WorkAny
A desktop agent that turns natural-language requests into workspace, code, and tool operations.
- Source repo
- workany-ai/workany
- Stars
- ★ 1.5k
- Last updated
- 3mo ago
- License
- NOASSERTION
- Primary language
- TypeScript
- FA score
- 46/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformOpenAI API · Claude API
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- An individual organizing files in a local workspace can submit the file-handling task in natural language.
- Not a fit if
- Users unwilling to install Node.js, pnpm, and the Rust toolchain
- Enterprises that need clear licensing and documented sandbox security boundaries
- Source review
- 46/100 · Major gaps 1 safety controls not found
What does this agent do, and when should you use it?
WorkAny is a desktop AI agent application that accepts natural-language tasks and streams execution in real time. Its repository describes a React 19, TypeScript, Vite, and Tailwind CSS 4 frontend; a Hono and @codeany/open-agent-sdk backend; and a Tauri 2, Rust, and SQLite desktop layer. The agent runtime runs in-process without an external CLI and exposes more than 30 built-in tools for file I/O, shell execution, web search, code editing, and related work. It can preview HTML, React, and code artifacts, while extending through custom skills and MCP servers over stdio, SSE, or HTTP. It fits users who want file work, code generation, and office-style output in one desktop workspace, provided they can support the required Node, pnpm, and Rust environment.
A user submits a natural-language task and WorkAny executes it with real-time streaming. Its Hono and @codeany/open-agent-sdk backend runs in-process and can use more than 30 built-in capabilities, including File I/O, shell execution, web search, and code editing; the desktop application manages the workspace and offers an isolated Sandbox for code execution. It can generate or handle code, HTML/React files, documents, data tables, and slides, with live Artifact Preview for HTML, React, and code files. Model access supports OpenRouter, Anthropic, OpenAI, and compatible API endpoints, while MCP servers can be integrated through stdio, SSE, or HTTP.
- An individual organizing files in a local workspace can submit the file-handling task in natural language.
- A developer prototyping a website can generate code and inspect HTML, React, or code artifacts in the application.
- An office user preparing a first draft of a document, data table, or slide deck can initiate the generation task from one desktop app.
- A team with existing MCP services can connect them to desktop task flows through stdio, SSE, or HTTP.
- A user working across OpenAI, Anthropic, OpenRouter, or a compatible endpoint can select a custom model provider for the agent.
How do you install or deploy this agent?
Requirements: Node.js >= 20, pnpm >= 9, and Rust >= 1.70. Install dependencies, then start the API and desktop application:
pnpm install
pnpm dev:api
pnpm dev:appThe README does not document where to enter model-provider credentials or the exact UI action for submitting a first task.
How do you use this agent?
Run pnpm dev:api, then pnpm dev:app to start the Web and desktop application. Enter a task in natural language; the README shows file organization, website generation, document generation, data-table generation, and slide generation as examples. For model access, use OpenRouter, Anthropic, OpenAI, or a compatible API endpoint. To extend the toolset, integrate an MCP server over stdio, SSE, or HTTP.
What are this agent's strengths and limitations?
- The runtime uses @codeany/open-agent-sdk in-process, with no external CLI dependency stated in the README.
- It consolidates more than 30 tools—including file I/O, shell execution, web search, and code editing—into a desktop task flow.
- It supports OpenRouter, Anthropic, OpenAI, and compatible API endpoints rather than documenting only one provider.
- It supports MCP servers over stdio, SSE, and HTTP, plus custom skills for extension.
- It provides live Artifact Preview for HTML, React, and code files.
- Local development requires Node.js, pnpm, and Rust, creating more setup overhead than a browser-only tool.
- The README does not specify API-key setup, provider configuration, or a default model.
- The Sandbox is described as isolated, but its permission boundaries and security guarantees are not documented.
- The README does not document failure recovery, task limits, resource limits, or concurrency behavior.
- Licensing needs verification before adoption: repository metadata is NOASSERTION, while the README describes a WorkAny Community License with additional conditions based on Apache License 2.0.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| WorkAny This agent | 46 · Major gaps | Desktop appFree + model costs | ★ 1.5k | 3mo ago | TypeScript | OpenAI API · Claude API |
| Ankita Desktop AI Workspace | 69 · Some gaps | Desktop appFree + model costs | ★ 15 | 7d ago | JavaScript | ChatGPT · OpenAI API |
| MyAgents | 57 · Major gaps | Desktop appFree + model costs | ★ 592 | 1d ago | TypeScript | Codex · Claude Code · Claude API |
| OpenHuman | 57 · Major gaps | Desktop appFreemium | ★ 43k | today | Rust | — |
How does FollowAgents rate this agent?
