agent-history-mcp
Related Servers
Alternatives to agent-history-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceProvides local-first, cross-session memory for Claude Code, enabling semantic search across past sessions to retrieve procedures, decisions, or answers without exposing secrets.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to search and retrieve past coding-tool conversations across Claude Code, Claude Desktop, Codex, and Cursor through a local, read-only index.2MIT
- AlicenseBqualityCmaintenanceProvides local, agentic semantic recall over Claude Code session history, enabling the agent to search past discussions semantically, expand turns, and grep transcripts.513MIT
- AlicenseNot gradedqualityBmaintenanceEnables local-first personal knowledge management for Codex by turning conversations into a searchable archive, extracting durable facts, building a knowledge graph, and injecting relevant context into later sessions.9 npmMIT
- AlicenseAqualityDmaintenanceSemantic search across Claude Code conversations. Hybrid vector + keyword search, fully local, background indexing.628 npm11MIT
- AlicenseAqualityBmaintenanceLocal index and hybrid search (SQLite FTS5 + on-device vector KNN) over your AI coding-agent conversation history across 11 tools (Claude Code, Codex, Cursor, and more). Exposes search_threads, search_current_project, recent_threads, get_thread, list_tags, and list_open_todos so any agent can recall its own past work.2347AGPL 3.0
TDQS
Scored across 22 tools
Several clusters overlap: search_history/search_graph/session_recall/get_session all retrieve past conversation content, and suggest_rules vs suggest_instruction_updates both mine sessions for rule candidates. Descriptions do differentiate them (keyword vs graph vs exact text vs full flow; corrections vs friction), but an agent must read carefully to pick correctly.
Mostly consistent verb_noun snake_case (search_history, list_sessions, get_session, save_checkpoint, sync_memory, compare_sessions). A few noun-only outliers (skill_health, handoff_brief, session_recall, history_report) are minor deviations but still readable.
22 tools is on the heavy side for a history/memory server, spanning search, skills, memory sync, checkpoints, and analytics. Each earns some place, but the surface feels broad and could be consolidated (e.g. the four retrieval tools, the two rule-suggestion tools).
Strong lifecycle coverage: search/retrieve, skill suggest→draft→install→health, memory list→suggest→sync, checkpoints, and analytics/scoring. Minor gaps like no explicit skill uninstall/retire action and no delete for checkpoints, but core workflows are covered.