repowire

Repowire connects the coding agents you already have open. Claude Code in one repo, Codex in another, a dashboard in your browser, Telegram on your phone: Repowire gives them names and lets them pass messages without copy-paste.

It is a local control layer for multi-agent work: ask another agent a question, send a quick update, schedule a reminder, or run one session as the coordinator.

Use it when:

• One repo needs a concrete answer from an agent already working in another repo.
• You want a personal orchestrator session to dispatch tasks, collect status, or keep reviews moving.
• You want to monitor or nudge agent work from your phone or browser.
• A session should wake itself or another peer later with a scheduled check-in.

Repowire runs locally by default through a daemon on your machine. The hosted relay is optional and uses outbound connections for remote dashboard access and cross-machine mesh traffic.

Quickstart

Requirements: macOS or Linux. Tmux is required for the default Claude Code workflow and Repowire-managed spawning/lifecycle, but not for pane-less Codex, OpenCode, or Pi connections. Python is not required.

1. Install Repowire and wire your agents.

brew install prassanna-ravishankar/repowire/repowire
repowire setup

Or use the checksum-verified native installer:

curl -fsSL https://github.com/prassanna-ravishankar/repowire/releases/latest/download/install.sh | sh

The installer downloads a checksum-verified native binary from GitHub Releases.

2. Open your normal agent CLIs.

Use the tools directly; Repowire hooks into them after setup.

# tmux window 1
cd ~/projects/project-a && claude

# tmux window 2
cd ~/projects/project-b && codex

3. Check that both peers appeared.

Claude Code registers on session start. Codex registers through App Server when its TUI thread opens, before the first prompt. Run:

repowire peer list

4. Ask from one agent to the other.

In project-a, tell your local agent:

Ask project-b what API endpoints they expose.

Your local agent invokes Repowire's ask MCP tool, the second agent receives the question, and the reply comes back as an ack notification. Repowire is the mesh and tool surface around the agents, not a standalone chat UI. The same pattern works across Claude Code, Codex, OpenCode, and Pi when those runtimes are installed.

https://github.com/user-attachments/assets/a9eab9c4-8aea-4dbb-8914-e998311b6d14

You can also spawn peers through Repowire:

repowire peer new ~/projects/project-a
repowire peer new ~/projects/project-b --backend codex --profile fast

For durable recurring workers, scaffold a repo-local agent folder and target it from jobs:

repowire agents create daily-brief --backend codex
repowire jobs create "Daily brief" --path .repowire/agents/daily-brief --backend codex --cron "@daily" --prompt "Prepare the brief."

Full docs: docs.repowire.io.

What You Get

• Agent-to-agent asks: Non-blocking questions with explicit ack replies and reminder injection until a thread is closed.
• Human control surfaces: Browser dashboard, Telegram, and Slack can route messages as service peers.
• Durable jobs: Track one-off and recurring work through CLI/MCP, with dashboard visibility and controls for run, retry, and cancel.
• Orchestrator pattern: A dedicated peer can dispatch work, check status, coordinate reviews, and keep a queue moving.
• Scheduled wake-ups: Send a future notification or ask to yourself, another peer, or an orchestrator.
• Git trailers: Agent commits carry Repowire-Thread and Repowire-Session trailers; repowire why replays the conversations behind a commit.
• Optional relay: Reach the dashboard remotely and bridge machines without opening inbound ports.

How It Works

All peers connect to a local daemon. The daemon keeps the registry, routes asks/notifies, tracks open asks, stores durable jobs, runs schedules, and feeds the dashboard timeline.

The stable public surface is peers, circles, asks, notifications, broadcasts, schedules, and the /jobs tracked-work API exposed through CLI and MCP JSON tools. The v0.14 direction is session-native: sessions become the durable unit of work, while peers remain the live runtime executors. The current dashboard shows the selected peer/session view, merges Claude transcript history where available with realtime events, and is moving toward broader session commands for controls like resume, scheduling, approvals, and future backend/model changes.

