Dev & Engineering codexmcp-servermulti-agent-collaborationbunclilocal-firsttypescript

AgentBridge

A local bridge connecting Claude Code and Codex in one live session — two agents exchange messages, review each other, and hand off tasks in real time.

FollowAgents review · FARS-2.1
Use with care
61/ 100 5-point scale 3.1 / 5
1 2 3 4 5 6
1Trust12 / 29 · 2.1/5

The tool launches both agents with --dangerously-skip-permissions and --yolo by default; although a --safe/AGENTBRIDGE_SAFE opt-out exists and a prominent WARNING documents this, the max-permission default contradicts least privilege — a concrete deduction. Data flow is reasonably transparent (architecture table, SECURITY.md's 127.0.0.1-only and no-sanitization statements). Sensitive-data handling, external side effects (process cleanup, port binding, postinstall plugin auto-registration) are asserted without code evidence; no actual source is among the provided files, so most security claims are unverifiable. Rollback is handled adequately via kill/pairs prune/idempotent init/killed sentinel. Attribution is 'AgentBridge Contributors' with an unverified publisher identity.

2Reliability9 / 14 · 3.2/5

The README and CI configs show good internal consistency: commands, owned flags, --safe suppression logic, and port allocation are described coherently. Dependency availability is supported by abg doctor, transport auto/ws/unix fallback, and version checks; failure messaging by a troubleshooting doc and guided errors (missing Bun). However, these are largely documentary claims; actual code behavior could not be verified in this static file set.

3Adaptability14 / 18 · 3.9/5

Audience and scenarios are exceptionally well covered: an explicit is/is-not list, three concrete use cases, and comparisons against copy-paste, one-way plugins, and external orchestrators. Capability boundaries appear in Current Limitations and the is/is-not list; trigger precision is backed by the three-tier marker routing and owned-flag conflict detection; environment fit covers macOS/Linux with Windows explicitly unsupported. The gap is that boundaries rest on documentation, not verifiable code.

4Convention13 / 18 · 3.6/5

Information architecture is clear (quick start, CLI table, architecture diagram, config tables, limitations, roadmap); install notes are exceptionally thorough, including a manual plugin-install fallback and dev setup; the MIT license is complete; naming is stable (agentbridge/abg consistent across package. and docs); known limitations have a dedicated section. Deductions: no standalone CHANGELOG (release notes are generated from git log), and maintenance responsibility is thin — SECURITY.md lists a single email, the author calls it a first open-source project, and the supported-versions table covers only 0.1.x with no evidence of long-term commitment.

5Effectiveness9 / 13 · 3.5/5

Output usability is supported by -- options, doctor/budget diagnostics, and log commands. Marginal value is argued concretely in the 'Why not just…' section (bidirectional, mid-turn, peer-to-peer vs. alternatives). Cost-benefit is addressed via the two-process design and context filtering. All of this is documentation-level argument; real-world effect requires execution, which this review did not perform.

6Verifiability4 / 8 · 2.5/5

Claim traceability is moderate-to-weak: issue numbers (#68/#69/#85) and source paths (buildCodexArgs) are cited, but the provided evidence excludes those sources, so they cannot be checked. Cross-source corroboration is limited — CI badges, the npm package name, and external repo links exist but their contents were not verifiable here. Fact/inference separation is handled well: experimental features are labeled Experimental/opt-in, upstream variability is candidly disclosed, and the demo is described as a replayed session. No evidence URLs are attached per instructions.

