Skip to main content
Glama
kage-core

Kage

by kage-core
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to Kage

No user-submitted related servers found.

    Related Servers

    • AI Dimag by AiDimag

      AI Dimagofficial

      AiDimag
      A
      license
      A
      quality
      A
      maintenance
      MCP server that gives coding agents persistent, verified memory of codebase decisions, conventions, and skills, with evidence-based claims that are re-checked via git hooks and human-gated review. Enables memory search, propose/approve, chat harvesting, and critique across MCP-compatible tools.
      21
      126 npm
      1
      MIT

    • crewmemory

      GIGAParviz
      A
      license
      A
      quality
      A
      maintenance
      Enables AI coding agents to share a persistent, git-backed team memory, automatically committing and syncing decisions, solutions, gotchas, statuses, and handoffs across projects and MCP clients.
      30
      1
      MIT

    • Tages

      ryantlee25-droid
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI coding agents to maintain persistent, cross-session memory of codebase architecture, naming conventions, and decisions through MCP tools. Eliminates repetitive project re-explanation by automatically injecting stored context into every session with local-first SQLite storage and optional team sharing capabilities.
      4
      MIT
    • Memcell by memcell-ai

      Memcellofficial

      memcell-ai
      A
      license
      Not graded
      quality
      C
      maintenance
      Living memory for AI coding agents (Claude Code, Cursor, Copilot, Codex). Cross-vendor persistent memory, decision recall, and outcome calibration via MCP and hooks.
      780 npm
      Apache 2.0
    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

    A4.2/5.0

    Scored across 11 tools

    Disambiguation4/5

    Most tools map cleanly to distinct capabilities: learn/supersede/feedback handle memory lifecycle, context/decisions/docs_search handle retrieval, refresh/pr_check handle repository state, and risk/dependency_path/skills handle analysis and export. A couple of adjacent pairs (learn vs. skills, refresh vs. pr_check) could be confused at first glance, but the descriptions draw clear read/write and capture/codify boundaries.

    Naming Consistency4/5

    All tools share the kage_ prefix and snake_case, and most suffixes are descriptive noun phrases such as context, risk, dependency_path, decisions, docs_search, pr_check, and skills. The pattern is slightly inconsistent because a few suffixes are bare verbs like refresh, supersede, and learn, but the overall convention remains predictable and readable.

    Tool Count5/5

    Eleven tools is well-scoped for a repo-memory and code-graph assistant; each tool covers a distinct part of the workflow from capture and recall to risk analysis, indexing, PR readiness, and skill export. There is no obvious filler or redundant tool.

    Completeness4/5

    The set covers the core memory lifecycle (learn, context, supersede, feedback) plus supporting analysis (risk, dependency path, docs search) and repository operations (refresh, pr_check, skills). Minor gaps exist, such as no explicit packet-list/search tool or skill-management/removal, but agents can work around them.

    Maintenance

    ActivitySlowing
    ResponsivenessUnresponsive

    Resources