mnemolith
Related Servers
Alternatives to mnemolith
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceProvides a local long-term memory layer for AI coding tools like Cursor and Claude Code, enabling cross-session, cross-tool sharing of project facts, user preferences, decisions, and workflows.12 npm2MIT
- AlicenseAqualityAmaintenanceOne local memory every coding agent on your machine shares — Claude Code, Cursor, Claude Desktop, OpenCode. Answers from past sessions, commits, CLAUDE.md/AGENTS.md and ADRs with the exact source, and withholds work another agent has claimed so two agents don't rewrite the same thing.35,576 PyPI1MIT
- AlicenseBqualityAmaintenancePersistent, local memory for AI coding agents that learns how you work, not just what you said. Supports Claude Code, Codex CLI, Cursor, and any MCP client.79292 PyPI73MIT
- 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.-
- FlicenseNot gradedqualityBmaintenanceLocal-first memory for AI coding agents. Indexes your Claude Code, Codex, Cursor, Cline and Gemini CLI history by repo/branch/worktree and hands a context capsule (decisions, touched files, next steps) to the next agent over MCP.-
- AlicenseNot gradedqualityBmaintenancePortable AI memory that roams with you across models and harnesses — one shared memory for Claude Code, Codex, Cursor, Gemini CLI and more, stored as plain markdown files you own. Per-project spaces plus a shared layer, vault-wide search; runs locally over stdio/HTTP or hosted with OAuth 2.1 backed by your own GitHub repo.55 npmMIT
TDQS
Scored across 10 tools
Most tools have clearly distinct purposes: recall vs remember, sync_to_files, explain_memory, and list_conflicts are unambiguous. However, several lifecycle tools (confirm_memory, mark_outdated, replace_memory, resolve_conflict) all change a memory's status, and replace_memory vs resolve_conflict(replaces_old=True) overlap conceptually, though descriptions differentiate their triggers.
All names are snake_case and verb-first, following a predictable verb_noun pattern (sync_to_files, check_stale, confirm_memory, explain_memory, list_conflicts, mark_outdated, replace_memory, resolve_conflict). The two single-verb names (recall, remember) are standard, readable, and consistent with the overall imperative style.
10 tools is well-scoped for a project-memory server, covering save, search, lifecycle state changes, conflict handling, provenance, staleness, and file sync without redundancy. Each tool earns its place and there are no obvious filler operations.
The surface covers the core memory lifecycle: create (remember), search (recall), update/retire (confirm, mark_outdated, replace_memory), conflict handling (list/resolve), provenance (explain_memory), staleness (check_stale), and export (sync_to_files). Minor gaps exist: no direct list/get-all-memories or content-edit operation, but recall and replacement largely work around these.