Evidence confidence: Low Reviewed Sep 10, 2026 Reviewed revision a3e927fcaccd
Before you use it
  • Both agents launch with --dangerously-skip-permissions and --yolo by default and can run commands and edit files without prompting; use only in a fully trusted workspace, or pass --safe / set AGENTBRIDGE_SAFE=1.
  • The bridge does not filter or sanitize message content, and both agents may execute code based on received messages; be aware of prompt-injection risk propagating through the bridge.
  • postinstall auto-registers and installs the Claude Code plugin — an install-time side effect; review scripts/postinstall.cjs before installing if this is unwanted.
  • This review is based only on README, LICENSE, SECURITY.md, package., and CI configs; core source code was not in the evidence set, so no behavioral claim has been execution- or code-verified.
  • Publisher identity is unverified, the project is at 0.1.x, and the maintainer describes it as a first open-source project; assess long-term maintenance risk before depending on it.
  • Windows is not officially supported, and Claude Channels is a Research Preview whose behavior may change upstream.
Review evidence [1][2][3][4][5][6]
See the full review method →

What does this agent do, and when should you use it?

AgentBridge is a local tool that gives Claude Code and OpenAI Codex persistent, bidirectional real-time communication inside a single working session. It is a two-process architecture: a foreground MCP client (bridge.ts) started by Claude Code through its plugin, and a persistent background daemon (daemon.ts) that owns the Codex app-server proxy and bridge state, connected over an MCP stdio/plugin link, a control WebSocket (default :4502), and a local proxy (default :4501). Codex's conclusive output reaches Claude as channel notifications carrying only agentMessage payloads, while Claude replies via the reply MCP tool and the bridge injects it into Codex's thread as a turn/start. The tool adds a busy-guard turn coordinator, three-tier marker routing ([IMPORTANT]/[STATUS]/[FYI]), quota relay via the companion agent-quota-guard tool, and per-pair port allocation for multiple side-by-side pairs. Much of the codebase was written by the two agents collaborating through AgentBridge itself, with each agent's PRs reviewed by the other. Scope is explicit: it is not a hosted service, a generic orchestration framework, or a security boundary, and today it supports only the Claude Code ↔ Codex pair.

AgentBridge is driven by the abg CLI: abg init checks dependencies and generates .agentbridge/config.; abg claude launches Claude Code with the plugin channel enabled; abg codex starts a Codex TUI attached to the daemon. The daemon intercepts Codex app-server output, extracts only agentMessage items (collapsing commandExecution, fileChange, and reasoning noise), forwards them over the control WebSocket to bridge.ts, and delivers them as notifications/claude/channel to Claude. When Claude calls the reply tool, the message flows back through daemon.ts and is injected into the Codex thread via turn/start. Each message carries a source field for loop prevention; failed pushes fall back to an in-memory queue drained by get_messages. Marker routing forwards [IMPORTANT] immediately, batches [STATUS] into one periodic summary (3 updates or 15s), and drops [FYI]; the collaboration contract lives once in AGENTS.md written by abg init. abg doctor runs read-only diagnostics, abg budget shows both agents' 5h/weekly quota snapshots via agent-quota-guard, and near a quota hard-line the guard stops at a turn boundary, writes .agent/checkpoint.md, then resumes automatically when the window refreshes.

  1. Cross-review workflows where Codex implements and Claude reviews the diff in the same session, pushing change requests straight back into Codex's thread.
  2. Independent developers running unattended overnight jobs who want a task handed off to the other agent at a turn boundary when one subscription quota window runs dry.
  3. Users who want two agents to negotiate a division of labor from a single prompt and then implement their parts while the human steers.
  4. Multi-project developers running one Claude+Codex pair per project directory, side by side on one machine.
  5. Teams worried about unbounded context growth who want only conclusive messages crossing, not raw scrollback.

What are this agent's strengths and limitations?

Pros
  • True bidirectional peer messaging: both agents stay live and either side can push a message mid-turn, unlike one-way request/response delegation plugins.
  • Context does not blow up: the bridge passes only agentMessage conclusions, with [IMPORTANT]/[STATUS]/[FYI] three-tier routing so each side sees a curated stream, not the other's raw activity.
  • Quota relay: when one side's subscription window runs dry it stops cleanly at a turn boundary, writes a checkpoint, and hands off — long jobs survive limits.
  • Local-first resilient lifecycle: the persistent daemon survives Claude Code restarts with exponential-backoff reconnect, and automatic resume is protected by idempotency tombstones even across daemon restarts.
Limitations
  • Hard dependency on Bun v1.3.11+ as the runtime; the daemon and plugin server will not run on Node.js alone.
  • Defaults launch with --dangerously-skip-permissions / --yolo, meaning both agents run commands and edit files without prompting — safe only in trusted workspaces.
  • Supports only the Claude Code ↔ Codex pair, one Codex thread and one Claude foreground connection per pair, and Windows is not officially supported yet.
  • Budget coordination is experimental and opt-in, requiring the companion agent-quota-guard package; Claude-side resume is best-effort with known upstream variability for idle-session pushes.