Why each dimension lost points
The README claims an in-process agent, sandbox, and broad tool set; the supplied API entry point shows configuration loading, built-in skill installation, and local server startup. The web-access skill uses CDP with the user's logged-in Chrome session and permits arbitrary JavaScript, clicks, and file uploads, while advising use of a new background tab and closing it afterward. Evidence for least privilege, confirmation, data flows, and sensitive-data handling is limited, so each scores 1. Browser operations and shell-related tools can cause external effects, but general safeguards are not sufficiently shown, scoring 1. No rollback mechanism is evidenced, scoring 0. The skill names an author, version, and source, and the license identifies a copyright holder, so source attribution scores 2.
The README, package configuration, and API entry point support a consistent picture of the desktop app, development commands, and stack, scoring 2 for self-consistency. Runtime requirements and dependency ranges are provided, but the supplied material does not include a lockfile or evidence of dependency availability safeguards, scoring 1. The API has 404 and 500 responses and startup error logging, but the error response is generic, scoring 1.
The README identifies file organization, web, document, spreadsheet, and slide tasks, while the skill covers search, scraping, and browser interaction, scoring 2 for audiences and scenarios. The skill specifies trigger situations and an operating approach, scoring 2 for trigger precision. Multiple model providers and desktop and web development modes support environment fit, scoring 2. Capability boundaries and restrictions on risky actions are only lightly documented, scoring 1.
The README provides project structure, stack, previews, development steps, and a contribution link, scoring 2 for information architecture. Development setup is documented, but end-user installation guidance is limited in the supplied material, scoring 1. Product and package naming are broadly consistent, scoring 2. README previews and skill operation examples are concrete, scoring 2. Known limitations are sparsely documented, scoring 1. The license is explicit but includes commercial, derivative-work, and frontend attribution conditions, scoring 2. Package, API, and skill versions appear, but no changelog is in the supplied material, scoring 1. The license and README identify an organization and contact email, but do not clearly describe maintenance commitments or update paths, scoring 1.
The feature descriptions and interface previews indicate that natural-language tasks, tool execution, and artifact previews can be combined in a desktop workflow, scoring 2 for output usability. Built-in tools, MCP, skills, and multiple providers show clear potential added value, scoring 2. The materials do not sufficiently establish costs, resource use, or cost-benefit, scoring 1.
Some major README claims about features and the stack have corresponding support in the package configuration, API entry point, and sample skill, scoring 2 for claim traceability. Cross-source support covers only part of the architecture and capabilities; broader implementation evidence is not supplied, scoring 1. The materials do not systematically separate implemented facts from promotional claims, scoring 1 for fact-inference separation.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- The web-access skill can use the user's logged-in Chrome session and run arbitrary page JavaScript; review access scope, file uploads, and submission actions carefully before use.
- This assessment uses only the supplied static sample and does not verify runtime behavior, the full dependency set, or rollback capabilities. The license also has commercial-use and frontend attribution conditions.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/workany)<a href="https://followagents.com/en/agents/workany"><img src="https://followagents.com/badge/workany.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v0.1.19 WorkAny v0.1.19
Release notes excerpt
Full Changelog: https://github.com/workany-ai/workany/compare/v0.1.18...v0.1.19View on GitHub ↗ -
v0.1.18 WorkAny v0.1.18
Release notes excerpt
What's Changed * feat: add Kimi CLI agent support by @keyuyuan in https://github.com/workany-ai/workany/pull/21 * Add API connection detection for custom providers by @fengcunhan in https://github.com/workany-ai/workany/pull/32 New Contributors * @keyuyuan made their first contribution in https://github.com/workany-ai/workany/pull/21 Full Changelog: https://github.com/workany-ai/workany/compare/v0.1.17...v0.1.18View on GitHub ↗ -
v0.1.17 WorkAny v0.1.17
Release notes excerpt
What's Changed * fix: Claude Code not found in windows by @joglea in https://github.com/workany-ai/workany/pull/16 * fix: soften message scrollbars by @fancyboi999 in https://github.com/workany-ai/workany/pull/23 * fix: align agent session ids across service and providers by @fancyboi999 in https://github.com/workany-ai/workany/pull/25 * fix: sync tauri window theme by @fancyboi999 in https://github.com/workany-ai/workany/pull/27 * fix: enforce response language by settings by @fancyboi999 in https://github.com/workany-ai/workany/pull/28 …View on GitHub ↗
FAQ
Must I use a particular model provider?
Does it depend on an external agent CLI?
Can it affect local files or run system commands?
Can it connect to an existing MCP service?
How should I evaluate cost and licensing?
Thanks — we use this to improve the page.