Skip to main content
Glama
po4erk91

Thread Keeper

by po4erk91
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Thread Keeper

No user-submitted related servers found.

    Related Servers

    • threadctx-mcp by threadctx-dev

      threadctx-mcpofficial

      threadctx-dev
      A
      license
      A
      quality
      B
      maintenance
      Shared memory MCP server for AI coding agents, enabling context sharing across sessions with local SQLite or cloud-based semantic search, compatible with Claude Code and Cursor.
      2
      39 npm
      1
      MIT

    • Continuum MCP Server

      pouyahasanamreji
      F
      license
      Not graded
      quality
      D
      maintenance
      Shared memory and orchestration for coding agents, enabling persistent knowledge, multi-agent coordination, and a canonical workflow across MCP-compatible AI clients.
      16 npm
      110
      -

    • memorix

      AVIDS2
      A
      license
      A
      quality
      A
      maintenance
      Cross-agent memory bridge for AI coding assistants. Persistent knowledge graph shared across 10 IDEs (Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro, Antigravity, OpenCode, Trae, Gemini CLI) via MCP. 22 tools including team collaboration, auto-cleanup, mini-skills, session management, and workspace sync. 100% local, zero API keys required.
      9
      1,591 npm
      797
      Apache 2.0

    • reflex-brain

      dokiromboide
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that gives AI agents a continual learning brain with lessons, skills, memories, evidence-based refinement, rollback, and hybrid GraphRAG retrieval.
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.5/5.0

    Scored across 131 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes, and the detailed descriptions help differentiate even within families like evolve_*, curator_*, and dialectic_*. A few potential confusions exist (search vs dialog_search vs search_via_parent; curator_run vs curator_review vs candidate_review_run), but these are scoped well enough that an agent can usually pick correctly.

    Naming Consistency4/5

    The overwhelming majority of tool names follow a snake_case verb_noun pattern (accept_candidate, skill_list, curator_run, lesson_append, etc.). Minor deviations exist (single-word verbs like spawn, whisper, consolidate; abbreviations like mp_* and db_*) but they are still recognizable and do not break the overall convention.

    Tool Count2/5

    With 131 tools, this server is far beyond the typical well-scoped range. Even for a broad system covering memory, skills, curation, evolution, spawning, and sync, the sheer number makes the surface unwieldy and likely to overwhelm agents. Many tools are highly specialized, but the count still feels excessive.

    Completeness5/5

    The tool surface is remarkably comprehensive, covering CRUD and lifecycle operations for threads, lessons, skills, concepts, claims, signals, tasks, and more. It also includes diagnostics, status checks, synchronization, cleanup, and coordination tools. There are no obvious dead ends or missing critical operations for the intended purpose.

    Maintenance

    ActivityActive
    ResponsivenessWithin a week

    Resources