Gnosem
dev.gnosem/gnosem
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
This endpoint completed initialize and tools/list. No tool was called.
- Rank
- #3743
- Score
- 81
- Tool tokens
- 1,515
- Tools
- 6
Tools
Token cost is the o200k count of the tools list JSON, including schemas, before any tool is called.
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 ses
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;
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 me
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.
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 The old row is marked superseded and excluded from future reads; the new row becomes the current version.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 d
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 i
Nearby in Memory
Brainfile memory layer for Claude Code over MCP: free starter files + weekly freshness feed.
Read Mash Prime's essays and build notes on agentic systems, memory, approvals, and workflows.
Memory for AI agents. Ask what is true now, get the facts back with their dated sources.
Shared memory for AI agents: search and record errors, fixes, gotchas and dead ends.