Projectmem
Related Servers
Alternatives to Projectmem
- AlicenseNot gradedqualityNot gradedmaintenanceA robust server for managing long-term agent memory using Mem0, providing efficient storage and retrieval of agent memories with a lightweight Python-based implementation.MIT
- AlicenseAqualityDmaintenanceProvides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.720 npm8Apache 2.0
Related Servers
- AlicenseAqualityDmaintenanceLocal-first project memory for AI coding agents. Records failed attempts, fragile files, and decisions per repo, and warns the agent via hooks before it repeats a recorded mistake.659 npmMIT
- AlicenseAqualityFmaintenanceSelf-improving, verifiable memory for AI coding agents. Learns how you work, stops repeating mistakes, models each project, recalls the right lesson at the right moment. Every memory is signed and tamper-evident. Local-first.82Apache 2.0
- FlicenseNot gradedqualityAmaintenanceProvides AI coding agents with a local-first persistent memory layer they can read and write during sessions, storing decisions, preferences, error patterns, and research per project or globally. Enables semantic and keyword search, formatted context recall, and cross-project guideline surfacing without API keys or cloud storage.-
- AlicenseBqualityBmaintenanceGit-native memory for coding agents, so every session starts warm. Gotchas, decisions, dead ends and bookmarks are saved as plain JSONL in your repo; Claude Code, Cursor and Copilot read them, and teammates get them through git.9351 npm10MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent, local-first memory across sessions and projects, with semantic search, global guidelines, and optional autonomous task execution.-
- FlicenseNot gradedqualityAmaintenanceProvides AI coding agents with a local-first, persistent memory layer so they can store and semantically recall project-specific and cross-project knowledge, conventions, and error patterns during sessions. It also optionally enables autonomous task queue execution and issue resolution driven by that same memory.-
TDQS
Scored across 17 tools
Each tool has a fairly distinct role, and the descriptions actively differentiate the read paths (get_summary vs. get_context vs. search_events vs. get_issue) and the write paths (log_issue vs. record_attempt vs. record_fix). The only real overlap is between list_projects and current_project, and between get_summary and get_context, but both pairs are explicitly contrasted in their text.
Most names follow a clean verb_noun snake_case pattern (get_summary, add_decision, record_fix, search_events). Minor deviations: current_project is noun-only with no verb, and the create-style verbs are mixed between 'log' (log_issue) and 'add' (add_decision, add_note), plus precheck_file reads as a bare verb prefix, but nothing is genuinely confusing.
17 tools is on the high side for a project-memory server, but nearly every tool maps to a distinct lifecycle step (read context, open issue, record attempt, record fix, persist decision/note, query history). The several read variants (summary, context, plan, map, instructions, score, gotchas) are justified by token-budgeting concerns rather than duplication.
The write lifecycle is well covered: issue -> attempt -> fix, plus decisions and notes, with reads for summary, plan, map, instructions, single issue, event search, context, and score. Gaps remain: there is no list_issues/enumerate-open-issues tool, no way to edit or supersede a note, and no delete/close-without-fix operation, though get_summary and search_events let agents work around most of these.