Skip to content
Desktop macOS · Windows · Linux

Put Claude Code, Codex, Gemini, Grok, OpenCode or a local model to work on your folders and repos, with your own accounts.

Download for macOS $ npx @danil-labs/terminus

Free and open source Apache 2.0 Bring your own AI plans

Terminus: a task with Claude Code on the terminus-landing repo — the conversation, the changes of the turn, the build output and the work tree of the task. Terminus: a task with Claude Code on the terminus-landing repo — the conversation, the changes of the turn, the build output and the work tree of the task.
The real app: a Claude Code task on a repo, its changes, its build and its own work tree. Terminus 0.2.71 · demo data

The problem

Your team already works with agents. Just not in one place: a terminal here, a chat tab there, a copy of the repo nobody remembers.

Terminus gives every task a home. One window. Its own copy. The agent you choose.

The real app.
Not a mockup.

Every screen on this page is Terminus itself, running on demo data.

Try the live demo
  1. 01

    Pick the agent.

    Claude Code, Codex, Gemini, Grok, OpenCode or a model on your machine. Per task, with its own model and reasoning.

    The model picker: Claude Code, Codex, Grok, Gemini, OpenCode Free and local models, with reasoning levels. The model picker: Claude Code, Codex, Grok, Gemini, OpenCode Free and local models, with reasoning levels.
  2. 02

    Decide how much it asks.

    Manual, accepts edits or automatic. In manual you see each step before it runs — where the agent supports it.

    Permission modes: Manual, Accepts edits, Automatic. Permission modes: Manual, Accepts edits, Automatic.
  3. 03

    It asks when it matters.

    Questions arrive with options. Your answer stays in the thread, next to what the agent did with it.

    An agent turn with an answered question and its findings. An agent turn with an answered question and its findings.
  4. 04

    See what changed.

    Every turn shows its diff, the commands it ran and their output. Nothing hides in a scrollback.

    Changes observed during the turn and the output of npm run build. Changes observed during the turn and the output of npm run build.

Orchestration

An extension
of you.

Create the agents you need. They split the work, talk to each other and come back with answers, while you think about what's next.

  1. 01

    Create your agents.

    A name and what it does. Each one works by its own criteria and remembers what it learns.

  2. 02

    They coordinate.

    One agent opens tasks for the others, in parallel, each in its own copy. Their answers come back in the same turn.

  3. 03

    You stay in charge.

    They work with your permissions. Anything destructive or outside the brief comes back to you.

Less setup.
More work.

01

Installs what's missing.

It checks your computer and sets up Git, Node and the agents. No commands to learn.

Environment status: Claude Code, Codex, Node.js, Git, GitHub CLI and pnpm, managed by Terminus and up to date. Environment status: Claude Code, Codex, Node.js, Git, GitHub CLI and pnpm, managed by Terminus and up to date.
02

Your accounts. Your plans.

Sign in with the subscriptions you already pay for, and see what's left of each.

AI providers: Claude Code and Codex accounts connected, with usage left for the last 5 hours and this week. AI providers: Claude Code and Codex accounts connected, with usage left for the last 5 hours and this week.
03

Every task in its own copy.

A repo task gets its own work tree. A documents task drafts until you save it.

A refund policy drafted by Claude Code in a documents folder, not yet saved. A refund policy drafted by Claude Code in a documents folder, not yet saved.
04

For you, and for your agents.

A window for people. A CLI for agents, on the same tasks and the same backend.

              # what an agent reads before it starts
              

              $ terminus guide
              

              $ terminus agent-context --json
              

              # same tasks, same backend as the window
              

              $ terminus --help
              

Works with

  • Claude Code Anthropic
  • Codex OpenAI
  • Gemini Google · Antigravity
  • Grok xAI
  • OpenCode Including free models
  • Local models No account needed

Questions.

Do I need to know how to code?

No. Write the task the way you'd tell a teammate. It works on a folder of documents as well as on a repo.

Which AI accounts can I use?

Claude Code, Codex, Gemini (through Antigravity), Grok and OpenCode, with your own subscription. Local models run on your computer and need no account.

Do my files go through Danil?

No. They go from your computer to your AI provider. If you connect a workspace to Radiant, it receives your sign-in and, if your organization asks for it, usage per turn — never your files, transcripts or paths.

Will it touch my folder?

Each task works in its own copy: a work tree in a repo, a draft in a documents folder. You decide when a draft is saved. In a repo, the agent can commit if you ask it to.

What does it cost?

Terminus is free and open source under Apache 2.0. You pay your AI provider, as you do today.

Which systems?

macOS (Apple Silicon and Intel), Windows 10 or 11 (64-bit) and Linux x86_64 as an AppImage (Ubuntu 22.04 or later). It updates itself. With Node: npx @danil-labs/terminus.

Book a demo

Tell us a bit about your team and we’ll find a time to show you Danil.

What are you interested in?

Company size (optional)

By submitting you agree to our privacy notice.

Join the waitlist

In-house AI model: your models, your compute. We’ll let you know when it opens.

What are you looking for? (optional)

By submitting you agree to our privacy notice.