Gnosem
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
| Endpoint | https://gnosem.dev/mcp (streamable-http) |
|---|---|
| Registry version | 1.0.0 |
| Now | 6 tools · grade C (75) · pin ts_c8655b195f1b4c8ede102c9d50a19cee · protocol 2025-06-18 |
| First / last listed | 2026-11-10 01:06 UTC / 2026-11-10 01:06 UTC |
| Grade over time | 2026-11-10: C (75), 6 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: memory_write memory_search memory_list memory_forget memory_supersede memory_write_bulk
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 params: content*, tags, written_by, session_id, no_optimize, force |
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 params: query*, k, mode, raw, tags, written_by, session_id, since, until |
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. params: limit, cursor, raw, tags, written_by, session_id, since, until |
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. params: id* |
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 The old row is marked superseded and excluded from future reads; the new row becomes the current version.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. params: old_id*, new_content*, tags, written_by, session_id |
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 { params: memories* |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.