ihmt-memory
Related Servers
Alternatives to ihmt-memory
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenanceProvides long-term memory for AI coding agents, enabling facts like stack, conventions, and decisions to be recorded once and recalled across sessions.8344 npmMIT
- AlicenseNot gradedqualityAmaintenancePersistent memory for AI coding agents that knows when it has gone stale.3MIT
- AlicenseAqualityAmaintenanceProvides coding agents with persistent, evidence-backed project memory and knowledge across sessions, using a structured memory tree and local knowledge base.6126MIT
- AlicenseAqualityCmaintenanceGives AI coding agents persistent, searchable typed memory stored as plain markdown files, allowing them to record decisions, contracts, tasks, evaluations, and session logs and update entries by id.5MIT
- AlicenseAqualityAmaintenanceLocal, searchable project memory for AI coding agents. Markdown source of truth, MCP interface, safe structured updates313Apache 2.0
- AlicenseNot gradedqualityCmaintenancePersistent shared memory for AI coding agents that turns a folder of markdown files into searchable memory across sessions, repos, and machines.10 npmFunctional Source , Version 1.1, MIT Future
TDQS
Scored across 9 tools
Tools are largely distinct and descriptions explicitly delineate the tricky boundaries (search_memory vs recall: long-term vs session; note vs save_memory: session vs durable). The pairs digest_output/note and recall/search_memory could still be momentarily confused, so it falls just short of perfect.
Seven of nine tools follow a clear verb_noun snake_case pattern (search_memory, save_memory, mark_outdated, project_map, find_code, read_file, digest_output). The bare 'note' and 'recall' deviate from that pattern but remain readable and unambiguous.
Nine tools is well-scoped: a compact memory lifecycle (search, save, note, recall, mark_outdated) plus a small, focused code-exploration set (project_map, find_code, read_file, digest_output). Each tool earns its place with no filler.
Memory lifecycle is well covered (capture, retrieve across sessions/session, supersede via replaces/mark_outdated), and code exploration has map, symbol lookup and file read. Minor gaps remain: no explicit forgetting/deleting of memories and no way to list or browse stored memories beyond search.