Report · marked 25 Aug 2026

bytedance/UI-TARS-desktop

An agent can work here, but it will waste turns finding its footing.

TypeScript · 38,705 stars · 2,491 files · branch main

69 /100 B

Instructions 3/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on agent instruction file and instruction quality.Setup 18/20Whether an agent can install the project and get it running without a human. Losing marks on reproducible environment.Verification loop 22/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on tests exist and static type checking.Context economy 17/20Whether the repo fits in a context window, or fights it. Losing marks on repository weight.Navigability 10/10How quickly anything new can orient itself. Full marks.

Higher is better. Accent marks what is costing you most.

Fix these first

Agent instruction file

Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.

Instruction quality

Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.

Repository weight

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

The full marking

Every deduction below names the file or setting it came from.

Instructions 3/27 F

Whether the repo tells an agent how to behave before it starts guessing.

✗Agent instruction file 0/12

None found. Every agent that opens this repo starts from zero.

Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.

Looked for AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .cursorrules

✗Instruction quality 0/12

Nothing to judge, since there are no instructions.

Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.

✓README as an entry point 3/3

README has a clear getting-started section.

Setup 18/20 A

Whether an agent can install the project and get it running without a human.

✓Deterministic install 6/6

pnpm-lock.yaml pins the dependency tree.

Found pnpm-lock.yaml

✓Discoverable commands 6/6

Commands are declared where an agent will look for them.

package.json scripts (commit, bootstrap, dev:ui-tars, format, lint, test…)

scripts/ directory

✓Environment config 4/4

.env.example documents what the app needs to run.

✓Pinned runtime version 2/2

The language runtime version is pinned.

Found .node-version

✗Reproducible environment 0/2

No container or devcontainer definition.

A Dockerfile or devcontainer removes an entire class of 'it won't install' failures.

Verification loop 22/25 A

Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.

✗Tests exist 6/8

162 test files against 1464 source files.

e.g. .github/workflows/agent_tars_test.yml, apps/ui-tars/e2e/app.test.ts, apps/ui-tars/src/main/agent/operator.test.ts

✓Test command is discoverable 7/7

An agent can find and run `npm run test`.

✓Continuous integration 4/4

8 GitHub Actions workflows define what "passing" means.

✓Lint and format rules 3/3

.eslintrc.cjs encodes the house style.

✗Static type checking 2/3

Type checking is configured, but not in strict mode.

Turn on `"strict": true`. Type errors are the fastest feedback an agent gets, and non-strict mode silently discards most of them.

Context economy 17/20 A

Whether the repo fits in a context window, or fights it.

✓No committed build output 6/6

No generated directories committed.

✓.gitignore hygiene 3/3

.gitignore covers 15 patterns.

✓File sizes fit in context 6/6

No source file is large enough to crowd out a context window.

✗Repository weight 2/5

About 193MB checked out. Large enough that cloning and searching are both slow.

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

Here is your AGENTS.md

Drafted from what is actually in this repository: the install command from your lockfile, the commands you already declare, your real directory layout. Anything marked TODO needs a person. Save it at the root as AGENTS.md.

AGENTS.md — drafted for bytedance/UI-TARS-desktop

# AGENTS.md

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

## Setup

```
pnpm install
```

## Commands

```
pnpm test          # run the test suite, must pass before any commit
pnpm lint          # lint
pnpm format        # format
pnpm commit
pnpm bootstrap
pnpm dev:ui-tars
pnpm test:bench
pnpm coverage
```

## Layout

- `multimodal/` 934 source files
- `packages/`   307 source files
- `apps/`       164 source files
- `infra/`      31 source files
- `examples/`   20 source files
- `scripts/`    4 source files

## Conventions

- Tests live alongside the code they cover, following `.github/workflows/agent_tars_test.yml`.
- TypeScript is not in strict mode. Turning it on catches a whole class of mistakes before they run.
- CI defines what passing means. See `.github/workflows/agent_tars_test.yml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

## Gotchas

- Copy `.env.example` before running anything that needs configuration.

---

Drafted by agentreadme.com from what is in this repository. Everything marked TODO
needs a human. Check it in as AGENTS.md at the root.

Open the raw markdown or curl -o AGENTS.md agentreadme.com/draft/bytedance/UI-TARS-desktop.md

Show the mark

The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.

[![agent ready](https://agentreadme.com/badge/bytedance/UI-TARS-desktop.svg)](https://agentreadme.com/bytedance/UI-TARS-desktop)

Other TypeScript repositories, marked

freeCodeCamp/freeCodeCamp 69 B openclaw/openclaw 68 B nilbuild/developer-roadmap 45 C vuejs/vue 67 B n8n-io/n8n 87 A anomalyco/opencode 80 A-

All TypeScript repositories

Think this mark is wrong?

Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.

Open an issue, already filled in