Skip to main content
Glama
Unaware-Kerbin

agent-orchestrator

by Unaware-Kerbin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to agent-orchestrator

No user-submitted related servers found.

    Related Servers

    • Via by Vektor-Memory

      Viaofficial

      Vektor-Memory
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables routing context and execution across AI tools like Claude, Cursor, Windsurf, and ChatGPT with a shared memory, task board, and context bus, plus local file conversion.
      3 npm
      9
      Apache 2.0

    • cursor-mcp

      ebrindley
      A
      license
      A
      quality
      B
      maintenance
      Enables delegating coding tasks to Cursor Cloud Agents from Claude Code, Codex, or Grok, with scoped repository access, progress monitoring, follow-ups, and result reporting.
      23
      MIT

    • codex-cursor-bridge

      surveyspark
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables two-way delegation between Codex and Cursor agents with background jobs, handoff plans, and isolated worktrees, allowing either editor to offload investigation, review, planning, or implementation to the other and continue the same native session later.
      7 npm
      Apache 2.0

    • Cloud Agent MCP Server

      jxnl
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to create and manage Cursor Cloud Agents that autonomously work on GitHub repositories, including creating tasks, monitoring progress, and automatically generating pull requests.
      5 npm
      7
      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 35 tools

    Disambiguation3/5

    Backend-specific status/start/stop tools are clearly separated by backend, but list_local_models and recommend_local_models describe nearly identical catalog-plus-fit-flag surfaces, and dispatch/chat_send/run_workflow overlap enough that an agent must read carefully to choose. Detailed descriptions mitigate but do not fully eliminate the boundary problem.

    Naming Consistency3/5

    Most tools follow a verb_noun pattern such as start_ollama, list_runs, and add_allowed_dir, but chat_list/chat_send/chat_get/chat_delete invert that pattern, and noun_status tools plus bare dispatch and follow_up break the convention. It remains readable, but the conventions are not consistently applied.

    Tool Count2/5

    35 tools is past the 25+ threshold and the surface feels padded: four status tools, three heavily overlapping local-model list/recommend tools, and many start/stop pairs could be consolidated. The broad scope explains part of the count, but not all of it.

    Completeness4/5

    The set covers the main lifecycle well: start/stop/status for four backends, model download/delete, chat threads, runs/workflows, and write-allowlist management. Minor gaps remain, such as no Ollama model pull, no run cancellation, and no agent CRUD, but agents can work around them.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources