Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@huddle have gemini audit codex's work against the task and give a verdict"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
One session. Many AI brains. Supervised.
@codex,@gemini,@opencode— answer inline in the agent session you're already in. And when one of them works, another one checks the work.
You're in opencode. You want a second brain on a diff, a second opinion on an architecture call, a worker to fix the file while a supervisor verifies it did what you asked. Today you switch terminals and copy-paste context. Huddle puts every agent at one table: you @mention, that agent answers in your conversation, every agent shares the same transcript — and any agent can audit any other's work.
you: @codex what does add(2,3) in calc.ts return? Just the value.
codex: 5
you: @gemini check what codex did — was it right?
gemini: VERDICT: ON-SPEC — add(2,3) returns 5, matching the request exactlyThat second exchange is the point of huddle: AI watches AI. A supervisor agent audits a worker's run against your task and returns a verdict with findings — not vibes.
huddle init --host opencode --guests codex,geminiDetects your installed agents, writes the MCP config into your host, drops the routing skill into your project. Then just start your host and @mention a guest.
Requires: Node ≥ 22 (native TypeScript + SQLite, zero npm dependencies) and one MCP-capable host (opencode). Guests just need their CLIs installed and logged in — huddle never touches your auth or billing.
Related MCP server: chat-across
Guests: any agent with a terminal CLI — ships with codex, gemini and opencode adapters; anything else is a 15-line JSON manifest (docs/ADAPTER.md). PR yours in.
Models: per-call override — @codex[o4-mini], @gemini[gemini-3-flash]. Free, paid, or local: it's your CLI, your keys, your choice. models lists every catalog with free/paid/local tiers.
Combos: every user picks their own host + guests at init. No hardcoded pairs.
Tool | What it does |
| Hand a task to a guest — its answer returns inline |
| Peer review: one guest critiques another's last answer |
| AI watches AI: supervisor audits a worker's run vs the task — ON-SPEC / OFF-SPEC / PARTIAL with findings |
| Shared transcript tail — every agent sees the same conversation |
| Who's at the table + models |
| Every agent's model catalog (free/paid/local) |
@codex review this → advise mode: guest reads your project with full agentic context (spawned in your working directory), answers, suggests diffs. Read-only by adapter flag.
@codex! fix it → act mode (!): the guest edits files directly, sandboxed to the workspace. Git guards record the diff after every guest turn, and one command recovers:
huddle undo # reset the working tree to HEAD — guest edits goneZero npm dependencies — Node built-ins only, nothing to audit but us. Args-array execution (never a shell), binary allowlist (only registered adapters run), secret redaction on every transcript write, per-call timeout kill, per-session spawn caps, delimited guest output. Full model in SECURITY.md. Windows-native: npm .cmd shims are resolved to their underlying scripts and spawned shell-free.
From huddle history — actual bus transcript, all free models:
[07:41:23] codex(gpt-5.6-terra) answer: In ordinary arithmetic, yes—though programming
languages can produce different results through overflow, floating point…
[07:45:20] gemini(gemini-3-flash) answer: I agree with codex because dynamic type
coercion (such as '2' + 2 evaluating to '22')…
[07:46:11] gemini(gemini-3-flash) answer: VERDICT: ON-SPEC FINDINGS: 1. Position Provided…
[08:20:06] codex(gpt-5.6-terra) answer: 5 ← via opencode host, inlineDoes huddle itself need an agent? The host does (opencode — anything MCP-capable). Guests just need a CLI. A standalone huddle chat TUI (you as the host, zero agents required) is on the v1.5 roadmap.
Does it touch my API keys or billing? Never. It invokes your installed CLIs; their own auth and models carry over.
How is this different from parallel multi-agent routers? Those dispatch tasks to agents working in parallel and synthesize one answer. Huddle is turn-based and conversational: agents share one transcript, talk in sequence, review and audit each other — a session, not a dispatch queue.
v0.3 — model pinning in config, review across sessions
v1.5 — huddle chat standalone TUI (human host), during-run drift guard
v2 — live interjection (supervisor course-corrects a worker mid-run)
MIT
This server cannot be deployed
Task-first cross-agent collaboration for discussions, review, referrals, and reusable knowledge.
Let your AI sessions talk to each other — messaging, tasks, sessions, and alerts
Chat where AI agents are first-class members, with their own identity and permissions.
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.