WTAgent

What it does

Writes code

YesTakes a plain-language task in the terminal and creates source files in the working directory, then runs them to check the result.WTAgent creates the files in the current directory, runs the script locally, and checks its output.github.com/XiXian42/wtagent ↗

Debugs and fixes

YesThe documented V1 loop runs builds, tests and linters, reads errors from the output and keeps editing until verification passes.4. 安装依赖并执行构建、测试和静态检查。 5. 启动开发服务并读取日志。 6. 根据错误继续修改。github.com/XiXian42/wtagent/blob/main/d… ↗

Ships it

PartlyPushing, releasing and deploying are permitted but classified as external-risk actions that always stop for an explicit human approval prompt.| `external` | `git push`、发布、部署 | 审批 |github.com/XiXian42/wtagent/blob/main/d… ↗

Not established: Writes tests, Reviews code, Whole-codebase work

How much it does unattended

Runs autonomously

PartlyReads, writes and ordinary project commands run automatically, but a human must sign in to the web AI first and approve anything sensitive or destructive.项目目录内的常规开发操作可自动执行。 - 访问项目外、读取凭证、提权、批量删除、推送或部署必须确认。github.com/XiXian42/wtagent/blob/main/d… ↗

Agent permissions

PartlyA local policy engine grades every tool call by risk: reads, writes and builds inside the project run unattended, sensitive or destructive calls need approval.| `read` | 项目内读取、搜索、列目录 | 自动 | | `write` | 项目内创建、编辑文件 | 自动 | | `sensitive` | 访问项目外、读取凭证、外部网络写操作 | 审批 |github.com/XiXian42/wtagent/blob/main/d… ↗

Not established: Multi-agent

Which models it runs on

Claude

YesClaude is a first-class provider selected with a flag; it uses whichever model your claude.ai browser profile already has chosen.Claude keeps the model selected by claude.ai in its browser profile; WTAgent does not override it.github.com/XiXian42/wtagent ↗

GPT

YesChatGPT is the default provider and the product's headline use case, including Pro accounts, driven through the signed-in web session.Turn ChatGPT Web (including Pro) into Codex.xixian42.github.io/wtagent ↗

Open models

PartlyProviders include DeepSeek, Kimi and GLM, whose weights are published openly, but WTAgent drives their hosted web chat rather than running any weights locally.Supported values are `chatgpt`, `claude`, `deepseek`, `gemini`, `kimi`, and `glm`github.com/XiXian42/wtagent ↗

Model choice

YesYou pick the provider on the command line from a published list, and two of them inherit whatever model your browser profile has selected.Choose a provider with `--model` (ChatGPT is the default).github.com/XiXian42/wtagent ↗

Where you use it

In your editor

NoThere is no editor extension or plugin: the vendor scopes the first version to a terminal CLI and says outright that no plugin is involved.V1 是 CLI，不做桌面 GUI 和远程控制台。github.com/XiXian42/wtagent/blob/main/d… ↗

On the command line

YesThe terminal is the only interface: you install globally with npm, run wtagent in a project directory and type tasks at a prompt.npm install -g wtagentxixian42.github.io/wtagent ↗

In your pipeline

NoIt needs a visible, non-headless Chrome with a manually signed-in web account, which rules out unattended pull-request or CI execution.github.com/XiXian42/wtagent/blob/main/d… ↗

In a browser

NoNo hosted dashboard or remote console exists; the vendor explicitly excludes a desktop GUI and a remote console from this version.V1 是 CLI，不做桌面 GUI 和远程控制台。github.com/XiXian42/wtagent/blob/main/d… ↗

Whose machine it runs on

Self-hosted

YesEverything but the chat itself runs on your own machine: files are created and commands executed locally by the installed CLI.Files and commands run locally, but code and output returned to the chat are sent to your web AI provider.xixian42.github.io/wtagent ↗

Open source

YesThe full source sits in a public GitHub repository under the MIT licence, with the licence linked from the site footer.Open source · MITxixian42.github.io/wtagent ↗

What it costs to run

How it meters

YesThe tool itself charges nothing; consumption is metered by whichever web AI account you sign in with, under that provider's own quota.WTAgent itself does not require an API key. It uses your own web account, available models, and quota.github.com/XiXian42/wtagent ↗

Free tier

YesA single global npm install with no sales contact, no account with the vendor and no API key required to start.No API key. No MCP. No tunnel. No plugin.xixian42.github.io/wtagent ↗

API access

NoIt ships only an interactive terminal binary; the vendor documents no HTTP API or library surface you could call from your own stack.V1 是 CLI，不做桌面 GUI 和远程控制台。github.com/XiXian42/wtagent/blob/main/d… ↗

MCP server

NoThe vendor advertises the absence of MCP as a selling point, so no other agent can query WTAgent over that protocol.No API key. No MCP. No tunnel. No plugin.xixian42.github.io/wtagent ↗

Bring your own key

PartlyYou bring your own inference, but as a signed-in web chat account in a dedicated Chrome profile rather than an API key or your own cloud.A dedicated Chrome profile opens. Sign in with your own web AI account when prompted. ChatGPT is the default provider.xixian42.github.io/wtagent ↗

Buying it for a team

Admin controls

PartlyConstraints are local, not organisational: a policy engine bounds paths to the project root and forces approval prompts, but no central admin console exists.所有文件路径必须： 1. 相对项目根目录解析； 2. `realpath` 后仍位于项目根目录；github.com/XiXian42/wtagent/blob/main/d… ↗

Audit log

PartlyEach session writes a local event log and raw tool output to disk, which is a developer record rather than an administrative audit trail.sessions/<session-id>/ session.json events.jsonl rollout-<timestamp>-<session-id>.jsonl tool-output.jsonlgithub.com/XiXian42/wtagent/blob/main/d… ↗

What happens to your code

Opt out of training

NoWTAgent offers no opt-out control of its own; whatever code it sends into the chat falls under your provider's terms and settings.Use your own account and follow your provider’s terms and limits.xixian42.github.io/wtagent ↗

Data residency

PartlyYour files and commands never leave your machine, but any code pasted into the chat lands in your web AI provider's jurisdiction, not WTAgent's.Files and commands run locally, but code and output returned to the chat are sent to your web AI provider. Do not share secrets or unauthorized data.xixian42.github.io/wtagent ↗

Getting out

YesThere is nothing to export from a vendor: session state, event logs and tool output are plain JSON and JSONL files on your own disk.状态持久化 | V1 使用原子 JSON + JSONL 事件日志；数据量增大后再迁移 SQLitegithub.com/XiXian42/wtagent/blob/main/d… ↗

Not established: Certifications