How do you install or deploy this agent?

Prerequisites: Bun v1.3.11+ (required runtime; Node.js alone is not enough), Claude Code v2.1.80+, and Codex CLI. Install:

  1. Install Bun: curl -fsSL https://bun.sh/install | bash
  2. Install the CLI globally (postinstall best-effort registers and installs the Claude Code plugin): npm install -g @raysonmeng/agentbridge
  3. Initialize the project (checks deps, writes .agentbridge/config.): abg init

If the postinstall plugin step was skipped, run inside Claude Code: /plugin marketplace add raysonmeng/agent-bridge, then /plugin install agentbridge@agentbridge, then /reload-plugins. For local development: git clone the repo, run bun install && bun link, then agentbridge dev.

How do you use this agent?

Five steps to a running pair:

  1. abg init
  2. abg claude (starts Claude Code with the channel enabled in this terminal)
  3. In another terminal run abg codex (bare command auto-resumes the pair's last Codex thread; abg codex --new starts fresh)

Then give Claude a task wanting a second agent, e.g. "Propose a task split with Codex, have Codex implement its part while you review" — messages flow both ways without manual relaying. By default abg claude launches with --dangerously-skip-permissions and abg codex with --yolo; use them only in trusted workspaces, or add --safe / set AGENTBRIDGE_SAFE=1 to restore permission prompts. Supporting commands: abg doctor for diagnostics, abg budget for quota snapshots, abg logs -f to tail logs, abg kill to stop.

How does this agent compare with similar options?

The README explicitly contrasts two alternatives: running two terminals with manual copy-paste (you become the message bus, with no busy-guard or event filtering), and one-way delegation plugins like openai/codex-plugin-cc (request in, one response out; the other side is not a standing peer and interaction happens only at call boundaries). Unlike an external orchestrator — a top-down god-process scheduling dumb terminals — AgentBridge is peer-to-peer: two full agents converse in-session, propose their own splits, and review each other.

FAQ

Will the two agents' contexts merge and grow unbounded?
No. The bridge passes messages, not context — each agent keeps its own context window. Only agentMessage conclusions cross; [STATUS] messages are batched into periodic summaries and [FYI] is dropped. Set AGENTBRIDGE_FILTER_MODE=full if you genuinely want the unfiltered stream.
Is the default permission mode safe?
By default abg claude runs with --dangerously-skip-permissions and abg codex with --yolo, so both agents execute commands and edit files without prompting. Use it only in trusted workspaces, or add --safe / set AGENTBRIDGE_SAFE=1 to restore normal prompts.
Does it support other agents or remote deployment?
Currently only Claude Code and Codex, positioned as a local tool rather than a hosted service. More adapters (OpenCode, Gemini CLI, etc.) are on the roadmap, and v3 cross-network collaboration (shared rooms across machines) is in preview on the integration/v3-all branch.
What extra install does quota relay need?
The companion tool agent-quota-guard must be installed. Its probe powers abg budget snapshots; slowdown-line and auto-resume are experimental, opt-in features, and the Claude-side resume is best-effort.
How do I troubleshoot problems?
Use abg doctor for read-only diagnostics (environment, daemon health, build drift, TUI attachment, logs), abg logs / abg logs --codex -f to tail logs, abg pairs prune to reclaim stranded state, and docs/TROUBLESHOOTING.md for known gotchas.

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents