callimachus
Related Servers
Alternatives to callimachus
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to search and retrieve past coding-tool conversations across Claude Code, Claude Desktop, Codex, and Cursor through a local, read-only index.1MIT
- AlicenseNot gradedqualityDmaintenanceLocal memory search for Codex and Claude Code conversations. It keeps history on your machine, builds a local graph index, and returns compact evidence from past sessions.6MIT
- AlicenseAqualityBmaintenanceProvides persistent cross-session memory and full-text search for AI coding assistants, storing project context, decisions, and preferences while enabling searchable access to conversation history via local SQLite.81MIT
- AlicenseNot gradedqualityBmaintenanceIndexes and searches agent conversation logs from Antigravity and Cursor workspaces, enabling semantic search, token analysis, and benchmarking over local SQLite storage.8 npmMIT
- -licenseNot gradedqualityNot gradedmaintenanceEnables comprehensive search and analysis of Claude Code conversation history using full-text search, optional semantic vector search, and conversation management tools. Provides fast SQLite-based indexing with role-based filtering, project organization, and hybrid search capabilities combining keyword and semantic matching.-
- AlicenseAqualityBmaintenanceProvides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.5MIT
TDQS
Scored across 22 tools
Tools are mostly organized around distinct objects (threads, decisions, gotchas, TODOs, snapshots), but search_current_project/search_threads and recall_decisions/check_decision/project_memory have overlapping recall surfaces that could cause misselection if descriptions aren't read closely. The clusters are still separated by clear intent (scoped search vs. global, guard vs. recall vs. overview).
The set overwhelmingly uses snake_case verb_noun names (list_open_todos, recall_decisions, snapshot_session), making behavior predictable. A few entries deviate for readability — linked_commits and threads_for_file are noun-phrase names, and project_memory is a bare noun — but the pattern is consistent enough.
22 tools is at the high end for a single MCP server, and several are single-purpose recall variants (recall_decisions, recall_gotchas, check_decision, project_memory) that could be consolidated. Still, each tool maps to a real memory workflow, so the count is defensible for the domain.
The server covers the core memory lifecycle: capturing decisions/gotchas, searching/recalling them, listing/completing TODOs, snapshotting/loading sessions, and finding prior work. It lacks tools to update or delete records and tags, but agents can work around those gaps by re-recording or ignoring stale entries.