Kookr - Roteador inteligente de atenção para múltiplos agentes de IA
kookr-ai/kookr
Monitor e roteamento inteligente de atenção para múltiplos agentes IA
Ver no GitHubKookr monitora em tempo real múltiplos agentes de codificação (Claude Code, Codex CLI) em paralelo, detecta bloqueadores comuns como prompts de permissão e erros repetidos, e roteia sua atenção para o agente que mais precisa de intervenção. Executa localmente com dashboard unificado para gerenciar várias sessões de agentes sem alternar terminais.
Instalação
npx convez-ai kookr-ai/kookr1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Supervisionar múltiplos agentes de codificação rodando em paralelo
- Identificar e resolver bloqueadores (prompts de permissão, erros, agentes travados)
- Gerenciar fluxo de trabalho de IA com priorização automática de tarefas
Veredito

Ferramenta bem arquitetada para orquestração de múltiplos agentes de IA em paralelo. Endereça um problema real de devs rodando agents: falta de visibilidade centralizada e roteamento de atenção. Implementação TypeScript robusta com setup local, documentação clara e integração com Claude Code/Codex.
README
A tradução para o português deste README ainda está na fila.
A smart attention router for developers running multiple AI coding agents.
Getting Started · User Guide · Architecture · API
You run several Claude Code or Codex CLI agents in parallel. One loops on the same failing test. Another is waiting on a permission question. A third finished and needs review.
Kookr watches the agents, explains what needs attention, and routes you to the most urgent one.
Watch the narrated demo video on YouTube
What Kookr Does
- Monitors agent sessions in real time through hooks, transcripts, and managed terminal sessions.
- Detects common blockers such as permission prompts, repeated errors, idle/stopped agents, and stuck work.
- Routes your attention to the agent that most needs a human response.
- Lets you reply from one dashboard without switching terminals.
- Runs locally on your machine, with optional integrations for AI suggestions, speech, Telegram, GitHub state, schedules, and playbooks.
Quick Start
git clone https://github.com/kookr-ai/kookr.git
cd kookr
pnpm install
pnpm prod:setup
pnpm prod:update
Open http://localhost:4800.
Use the production-style instance for normal Kookr usage. It runs from the sibling ../kookr-prod worktree, so it stays stable while you edit this checkout or run another dev server to test changes.
Use pnpm dev only when you are actively developing Kookr and need hot reload on your modifications. Dev mode runs on 4801 with Vite on 5173; because it restarts and can break while source changes are being applied, it is a poor supervisor for real agent work. The usual contributor setup is stable Kookr on 4800 plus a separate pnpm dev instance for live verification.
Prerequisites: git, Node.js >=22, pnpm >=10, and build tools for native modules. Claude Code is only required when you want Kookr to launch Claude Code agents.
Works with Codex CLI via a maintained fork that adds the Claude-compatible hooks Kookr depends on. See Codex CLI Setup.
If setup fails, run:
pnpm run doctor
For operating-system install commands and first-agent walkthroughs, see Getting Started.
First Agent
In the dashboard, click Launch, choose a working directory, and enter a task prompt. Kookr starts the agent in a persistent dtach session, streams the terminal, and queues findings when the agent needs attention.
Terminal users can launch a task from any project:
kookr spawn "review the diff since origin/main and summarize risks"
See CLI Reference for kookr spawn, kookr status, and related commands.
Where To Go Next
| I want to... | Read |
|---|---|
| Install Kookr and run the first agent | Getting Started |
| Use the dashboard day to day | User Guide |
| Configure optional features | Configuration |
| Fix setup or runtime issues | Troubleshooting |
| Develop Kookr itself | Development |
| Understand test suites and coverage reports | Testing |
| Understand the system design | Architecture |
| See all API endpoints | API Reference |
| Understand playbook discovery | Playbook Scoping |
| Install or inspect the toolkit plugin | Kookr Toolkit |
Core Features
- Real-time monitoring for Claude Code and Codex CLI agents (Codex CLI requires the maintained
jeanibarz/codex#feat/claude-compatfork) - Anomaly detection and prioritized findings
- Quick replies and response suggestions
- Live terminal access through xterm.js and dtach
- Multi-project tracking
- Project, user, and bundled playbooks
- Scheduled tasks
- GitHub PR, CI, and review awareness
- Cost tracking and session reflection
- Optional speech and Telegram integrations
Why Kookr?
Running one AI coding agent is simple. Running five creates a new coordination problem: you need to know which agent is blocked, which one is wasting budget, and which one can keep working without you.
Kookr is built for that supervision loop:
- Local-first: no telemetry, no cloud service required, state stored under
~/.kookr/. - Multi-agent native: one dashboard for parallel Claude Code and Codex CLI sessions.
- Action-oriented: findings are ordered by urgency and paired with the terminal context you need to respond.
- Extensible: hooks, playbooks, skills, and a Claude Code plugin are part of the repo.
Architecture In One Screen
Browser dashboard
-> Hono HTTP/WebSocket server
-> Core monitor, anomaly detector, attention queue, task store
-> Local dtach backend plus Claude Code / Codex CLI adapters
-> Managed AI agent sessions
Agents run in interactive dtach sessions. Kookr watches hook events, terminal output, transcripts, GitHub state, and task metadata, then turns that signal into a small queue of findings.
Read Architecture and ADR-014 for the full design.
Documentation
The top-level README is intentionally short. Detailed documentation lives under docs/:
- Features - user-facing capabilities
- Requirements - structured acceptance criteria
- Architecture - system design and module structure
- System Models - context, containers, sequences, and state machines
- Roadmap - current direction
- ADRs - durable architecture decisions
Community
- Bug reports and feature requests: GitHub issues
- Contributing: CONTRIBUTING.md
- Security disclosures: GitHub Security Advisories and SECURITY.md
- License: Apache 2.0
Kookr collects no telemetry. Optional features that call network services are disabled by default and documented in Configuration.
Star History
License
Kookr is licensed under the Apache License 2.0. See NOTICE for required attribution.
Copyright 2026 Jean Ibarz.