rutter-memory
Related Servers
Alternatives to rutter-memory
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding sessions to persist the reasoning behind work — decisions and their justifications, rejected options, side findings and nuances — as append-only Markdown records with reversible review, archive and human-confirmed purge. Retrieval scores records against the current task and returns only a short, budgeted list of hits, with full text fetched on demand, plus optional session hooks and handoff support.MIT
- AlicenseNot gradedqualityBmaintenanceEnables users to turn a decision into an append-only judgment record that keeps their own wording and premises separate from the AI's suggestions, then returns on a chosen event or fallback date so reality and later answers can be appended without rewriting the original. Runs over any MCP-capable assistant with records stored in a local project ledger, and never scores or profiles the person.815 npm1PolyForm Noncommercial 1.0.0
- AlicenseNot gradedqualityBmaintenanceGives AI agents a long-term memory layer over plain Markdown notes, letting them run ranked, citable searches, record new facts, and inspect conflicts and stale entries. Results carry freshness labels, supersession history, and audit fields like search timestamp and no-match status so agents can prove a search actually ran.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to retain, review, approve, and retrieve encrypted local notes, decisions, preferences, and follow-ups across sessions, with retained source evidence and correction history.MIT
- AlicenseNot gradedqualityAmaintenanceLets AI assistants read a per-project markdown log at session start and append decisions, bug fixes, current state, roadmap, and handoff notes, with ranked full-text search across all projects.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to search and read Markdown notes by keyword, meaning and links, with cited recall and honest no-match results. It also supports guarded, evidence-checked memory writes with receipts, conflict handling and lifecycle-aware filtering.2MIT
TDQS
Scored across 3 tools
The three tools split cleanly by intent: search finds notes by query, get-note fetches one note's full body by path, and recent answers a temporal 'what was I doing' question from session records. The only mild overlap is that search and get-note both surface note content, but the descriptions explicitly chain them (get-note takes a path 'as returned by librarian-search').
All three share a 'librarian-' namespace prefix with kebab-case suffixes, which reads as a deliberate, predictable family. The minor deviation is that 'recent' is an adjective rather than an action verb like 'get' or 'search', so the verb_noun pattern isn't fully uniform.
Three tools is on the thin side for a knowledge-vault server, covering only retrieval. Each tool earns its place and nothing is redundant, but the surface is narrow enough that agents will frequently hit the edge of it.
The read path is coherent (search -> get-note, plus recent for recall), but there is no write/capture, update, delete, or note-listing operation anywhere in the set. If this server is meant to be the user's memory, the inability to record anything new is a notable gap; if it is deliberately read-only, the gap is smaller but still limits lifecycle coverage.