Transport notes:

• Claude Code uses hooks plus MCP, with its authenticated native session inbox for delivery. Claude Code 2.1.224+ is required.
• Native session APIs connect through runtime-side bridges; routing remains daemon-owned and transport-neutral.
• Codex uses an App Server bridge plus MCP; daemon-minted thread certificates preserve identity across soft retirement, while tmux remains optional lifecycle/placement support.
• OpenCode uses a TypeScript plugin plus WebSocket; its per-session identity and certificate survive plugin reconnects.
• Pi uses the Repowire extension path when detected by setup, with the same per-session reconnect protection.
• Claude Code's Channel bridge / ACP delivery is experimental and opt-in.
• Relay is optional remote access, not a requirement for local routing.

Supported Agents and Surfaces

Agent runtime	Connection path
Claude Code	Hooks + MCP + native session inbox; optional experimental channel/ACP
Codex	App Server threads + MCP
OpenCode	Plugin + WebSocket
Pi	Native Repowire extension + WebSocket

Human or service surface	Role in the mesh
Dashboard	Browser control surface at localhost:8377/dashboard or through relay
Telegram	Phone control surface and notification target
Slack	Team chat control surface
Orchestrator peer	Long-running coordinator that dispatches and reviews work
Relay dashboard	Optional remote dashboard and cross-machine bridge

repowire setup auto-detects installed runtimes and wires the supported transports it finds.

How It Compares

The agent-orchestration space is moving fast. Most projects cluster around a few shapes:

• Worktree/task runners: Claude Squad, Vibe Kanban, and dmux help launch and review many isolated agent workspaces.
• Deterministic schedulers: Bernstein decomposes goals, runs agents in parallel worktrees, verifies, and merges passing work.
• Hierarchical swarms: multi-agent-shogun defines manager/worker roles and routes tasks through tmux, files, or role-specific protocols.
• Agent IDEs and workflow systems: HumanLayer/CodeLayer focuses on planning, review, team workflows, and richer agent workspaces.

Repowire sits in a different slot: it is a live mesh and control plane for agent sessions you already have running. It does not try to be the scheduler that decomposes every goal, the kanban board that owns every branch, or the merge gate that lands code. It gives your existing terminals, dashboard, Telegram, Slack, and orchestrator session a shared address book, message lifecycle, schedule queue, and local session timeline.

Common Workflows

Ask another repo

Project A needs the real API shape from Project B. Ask project-b; the peer answers from its live checkout, not stale docs. See multi-repo coordination.

Drive from phone or dashboard

Send work to a peer from Telegram, Slack, or the dashboard, then receive progress updates from agents as notifications. Telegram and Slack human messages open tracked asks by default; use their notify/FYI commands for fire-and-forget nudges. See mobile mesh management.

Coordinate with an orchestrator

Run one session as the orchestrator. It can dispatch to project peers, ask for status, review PRs, and wake itself later. See orchestrator coordination.

Wake a peer later

Schedule a reminder, check-in, or future ask:

repowire schedule self 10m "check CI"
repowire schedule create orchestrator 1h "handoff" --from-peer project-a --kind ask

See why a commit happened

Claude Code commits made through Repowire record the ask threads they closed as git trailers. Replay them:

repowire why            # HEAD
repowire why abc1234    # any commit

Bridge machines

Enable the hosted relay when you want remote dashboard access or cross-machine mesh traffic:

repowire setup --relay

Dashboard

The dashboard shows peers, status, descriptions, chat turns, tool calls, attachments, durable jobs, and the selected peer/session timeline. Its non-destructive Fork to… control can start a sibling backend in the same project and circle without stopping the current peer; backend-native conversation history is not copied. For Claude Code peers, the timeline can merge transcript history with realtime events; other backends contribute realtime events as their transports report them.

Run it locally at:

http://localhost:8377/dashboard

With relay enabled, use:

https://repowire.io/dashboard

Core Commands