ADF Studio
A desktop app for making and running AI agents on your own computer. Each agent is one .adf file that you keep, copy, and move like any other file.
On this page
- Chat with an agent and see what it does: its reasoning, the tools it calls, and what they return.
- Use the model you choose: a Claude, ChatGPT, or SuperGrok subscription, an API key, or a model running on your computer.
- Approve or reject actions before an agent takes them.
- Run many agents at once and watch them on a map.
- Run agents on this computer and on other computers you connect to, from one window.
Download
| Platform | File | Size | SHA-256 |
|---|---|---|---|
| Windowsx64 installer | ADF-Studio-Setup-0.8.9.exe | 170 MB | ca8db69dc7c6… |
| macOS (Apple Silicon)M1 and later | ADF-Studio-0.8.9-arm64.dmg | 227 MB | 9cfb12ff1f3f… |
| macOS (Universal)Intel and Apple Silicon | ADF-Studio-0.8.9-universal.dmg | 329 MB | e83202e2db95… |
| Linux (Debian, Ubuntu)x64 | adf-studio_0.8.9_amd64.deb | 166 MB | e302b734c64f… |
| Linux (AppImage)x64, needs libfuse2 | ADF-Studio-0.8.9.AppImage | 230 MB | f596ca154ebb… |
Studio is an early release. The format and app may change between versions. Older builds are on GitHub Releases.
Documentation
- Getting started
- First run: make an agent, connect a model, send a message.
- Studio tour
- The window, the Loop, agent configuration, and shortcuts.
- Connections and runtimes
- The local server, connections to other computers, pairing, sharing, and upgrading from 0.7.
- Settings
- Identity, providers, MCP servers, channels, and other app-wide settings.
- Mesh view
- Every agent on one map. Select, command, and approve in groups.
Screenshots







Features
| Feature | What it does |
|---|---|
| Loop | Chat with an agent. The transcript shows your messages, the agent’s reasoning, tool calls, results, and token counts. |
| Agent configuration | Identity, model, instructions, tools, triggers, messaging, serving, and timers, plus the raw config. |
| Files | The agent’s files: README.md, mind.md, soul.md, and any uploaded or agent-written files. |
| Providers | Claude, ChatGPT, and SuperGrok subscriptions (Claude through the Claude Code sign-in on the same computer), hosted APIs (Anthropic, OpenAI, OpenRouter, Gemini, and others), and local servers such as LM Studio or Ollama. Other OpenAI-compatible chat completions servers work when both the server and model support native tool calling. |
| Connections | Agents run in the local server (the ADF daemon), shared with the terminal app. Saved connections add the servers of other computers, each listed as a runtime of its own, and Share lets other devices use this one. |
| Mesh view | Every agent as a tile on a hex map, grouped by directory, with other runtimes as platforms at the edge. Select and command groups with hotkeys. |
| Approvals | Restricted tools pause for human approval, inline on the Mesh view or in a full-context modal. |
| Home dashboard | Status tiles for providers, MCP servers, channels, packages, containers, agents, and networking. |
| MCP servers | Register tool servers and their credentials; attach them to agents. |
| Code execution | Sandboxed code with a shared package store available to every agent on the instance. |
| Computer | Isolated agents can get a small Linux desktop with a managed Chromium, streamed into Studio. |
| Networking | Agent-to-agent messaging over ALF, LAN discovery (mDNS), and HTTP serving of agent content. |
| Multimodal | Image, audio, and video input when the model and agent config enable it. |
| Updates | Checks for new releases hourly and on demand from Settings → About. |
System requirements
| OS | CPU | Package | Notes |
|---|---|---|---|
| Windows | x64 | .exe (NSIS installer) | |
| macOS | Apple Silicon | .dmg (arm64) | Signed and notarized |
| macOS | Intel or Apple Silicon | .dmg (universal) | Signed and notarized |
| Linux | x64 | .deb | sudo apt install ./adf-studio_*_amd64.deb |
| Linux | x64 | .AppImage | Needs libfuse2 |
- At least one model provider: an API key, a local model server, a ChatGPT or SuperGrok subscription, or a Claude Pro or Max plan with Claude Code installed.
- Local models need native tool calling (function calling) for agent tools. Vision is optional: understanding images or screenshots needs image support in the server and model, with image input enabled for the agent. See Local models for server setup requirements.
- Optional: Podman for container-backed compute.
- On first launch Studio creates
~/.adf-studio/for settings, the shared package store, and compute state.
Build from source
Building current ADF main requires Node.js ^22.23.4 || ^24.22.1 || ^26.12.1 and npm. The packaged desktop app includes its own runtime.
git clone https://github.com/christianbalevski/adf.git
cd adf
npm install
npm run dev # launches ADF Studionpm run package builds platform installers with electron-builder. See README and RELEASING.md.