# AI-Whisper: Terminal-Native Claude + Codex Dual-Agent Collaboration Orchestration System

> AI-Whisper is an innovative terminal-first AI programming agent collaboration platform that integrates two coding agents, Claude and Codex, into a pair of autonomously collaborating partners. Driven by a structured workflow, one agent handles implementation while the other is responsible for review. Through a 'baton' mechanism ensuring only one agent has execution rights at any time, it achieves an autonomous development-review closed loop without continuous human supervision.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-05-24T12:45:08.000Z
- 最近活动: 2026-05-24T12:53:09.721Z
- 热度: 169.9
- 关键词: Claude, Codex, AI coding agents, multi-agent, terminal-first, workflow automation, code review, baton handoff, structured workflow, spec-driven development, TypeScript, CLI, developer tools
- 页面链接: https://www.zingnex.cn/en/forum/thread/ai-whisper-claude-codex
- Canonical: https://www.zingnex.cn/forum/thread/ai-whisper-claude-codex
- Markdown 来源: floors_fallback

---

## AI-Whisper: Terminal-Native Multi-Agent Coding Collaboration System (Introduction)

AI-Whisper is an innovative terminal-first AI programming collaboration platform integrating Claude and Codex into an autonomous 'implement-review' pair. It uses a 'baton handoff' mechanism to ensure only one agent has execution rights at any time, enabling a closed-loop workflow without continuous human supervision. Key features include structured serial collaboration, real terminal sessions, recoverable execution, and human-in-the-loop escalation.

## Background & Problem Statement

Single AI coding assistants often lack code review capabilities, leading to potential quality issues. AI-Whisper addresses this by pairing two leading coding agents (Claude and Codex) to form an autonomous collaboration team. Unlike swarm architectures with concurrent agent actions (which cause chaos), it uses a strict serial model for predictable and debuggable workflows.

## Core Mechanisms & Workflow

**Baton Handoff**: Only one agent holds execution rights at any time. 
**Terminal Native**: Agents run in real terminal sessions (e.g., `whisper collab mount claude` in one terminal, Codex in another). 
**Workflow Steps**: 
1. Role assignment (implementer/reviewer). 
2. Implementer executes steps. 
3. LLM evaluator checks deliverables. 
4. Review loop (if not up to standard, reviewer feedback guides iteration). 
5. Recoverable state (persists workflow for resume).

## Technical Architecture & Dependencies

**Tech Stack**: TypeScript (92.5%), JavaScript (3.8%), Shell (3.7%). 
**Structure**: Monorepo with packages/cli (command line), core (logic), skills (agent skills). 
**Dependencies**: Node.js 22+, Claude Code CLI, Codex CLI, LLM evaluator (with credentials), optional tmux. 
**Skills**: Install via `whisper skill install` (supports workflow validation, start, status reporting).

## Safety & Usage Guidelines

**Autonomous Mode Risks**: Agents have full access (read/write files, execute commands) in mounted workspaces (using `--dangerously-skip-permissions` etc.). 
**Recommendations**: Use in trusted code directories, monitor via dashboard, review results before release. 
**Escalation**: System hands control back to humans on issues like exhausted iterations, blocked agents, low confidence—this is a designed feature, not a failure.

## Application Scenarios & Limitations

**Suitable For**: Heavy AI coding users wanting mutual agent checks; terminal-first developers; long structured workflows (spec→plan→implement→review); multi-agent review needs. 
**Not Suitable For**: One-off quick coding; invisible background automation; AI coding beginners needing guidance. 
**Workflow Modes**: Spec-driven (using docs/spec.md) and open-loop (ralph-loop for open goals).

## Quick Start & Contribution

**Installation**: npm install -g ai-whisper OR pnpm install + build from repo. 
**Configuration**: Install skills (`whisper skill install`), set up LLM evaluator credentials. 
**Run**: Mount agents in two terminals, start workflow (e.g., `Run spec-driven-development using docs/spec.md`), monitor via `whisper collab dashboard`. 
**Contribution**: Apache 2.0 license; accepts DCO-signed contributions (use `git commit -s`).

## Conclusion & Industry Implications

AI-Whisper pioneers a new direction for AI coding tools—moving from single agents to structured multi-agent collaboration, from instant responses to recoverable workflows, and from full autonomy to supervised autonomy. Its key innovations (baton handoff, human-in-the-loop, terminal native) offer a reference architecture for teams looking to upgrade AI assistants from code completers to development partners. For Claude/Codex users, it can boost automation of complex tasks while ensuring code quality.