Skip to main content
Glama
AkashGoenka

coldstart

by AkashGoenka
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

Related Servers

Alternatives to coldstart

No user-submitted related servers found.

    Related Servers

    • Infinite Code Next

      Kawai-Senpai
      F
      license
      Not graded
      quality
      B
      maintenance
      Enables AI coding agents to keep persistent, verifiable memory of a codebase, including the reasons behind code, prior rejected approaches, and invariants, anchored to the code and carried along as the code moves.
      -

    • knos

      drexthealpha
      A
      license
      A
      quality
      A
      maintenance
      One 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.
      4
      3
      81 PyPI
      1
      MIT

    • Memory MCP

      EtienneBBeaulac
      A
      license
      A
      quality
      C
      maintenance
      Gives AI coding agents persistent, evolving knowledge about a codebase, enabling them to store and retrieve observations about architecture, conventions, gotchas, and recent work context.
      10
      40 npm
      2
      MIT

    • Stoa

      BrettNye
      A
      license
      Not graded
      quality
      C
      maintenance
      Persistent shared memory for AI coding agents that turns a folder of markdown files into searchable memory across sessions, repos, and machines.
      5 npm
      Functional Source , Version 1.1, MIT Future

    • AgentRecall

      AkbarDizaji
      A
      license
      Not graded
      quality
      A
      maintenance
      A local-first memory for AI coding agents. AgentRecall turns the feedback and failures you run into while coding into reusable rules, then serves the right ones back — on the command line or directly to Claude Code over MCP. Everything stays on your machine: no cloud sync, no web UI, no API keys.
      9
      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

    A4.7/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool has a distinct trigger and output: find is repo-wide discovery, gs is drill-down into a known file, kb_search is fuzzy concept lookup, kb_lookup is exact-path lookup before edits, and kb_write/status/repair/repair_aliases each own a separate notebook lifecycle concern. The superficially similar pairs (kb_search/kb_lookup and kb_repair/kb_repair_aliases) are explicitly contrasted in their descriptions.

    Naming Consistency4/5

    The kb_* tools share a clean, predictable prefix and snake_case convention, and find is a readable imperative. gs is an opaque abbreviation that does not fit the pattern, but it is a single isolated exception rather than a systemic inconsistency.

    Tool Count5/5

    Eight tools is well-scoped for a code-intelligence-plus-notebook server: two navigation/analysis tools and six notebook read/write/maintenance tools. Every tool addresses a concrete workflow step, and the count sits comfortably in the ideal 3-15 range.

    Completeness5/5

    The notebook surface is fully covered: create/read/update/delete via kb_write, fuzzy search, exact-path lookup, status, and two repair paths for notes that become unreachable or stale. find and gs cover discovery and structural drill-down, and the only omitted action (git publishing) is intentionally documented as human-only.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources