Trebell. Download 2.1.6
Trebell Code 2.0

A desktop workspace for AI coding agents

Trebell Code gives AI coding agents one desktop workspace: files, a terminal, Git and pull requests, worktrees, previews and a browser panel. Version 2.0 runs Trebell Native, Trebell's own agent, beside Codex, Claude Code, OpenCode, Cursor, Grok Build, Antigravity and the new Muse Code.

Version 2.1.6Windows 10/11 (x64)FreeWorks with many providers
Trebell Code 2.0 in dark mode: a Trebell Native thread whose activity card lists the files it read and edited, with one edit's diff open, above the reply, and the Diff panel with the changed files beside itTrebell Code 2.0 in light mode: a Trebell Native thread whose activity card lists the files it read and edited, with one edit's diff open, above the reply, and the Diff panel with the changed files beside it
What it provides

What's in Trebell Code

Everything around the model: the files, tools and history an agent needs to do work you can inspect, check and recover.

Context

Repository-aware sessions

Projects and environments, files and each thread's conversation stay attached to the engineering task instead of living in an isolated chat box.

Execution

Terminal, files and Git

Agents edit files, run commands and work with Git, pull requests and worktrees, with a terminal, previews and a browser panel beside them.

Visibility

Every turn shows what it did

Each turn keeps an activity card that says what each step did, such as a command's exit code and duration or an edit's diff. Trebell Native checks its work on code-change tasks before it answers.

Runtime

Trebell Native + seven harnesses

Trebell Native is Trebell's own agent harness. Codex, Claude Code, OpenCode, Cursor, Grok Build, Antigravity and Muse Code run as their real harnesses, each with its own sign-in and approvals.

Models

Your choice of model

Each harness brings its own model list, options and default, and a reopened thread resumes on the model it used, so you can change agents without rebuilding the workflow.

Recovery

Long-running work

Trebell Native waits out network drops instead of failing the turn. With Codex, Cursor, Grok Build and Antigravity, coming back to a running thread shows its reply from the start, in order.

Benchmarks

We measure the finished result and what it cost.

Trebell benchmarks the same model across coding harnesses on fresh tasks, graded by an independent verifier. Against Codex using the OpenAI API, with the same model and settings, Trebell Native resolved as many or more tasks on SWE-bench Multilingual, Terminal-Bench 2.0 and Terminal-Bench Pro 1.0. On the tasks where both got the same result, its API-equivalent cost was 18% lower on SWE-bench Multilingual and 28% lower on Terminal-Bench 2.0.

The full results are on the product site.

Each result is listed with its benchmark, the number of fresh tasks, the verifier outcome, the model and reasoning settings and the cost comparison, so you can check it yourself.