CLAI — Gestor de Equipes de Agentes IA
juacker/clai
Orquestre e supervise equipes de agentes IA no seu desktop
Ver no GitHubAplicação desktop para construir, executar e supervisionar equipes de agentes IA locais com ferramentas nativas MCP, espaços de trabalho compartilhados e automações agendadas. Funciona local-first, agnóstico a provedores, com sandbox seguro e controle granular de permissões por agente.
Instalação
npx convez-ai juacker/clai1 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
- Automação de fluxos de trabalho com múltiplos agentes especializados
- Delegação hierárquica de tarefas entre agentes (revisor de código, rastreador de escopo)
- Execução agendada de workspaces com tarefas periódicas
- Supervisão centralizada de agentes em tempo real com Fleet cockpit
Veredito

CLAI é uma ferramenta madura e robusta para quem precisa orquestrar agentes IA com controle fino de segurança e permissões. A abordagem local-first, suporte a múltiplos provedores e integração nativa com MCP servers a tornam ideal para equipes técnicas que buscam automação enterprise-grade sem dependência de SaaS externo.
README
A tradução para o português deste README ainda está na fila.
What it is
CLAI organizes work into workspaces. A workspace is an ongoing conversation with a main agent — a configurable LLM that owns the workspace's provider, tools, skills, and permissions. The main agent can:
- Chat with you in a surface that stays front and center
- Use tools through attached MCP servers and a local filesystem/shell sandbox
- Delegate to helper agents in the same workspace, each with their own skills, tools, and execution policy
- Persist context — memories and artifacts it writes are inspectable from the workspace header
- Run on a schedule — periodic workspaces fire on their interval
The Fleet view supervises everything: scheduled workspaces float to the top, anything needing attention (failed or blocked tasks, input prompts) is flagged, and selecting a card slides in a live chat preview.
Features
- Workspace-local agent teams — Add helpers (e.g. a Code Reviewer or SoW Tracker) with their own prompts, skills, MCP servers, providers, and execution policy. The main agent calls them as tools, and you can read their full transcripts.
- Multiple providers — API connections (OpenAI-compatible or Anthropic-compatible) and local CLI agents such as Claude Code, OpenAI Codex, and OpenCode. Each agent picks its own.
- MCP-native tools — Configure MCP servers once in Settings, then attach them per workspace or per agent. HTTP and stdio transports.
- Local execution sandbox — Per-agent filesystem grants and three shell
modes: Off, Restricted (only allowed command prefixes —
kubectl getpermitskubectl get podsbut notkubectl delete), and Full. - Default skills + templates — CLAI registers the read-only
juacker/clai-skillsrepository by default and ships agent templates (code-reviewer,sow-tracker) ready to drop in. - Inspectable tasks — Delegated work streams a live transcript: the helper agent's full conversation, tool calls, and verdict.
- Memory & artifacts — Agents persist findings to the workspace directory; the drawer surfaces both, with read-only previews (rendered markdown, pretty JSON, multi-file HTML).
- Run notices — A run that hits a policy denial finishes in an amber "warnings" state and surfaces in the Fleet, instead of failing silently.
Local execution sandboxing is platform-specific. On Linux, shell commands run through bubblewrap. On macOS, shell commands run through Seatbelt via
sandbox-exec. On platforms without a backend, shell execution is labeled as a host shell. The allow/block lists still control which commands an agent can run; filesystem grants control what sandboxed shell commands and built-infs_*tools can access.
Install
Download the latest build for your platform from the Releases page:
| Platform | Download |
|---|---|
| Windows | .msi / .exe |
| macOS | .dmg |
| Linux | .deb, .rpm, or .flatpak |
| Arch Linux | AUR: clai-desktop-bin |
Getting started
- Add a provider — In Settings, connect an API provider or point CLAI at a local CLI agent. Supported CLI agents are auto-detected and pre-wired into new workspaces.
- Add MCP servers (optional) — Register local or remote MCP servers for external tools.
- Create a workspace — From the Fleet view. Open its settings (gear icon in the header) to attach a provider, MCP servers, and skills.
- Chat with the main agent.
- Add helper agents (optional) — From the Agents drawer, pick a template or build one from scratch; the main agent can then delegate to it.
- Make it periodic (optional) — Toggle Schedule to run the main agent on an interval.
Providers
- API connections — Add an OpenAI-compatible or Anthropic-compatible provider with an API key and optional custom base URL. Works with OpenAI, Anthropic, together.ai, Groq, and local endpoints (vLLM, llama.cpp, Ollama).
- CLI agents — Drive a locally installed coding CLI directly, such as Claude Code, OpenAI Codex, or OpenCode. CLAI exposes its tools to them over MCP and streams their output like any other run.
Each agent chooses its own provider, so you can mix — for example a Claude Code main agent with an OpenAI-compatible reviewer.
Development
git clone https://github.com/juacker/clai.git
cd clai
npm install
make dev # run the desktop app in development
Before pushing:
npm run lint && npm run format:check && npm run build
cargo fmt --manifest-path src-tauri/Cargo.toml --check
cargo clippy --manifest-path src-tauri/Cargo.toml --all-targets -- -D warnings
cargo test --manifest-path src-tauri/Cargo.toml
Architecture
- Frontend — React + Tauri; a chat-first workspace with a drawer for agents / tasks / memories / artifacts and slide-out transcript and file panels.
- Runtime — Each workspace owns one or more agent rows and a persistent session. Built-in tools (filesystem, inter-agent calls, task management) plus MCP tools, gated by each agent's policy.
- Scheduler — Periodic workspaces run from the agent runner, emitting the same streaming events as interactive chat.
- Skills + templates — Skills are discovered from read-only local or git
sources. The app-managed default source is
juacker/clai-skills; agent templates are embedded viainclude_dir!.
License
MIT