Features
200+ models, real files, real computers, custom agents, voice, and automations — designed to work as one workspace.
GPT, Claude, Gemini, Grok, Llama: pick mid-conversation, cheapest-first.
Voice in, voice out. Claude, GPT, Gemini, whichever you pin.
A push-to-talk overlay that floats above every app: ask, hear the answer, keep working.
Real-time info, cited sources, every model: no per-provider tax.
DALL·E, Imagen, FLUX, Stable Diffusion: same composer, same files.
Veo, Runway, Kling, Luma: short clips generated in chat, saved to your Drive.
Dozens of voices for text to speech, plus fast accurate transcription: in every chat.
Dictate messages and transcribe recordings, accurately, in any chat.
Folders, previews, and lightweight versioning for AI work.
Store API keys, tokens, and passwords: encrypted, never shown to agents.
Public URLs for files, agents, and chats: granular, revocable.
Shared folders, agents, computers, and chats: one container.
Tasks Lists, multiple assignees, sub-tasks, blockers, and duplicates: clean OR-123 ids.
A durable, private memory every agent reads and updates as it works.
Skills, scoped permissions, persistent memory: any model you pick.
Parallel subagents, isolated context, full observability.
Delegated runs with schedules, bounded execution, and full progress traces.
Installable instruction bundles agents load on demand: curated, forkable, shareable.
Use any model in normal idapt Chat to inspect, edit, test, and deliver code.
Sandboxed Python, Node, and shell: agents and you, side-by-side.
Daemon-connected machines with real filesystems and agent-friendly controls.
Agents see the screen, click, and type to finish real UI work: with your consent.
The desktop overlay reads your screen and points you to the next step, so you click.
Run any Docker image or Compose file on your computers. Secrets and backups included.
Spin up cloud machines your agents can use: per-second billing, hibernate when idle.
Run open models on your own hardware with Ollama: private, free, no rate limits.
OpenAI-, Anthropic-, and OpenRouter-compatible endpoints with routing you control.
A typed SDK and a versioned REST API over chats, files, agents, and computers.
Script files, agents, chats, and 200+ models: from your shell.
Use your files, agents, and tools from any MCP-compatible client.
One command exposes any port. SSH included.