Control teams of AI agents.

Local-first, open source, sandboxed. One team per workspace — each with its own provider, files, tools, and permissions, working in parallel, on a schedule, and reporting to you from one Fleet cockpit.

Local-first Open source Sandboxed
Download for desktop View source

See the work as it happens.

One Fleet cockpit — agent messages, tool calls, delegated tasks, files, memory, and generated artifacts, in one place.

Desktop appBuilt for local workspaces on macOS, Windows, and Linux.
Open sourceCLAI Desktop is MIT licensed and developed in the open on GitHub.
Local controlsChoose what each agent can read, write, and run on your machine.
Model choiceRun local models (Ollama, LM Studio, vLLM), API providers, or CLI agents per workspace and agent.

Built around the way agent work actually happens.

One workspace, one team, one cockpit.

Model choice

Pick a model and a stack per workspace.

Local Ollama / LM Studio / vLLM, hosted OpenAI/Anthropic, or your existing CLI agents — Claude Code, Codex CLI, OpenCode.

  • Self-hosted and local model presets are first-class.
  • Hosted OpenAI-compatible and Anthropic-compatible APIs fit into the same provider list.
  • CLI-backed agents can use your existing subscription login.
CLAI provider picker showing hosted providers, local CLI agents, and self-hosted local model options including Ollama, LM Studio, and vLLM.
Agent teams

Each agent gets its own role, provider, files, tools, and permissions.

A workspace can have a main agent plus helpers for review, research, operations, or any task you want to split out. Each agent gets its own instructions, skills, MCP servers, provider connection, and local permissions.

  • Pick skills and MCP servers per agent instead of sharing everything by default.
  • Use local filesystem and shell grants to keep the agent's scope clear.
  • Delegate work from the main agent without losing the task transcript.
CLAI workspace settings modal for adding a sub-agent with skills, MCP servers, provider connections, and local capabilities.
Schedules

Schedules run the workspace — not just a prompt.

Hourly, daily, cron, or timezone-aware. Outputs, transcripts, and artifacts stay attached to the workspace.

  • Use quick presets or write a cron expression.
  • Preview the next run times in your timezone.
  • Keep outputs, transcripts, and artifacts attached to the same workspace.
CLAI schedule settings showing a recurring cron schedule, timezone, and upcoming run times.

Everything an agent workspace needs.

CLAI brings the practical pieces together: models, MCP tools, skills, permissions, schedules, transcripts, and files.

Local and hosted models

Local (Ollama, LM Studio, vLLM, LiteLLM) and hosted providers — OpenAI-compatible and Anthropic-compatible.

CLI agents

Run Claude Code, Codex CLI, and OpenCode from a workspace and keep their outputs in the Fleet cockpit.

MCP client

Connect MCP servers with static credentials or OAuth, then choose which workspaces and agents can use them.

Scheduled teams

Run a workspace on a schedule — hourly, daily, cron. Preview the next runs before saving.

Skills

Reuse instructions from bundled, local, or Git-backed skill sources and attach them where they help.

Artifacts and transcripts

Keep generated files, task transcripts, and durable memories next to the workspace that produced them.

Set it up once, reuse it often.

Create a workspace for a project or recurring task, give agents the right context, and come back to a clear record of what happened.

Connect providers and tools

Add API providers, local CLI agents, and MCP servers from Settings.

Assemble a team

Attach the right model, tools, skills, files, and helper agents to a workspace.

Run the workspace

Start work immediately, schedule it on a cadence, and review transcripts, memories, and artifacts when it finishes.

Questions, feedback, or integration ideas?

Reach the CLAI team directly for product feedback, MCP integrations, packaging questions, or collaboration.

Prefer the open channel? Ask or share feedback in GitHub Discussions.