Personal Memory MCP
Related Servers
Alternatives to Personal Memory MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables coding agents and other MCP clients to read and write the same durable facts in a local SQLite memory, searched by embedding plus full text and separated into global and per-repository scopes, with a browser notebook and ZIP backup/migration. Runs over stdio or HTTP, keeping search on-machine and secrets redacted before storage.MIT
- AlicenseNot gradedqualityAmaintenanceEnables coding agents to store and retrieve source-backed context locally in SQLite, with FTS5 search, optional reranking, and stdio MCP tools.MIT
- AlicenseBqualityCmaintenanceLocal-first knowledge system for reasoning agents, exposing facts, evidence, documents, retrieval, and audit history through a thin stdio MCP server.14MIT
- AlicenseNot gradedqualityAmaintenanceProvides a local stdio MCP server that gives AI coding agents a typed, temporal, evidence-backed memory on embedded SQLite, letting them record decisions and constraints, ask why something happened, navigate memory by time, trace proof paths between refs, and export or supersede stored state without rewriting it. It also exposes read-only ChronoLoom view tools so a person and their agent can steer the same multidimensional memory view by semantic intent rather than raw coordinates.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables development agents to keep persistent memory: proposing and reviewing workspace-scoped content, running hybrid search over accepted sources, and resuming projects with auditable history and provenance. It exposes 32 MCP tools over stdio and authenticated Streamable HTTP, with optional embeddings and rerank.Apache 2.0
- AlicenseNot gradedqualityDmaintenancePersonal memory MCP server backed by SQLite FTS5 BM25 search with temporal reranking.16 npm1MIT
TDQS
Scored across 3 tools
Each tool has a distinct role: search retrieves answer content, history audits revisions/tombstones, and status reports configuration. Search and history both perform temporal memory lookups, so an agent could occasionally confuse them, but the descriptions explicitly demarcate answer context versus audit data.
All three tools use the same memory_ prefix with a short noun-like suffix, giving a clear and predictable pattern. No mixing of conventions or verb styles.
Three tools is on the low side but each maps to a genuinely different capability (retrieve, audit, diagnose). The thinness is acceptable for a focused read-oriented memory interface, though it borders on under-scoped.
The surface is entirely read-only: there is no tool to store, update, or delete a memory, so the core write lifecycle of a personal memory system is absent. The mention of 'write availability' in status hints at writes happening elsewhere, which agents cannot invoke through this server.