: gnosem
Remote MCP server URL: https://gnosem.dev/mcp

Cursor

{
  "mcpServers": {
    "gnosem": {
      "url": "https://gnosem.dev/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"gnosem","type":"http","url":"https://gnosem.dev/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

6 tools

Tools of Gnosem
	Description		Read-only	Idempotent	Open world
`memory_forget`Soft-delete a memory by id. The row is retained for audit but excluded from search/list and removed from the vector index.	Soft-delete a memory by id. The row is retained for audit but excluded from search/list and removed from the vector index.	Not declared	Not declared	Not declared	Not declared
`memory_list`List the user's most recent memories in reverse chronological order. Use for browsing or catching up on what the user's other model sessions have written recently. Same content/content_raw shape as memory_search. Optional filters (tags, written_by, session_id, since, until) narrow the listing at the SQL level.	List the user's most recent memories in reverse chronological order. Use for browsing or catching up on what the user's other model sessions have written recently. Same content/content_raw shape as memory_search. Optional filters (tags, written_by, session_id, since, until) narrow the listing at the SQL level.	Not declared	Not declared	Not declared	Not declared
`memory_search`Search the user's memories. Default mode is 'hybrid': blends semantic (cosine over Vectorize) and keyword (BM25 over SQLite FTS5) hits via Reciprocal Rank Fusion (k=60). Semantic catches paraphrases; keyword catches exact-string hits (IDs, dates, code snippets). Pass mode:'semantic' or mode:'keyword' to run just one. Content defaults to the LLM-optimized (compressed) form when available (raw:true to invert). Excludes forgotten + superseded. Optional filters narrow after retrieval: tags (AND), written_by, session_id, and/or since/until (ms epoch).	Search the user's memories. Default mode is 'hybrid': blends semantic (cosine over Vectorize) and keyword (BM25 over SQLite FTS5) hits via Reciprocal Rank Fusion (k=60). Semantic catches paraphrases; keyword catches exact-string hits (IDs, dates, code snippets). Pass mode:'semantic' or mode:'keyword' to run just one. Content defaults to the LLM-optimized (compressed) form when available (raw:true to invert). Excludes forgotten + superseded. Optional filters narrow after retrieval: tags (AND), written_by, session_id, and/or since/until (ms epoch).	Not declared	Not declared	Not declared	Not declared
`memory_supersede`Replace a stale memory with a corrected one. The old row is marked superseded and excluded from future reads; the new row becomes the current version. Use for corrections; use memory_forget for pure deletions.	Replace a stale memory with a corrected one. The old row is marked superseded and excluded from future reads; the new row becomes the current version. Use for corrections; use memory_forget for pure deletions.	Not declared	Not declared	Not declared	Not declared
`memory_write`Save a fact, preference, decision, or note to the user's cross-model memory. Any MCP client can read this back later. Include written_by (e.g. 'claude-code', 'gpt-5', 'kimi-k2') for provenance and session_id to group related writes. Long content (>400 chars) is automatically compressed on write to a structured-facts form optimized for LLM reading — the raw text is preserved. Pass no_optimize:true to skip. Writes are deduped by default: (1) SHA-256 of trim(content) short-circuits byte-identical writes with { id, exact_duplicate:true } for free (no embed call); (2) failing that, semantic dedup returns { id, deduped:true, matched_score } when cosine ≥ 0.85. Pass force:true to bypass both, or use memory_supersede to explicitly correct a prior memory.	Save a fact, preference, decision, or note to the user's cross-model memory. Any MCP client can read this back later. Include written_by (e.g. 'claude-code', 'gpt-5', 'kimi-k2') for provenance and session_id to group related writes. Long content (>400 chars) is automatically compressed on write to a structured-facts form optimized for LLM reading — the raw text is preserved. Pass no_optimize:true to skip. Writes are deduped by default: (1) SHA-256 of trim(content) short-circuits byte-identical writes with { id, exact_duplicate:true } for free (no embed call); (2) failing that, semantic dedup returns { id, deduped:true, matched_score } when cosine ≥ 0.85. Pass force:true to bypass both, or use memory_supersede to explicitly correct a prior memory.	Not declared	Not declared	Not declared	Not declared
`memory_write_bulk`Write up to 50 memories in a single call. Each entry runs the same path as memory_write (semantic dedup by default; pass force:true per-entry to skip). Embeddings + optimizations run in parallel; D1 inserts are batched. Returns { results: [...] } with one entry per input in the same order — each is { id, created_at, optimized? } on success, { id, created_at, deduped, matched_score } on dedup, or { error } on failure. Free-tier limits apply to the sum: if adding N would exceed 200, the first (200 - existing) succeed and the rest return an error.	Write up to 50 memories in a single call. Each entry runs the same path as memory_write (semantic dedup by default; pass force:true per-entry to skip). Embeddings + optimizations run in parallel; D1 inserts are batched. Returns { results: [...] } with one entry per input in the same order — each is { id, created_at, optimized? } on success, { id, created_at, deduped, matched_score } on dedup, or { error } on failure. Free-tier limits apply to the sum: if adding N would exceed 200, the first (200 - existing) succeed and the rest return an error.	Not declared	Not declared	Not declared	Not declared

Details

Registry status: Active
Published: Jul 30, 2026
Updated: Jul 30, 2026
Website: https://gnosem.dev/⁠ (opens in a new tab)
Repository: https://github.com/gnosem/gnosem⁠ (opens in a new tab)
Categories (suggested): E-commerce Knowledge and notesSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing