CogmemAi: Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory
If you already use Cogmemai MCP, the cogmemai mcp mcp server is the piece that lets your assistant work with it directly. CogmemAi: Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory benchmark) and 91% on LoCoMo (above human performance). Autonomous memory capture: your Ai's work.
CogmemAi is a portable memory layer that gives any Ai system persistent recall across sessions, devices, users, and teams — and captures knowledge autonomously, even when your Ai forgets to save. 95.10% accuracy on LongMemEval — top published score on the field's hardest long-term memory benchmark. 91% on LoCoMo, above human performance (87.9%). Quantum-safe encryption. Works with Claude Code, Cursor, Windsurf, Cline, Continue, and any MCP-compatible tool. Switch editors, switch models, switch machines — your knowledge stays. Not just one score on a test — the most complete Ai memory system available.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
preflight — Proactive recall. Fast recall to check prior context before making any suggestionsave_memory — Store a fact explicitly (architecture decision, preference, etc.)recall_memories — Search memories using natural language (semantic search)extract_memories — Ai extracts facts from a conversation exchange automaticallyget_project_context — Load top memories at session start (with smart ranking, health score, and session replay)list_memories — Browse memories with filters (paginated, with untyped filter)update_memory — Update content, importance, scope, type, category, subject, and tagsdelete_memory — Permanently delete a memorybulk_delete — Delete up to 100 memories at oncebulk_update — Update up to 50 memories at once (content, type, category, tags, etc.)get_usage — Check your usage stats and tier infoexport_memories — Export all memories as JSON for backup or transferConfiguration is passed through the environment: COGMEMAI_API_KEY, COGMEMAI_MODE. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Cogmemai MCP's toolset — preflight, save_memory, recall_memories and 11 more — is a fair guide to whether it matches your workflow. It is maintained by hifriendbot; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Cogmemai MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| preflight | **Proactive recall.** Fast recall to check prior context before making any suggestion |
| save_memory | Store a fact explicitly (architecture decision, preference, etc.) |
| recall_memories | Search memories using natural language (semantic search) |
| extract_memories | Ai extracts facts from a conversation exchange automatically |
| get_project_context | Load top memories at session start (with smart ranking, health score, and session replay) |
| list_memories | Browse memories with filters (paginated, with untyped filter) |
| update_memory | Update content, importance, scope, type, category, subject, and tags |
| delete_memory | Permanently delete a memory |
| bulk_delete | Delete up to 100 memories at once |
| bulk_update | Update up to 50 memories at once (content, type, category, tags, etc.) |
| get_usage | Check your usage stats and tier info |
| export_memories | Export all memories as JSON for backup or transfer |
| import_memories | Bulk import memories from a JSON array |
| ingest_document | Feed in a document (README, API docs) to auto-extract memories |
{
"mcpServers": {
"cogmemai": {
"command": "npx",
"args": ["-y", "cogmemai-mcp"],
"env": {
"COGMEMAI_API_KEY": "your-value",
"COGMEMAI_MODE": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| COGMEMAI_API_KEY | Credential the server authenticates with. | Yes |
| COGMEMAI_MODE | Configuration value read at startup. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.