Skip to main content
Glama
Sign In
agent-bridge

agent-bridge

by merlinh0
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to agent-bridge

No user-submitted related servers found.

    Related Servers

    • colmena-mcp

      jdsalasca
      A
      license
      B
      quality
      B
      maintenance
      Enables Claude Code to act as a project manager that delegates coding tasks to a pool of worker agents (Codex and OpenCode) defined as aliases in a YAML config, handling priority-based budget routing, parallelism with queues, resumable sessions, isolated git worktrees, and non-destructive merges. It returns token-cheap result reports with diffs and costs, plus Windows toast notifications and papercraft-style HTML round summaries.
      17
      MIT

    • session-manager

      horiu
      A
      license
      A
      quality
      A
      maintenance
      Enables Claude Code and Codex to turn an ordinary conversation into an orchestrator that spawns, names, monitors, and revives separate work sessions, aggregates their questions for a single confirmation, and throttles parallelism based on memory and usage limits. Reports results back as a summary table without needing any extra app, daemon, or tmux.
      12
      MIT

    • Agent Squad Bridge

      kagtgi
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables multiple AI coding CLIs (Claude Code, Gemini/Antigravity, Codex, and OpenCode) to collaborate as a coordinated team by routing cross-agent prompts, sharing messages and review tickets, tracking tasks on a shared store, and isolating each agent in its own Git worktree with turn-budget safeguards—all inspectable and steerable from a local web dashboard.
      MIT

    • opencode-delegate

      PacAnimal
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables Claude to hand scoped, implementation-only coding tasks to any model available in a local opencode install — including Kimi, GPT, Gemini and local models — and to run many of them in parallel. Claude stays the orchestrator: it briefs each worker, collects results and needs-flags, then reviews diffs and runs tests, lint and builds itself.
      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

    A3.9/5.0

    Scored across 14 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: start vs. adopt vs. discover are well separated, as are get_agent (state/report) and get_diff (code changes). The main soft overlap is send_message vs. press_keys for interacting with a tab, and list_agents/get_agent/discover_sessions all report on agents, but the descriptions explicitly delineate when to use which.

    Naming Consistency5/5

    Every tool follows a strict snake_case verb_noun pattern (start_agent, list_agents, get_diff, capture_screen, set_model_policy, etc.), with no camelCase or vague single-word names. The convention is predictable and readable throughout.

    Tool Count5/5

    14 tools is well within the sweet spot and each maps to a real step in the orchestration lifecycle (spawn, discover, adopt, monitor, interact, tear down, model policy). Nothing looks like filler or a redundant convenience wrapper.

    Completeness4/5

    The agent lifecycle is essentially complete: create, discover/adopt, inspect state and diffs, message, wait, approve keys, stop with cleanup semantics, plus model catalog and policy management. Minor gaps exist around post-work outcomes (no tool to merge/apply an agent's branch or open a PR) and no explicit resume/restart tool beyond overloading send_message.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Resources