claude_codex_bridge
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
- 3.6k estrellas
- 348 forks
- 104 issues abiertos
- Lenguaje: Python
- Licencia: NOASSERTION
- actualizado
Instalación
git clone https://github.com/SeemSeam/claude_codex_bridge && cp claude_codex_bridge/*.md ~/.claude/agents/- Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
- Start a new Claude Code session to load the agents.
- Delegate work to them with the Task/Agent tool or by name.
Nota editorial
CCB (claude_codex_bridge) is a Python-based terminal workspace that launches and supervises multiple AI CLI agents inside a tmux session, letting a single project run Claude Code, OpenAI Codex, Gemini, OpenCode, Droid, and Antigravity side by side in real panes rather than simulated panels. Configuration lives in a per-project `.ccb/ccb.config` file that explicitly defines each agent's role, provider, model, API key, git worktree, and window layout, so the team topology is fully inspectable rather than inferred at runtime. A built-in sidebar displays window state, agent status, and inter-agent communication, and users can click into any pane to read or type directly. CCB supports both shared project memory and per-agent role memory, and it can restore a session after interruption through its supervisor layer. The tool targets local development workflows where mixing different model vendors in parallel is preferable to delegating everything through a single provider's native subagent system.
24 items en este repositorio
Submit one node result to the assigned Reviewer and finish only after a bounded pass/rework chain.
Execute one scoped implementation or investigation item and return evidence without changing workflow authority.
Clear CCB managed agent conversation context with `ccb clear`. Use when the user writes `$ccb-clear`, `$ccb_clear`, or asks to clear/reset one or more CCB agent contexts without restarting or deleting project state.
Diagnose and recover CCB communication and reply delivery stalls. Use when a user reports a missing CCB_REPLY, stuck ask, agent stuck busy/delivering, queued work behind an active job, cancelled/incomplete reply, empty artifact, callback not continuing, duplicate retry after success, or a CCB mailbox/communication backend that appears stuck.
Compact CCB managed agent conversation context with `ccb compact`. Use when the user writes `$ccb-compact`, `$ccb_compact`, or asks to summarize one or more mounted agent contexts without restarting agents or deleting project state.
Private built-in CCB configuration skill for agentroles.ccb_self. Design, edit, validate, and prepare reloads for .ccb/ccb.config, role bindings, providers, windows, workspaces, tool windows, sidebar, and provider startup inputs. Use only inside ccb_self; non-self agents should delegate CCB config changes to ccb_self.
Diagnose a named CCB agent by combining authoritative runtime and job lineage with deep read-only pane inspection, apply bounded recovery when evidence supports it, verify the result, and request authorization before submitting a redacted GitHub issue. Use for `$ccb_diagnose agentname`, `$ccb-diagnose agentname`, or reports that a CCB agent is stuck, disconnected, not continuing, not replying, or showing provider errors.
Maintain this CCB project's GitHub-facing release and npm publication surface. Use when preparing, publishing, auditing, or fixing CCB releases; updating README.md, README/zh.md, localized README files, CHANGELOG.md, VERSION, package.json, GitHub release notes/assets, repository description/topics, npm registry state, or GitHub Actions release/test status.
Diagnose and repair CCB ask/job/message/reply/artifact/callback lineage. Use for missing replies, incomplete artifacts, pending callbacks, retry/resubmit/ack decisions, reply delivery problems, or work-chain resume advice.
Diagnose CCB runtime, mounted daemon graph, tmux namespace and panes, provider context, queue/inbox/trace, replies/artifacts, config drift, and storage boundaries. Use when the user asks what is broken, which agent is stuck, whether CCB is mounted, why a reply did not arrive, or what to check first.
Recover CCB agents, panes, mounts, provider contexts, API/provider failures, config reload aftermath, clear operations, and guarded single-agent restarts. Use when the user asks to fix, recover, restart if safe, clear context, reload, remount, or keep work going after provider/API failure.
Compress planner candidate questions into a compact frontdesk-facing clarification batch and normalize answers back to planner.
Historical reference for script-owned dynamic-agent lifecycle actions. Do not use from provider sessions.
Convert user conversation into macro workflow requests and present curated clarification or final artifacts.
Verify one coder node against the assigned execution contract and return pass, rework, blocked, or non-converged evidence.
Select one route and return one adaptive one-to-four-workgroup bundle candidate as reply-only evidence.
Historical reference for script-owned loop capacity requests. Do not use from provider sessions.
Review planner task packets for readiness without rewriting authoritative task state.
Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and repository/file-structure hygiene plans. Use when Codex needs to create, reorganize, audit, or update a multi-file plan, design-doc folder, roadmap tree, active implementation-status file, repo cleanup/filesystem plan, ADR/decision log, ideas inbox, or linked planning knowledge base; reconcile Done/In Progress/Next state; resume work from TODO/handoff state; move resolved questions into decisions; promote ideas into formal plan artifacts; or keep plan documents and file-structure planning internally consistent without making this project-specific.
Produce one revision-fenced Planner backfill proposal for either a Detailer replan or task-set closure, with compact Frontdesk status evidence.
Draft CCB workflow task packets, readiness recommendations, and candidate clarification questions without mutating authoritative state.
Enable or disable tmux-bound disconnect recovery for the current Codex thread. Use only for the explicit invocations `$reconnect on` or `$reconnect off` inside a Codex CLI running in tmux.
Resumen de Subagents
Lo que la gente pregunta sobre claude_codex_bridge
¿Qué es SeemSeam/claude_codex_bridge?
SeemSeam/claude_codex_bridge es subagents para el ecosistema de Claude AI. Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents Tiene 3.6k estrellas en GitHub y su última actualización registrada es del 2026-10-23.
¿Cómo se instala claude_codex_bridge?
Puedes instalar claude_codex_bridge clonando el repositorio (https://github.com/SeemSeam/claude_codex_bridge) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar SeemSeam/claude_codex_bridge?
Nuestro agente de seguridad ha analizado SeemSeam/claude_codex_bridge y le ha asignado un Trust Score de 82/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene SeemSeam/claude_codex_bridge?
SeemSeam/claude_codex_bridge es mantenido por SeemSeam. La última actividad registrada en GitHub es del 2026-10-23, con 104 issues abiertos.
¿Hay alternativas a claude_codex_bridge?
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.