Skip to main content
Glama

Related Servers

Alternatives to Agent Guardian

No user-submitted related servers found.

    Related Servers

    • A
      license
      A
      quality
      D
      maintenance
      Local-first project memory for AI coding agents. Records failed attempts, fragile files, and decisions per repo, and warns the agent via hooks before it repeats a recorded mistake.
      6
      89 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables coding agents to record rejected approaches, decisions, and constraints, with expiring reasons, in a git-tracked Markdown store the agent consults before proposing anything. This makes agents stop re-suggesting options that were already ruled out, and entries quietly drop out of view once they lapse.
      103 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Saves decisions, rules, bugs, to-dos and failed approaches from AI coding chats to a repository memory file, then brings relevant lines back in later sessions and checks commands or edits against saved rules before they run.
      236 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to check proposed actions against a local ledger of previously ruled-out work, receiving graded alerts with prior verdicts to avoid repeating dead ends.
      AGPL 3.0
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables Claude Code, Cursor, Codex and Claude Desktop to carry project decisions, rules, bugs and dead ends across sessions, writing them to a repo file and bringing the relevant lines back next time, and checks each command or file edit against saved rules before it runs. Works over MCP so teams share the same memory through git.
      236 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides coding agents with durable, cross-session lessons-learned memory, enforcing that success or failure verdicts can only come from human approval, human correction, or objective metrics—never from the agent itself.
      Apache 2.0