A
licenseA
qualityA
maintenanceA local MCP server that gives AI assistants a long-term memory by capturing sessions verbatim and surfacing relevant context automatically.
15
912
MIT
crbro-memory
by Octonove
Related Servers
Alternatives to crbro-memory
- AlicenseAqualityAmaintenanceHosted memory for AI agents that learns from outcomes, with shared rooms. One key across Claude, Cursor & ChatGPT.111,161 npm27MIT
- AlicenseAqualityAmaintenanceMulti-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.10MIT
Related Servers
- AlicenseAqualityAmaintenanceA fully local MCP server that gives AI agents persistent, semantic long-term memory without any cloud dependencies.11216 npm1MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides AI agents with persistent, multi-layered memory inspired by the human brain, including consolidation, self-reflection, and generative replay.1MIT
- AlicenseNot gradedqualityDmaintenanceA self-hosted MCP server that gives AI agents persistent, searchable memory with importance scoring, knowledge graphs, and autonomous memory consolidation.1MIT
- AlicenseNot gradedqualityDmaintenanceA local MCP server that gives AI coding agents persistent memory and context across sessions.3 npmMIT
- FlicenseNot gradedqualityDmaintenanceAn advanced MCP server that gives AI assistants persistent memory with machine-learning-powered semantic understanding, enabling branching memory, semantic search, and project analysis.-
- AlicenseNot gradedqualityCmaintenanceA local-first MCP server that gives AI assistants long-term memory by storing, searching, and recalling notes as Markdown files on your machine.5 npmMIT
TDQS
A4.4/5.0
Scored across 15 tools
Disambiguation4/5
The set has several families that could collide on purpose alone — read paths (boot, recall, inspect, map, audit), write lifecycles (learn, revise, forget) and team tools (space, share) — but every description explicitly draws the boundary, e.g. 'to search by content use crbro_recall', 'atomic facts belong in crbro_learn — the map is the prose around them', and the staged lifecycle wording. A careful agent can pick correctly, though the dense cross-referencing is needed because a few pairs (recall vs inspect, context vs learn) are genuinely close.
Naming Consistency4/5
All tools share a uniform crbro_ namespace in lowercase snake_case single tokens, with no camelCase or style mixing. The only deviation is that some names are verbs (learn, recall, revise, forget, consolidate) and others nouns (context, map, secret, space, maintenance), so there is no single verb_noun grammar even if the surface reads consistently.
Tool Count4/5
Fifteen tools sit at the top of the comfortable band, and each maps to a real function: memory CRUD, session lifecycle, synapse linking, map, housekeeping, audit, secrets, and team sharing. It is slightly heavy — reads alone are spread across boot, recall, inspect, map and audit — but nothing looks gratuitous for a persistent-memory server.
Completeness5/5
Coverage is unusually thorough: full lifecycle (learn create, revise supersede/retire, forget quarantine/restore/merge), multiple read surfaces (boot, recall, inspect, map, audit), connections, context/pending tasks, session logging via consolidate, maintenance, OS-keychain secrets, and team-space create/join/sync/leave/share. No obvious dead end — even destructive and sharing operations have dry-run plus confirm-token paths.
Maintenance
ActivityActive
ResponsivenessNo issues