# AutoCua > AutoCua is an open-source Python agent that operates a computer the way a person does, desktop apps, a terminal, your own Chrome and iOS or Android phones, with any of 60 models from ten providers. - Canonical: https://www.anchorterminal.com/tools/autocua - Pricing: https://www.anchorterminal.com/tools/autocua#pricing - Reviews: https://www.anchorterminal.com/tools/autocua#reviews - Markdown: https://www.anchorterminal.com/tools/autocua.md (~4,750 tokens) - Slim: https://www.anchorterminal.com/tools/autocua.min.md (~1,280 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/autocua.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT autocua.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-06 ## Overview **Grade E · 44.3/100 · rank #1100 of 1354 · #8 in Desktop & mobile app control · not agent-ready · confidence low** ## Assessment A capable, fast-moving open-source agent for driving desktops, browsers and phones through real input and accessibility trees, with a careful safety section. It's two weeks old, with no test CI or changelog, and on Windows the model itself decides whether to accept an admin elevation prompt. ## Facts | Field | Value | | --- | --- | | Vendor | Ashish Yadav and contributors (ComputerUseAgent on GitHub) (https://github.com/ComputerUseAgent/AutoCua) | | Kind | Agent framework | | Category | Desktop & mobile app control (https://www.anchorterminal.com/categories/desktop-automation) | | Auth | None · No account. You bring an API key for the model provider you choose, kept with chats, Chrome profiles and a credential vault in a local AutoCua_data folder. | | Pricing | Free (Free · OSS) · Free and MIT-licensed. You pay your model provider for tokens. Nothing to buy from the project (checked 2026-11-06). | | x402 | No · A local package with nothing to buy and no payment protocol (checked 2026-11-06). | | Licence | MIT | | Packages | pypi: `AutoCua` | | Source | https://github.com/ComputerUseAgent/AutoCua | | Docs | https://github.com/ComputerUseAgent/AutoCua#readme | | llms.txt | not found | | Last release | 2026-11-04 | | Surface graded | The open-source package, read from a clone of github.com/ComputerUseAgent/AutoCua (main at c7ca4db) on 6 November 2026: the README, pyproject.toml, licence, workflows and tags. Nothing was installed or run, and GitHub issues weren't read | | Modes | computer use (macOS, Windows, Linux with GNOME), computer use with phone sub-agents, shell use, web use through your own Chrome and an extension, mobile use on an iOS Simulator or paired iPhone (Mac only) and on an Android emulator or phone | | Safety | A UAC prompt is asked of the model with no screenshot, and its alt+y or alt+n is injected through the Interception driver. The worker tool set has no write tool, unseen element ids are refused, vault credentials are typed by the runtime, nothing is downloaded without a yes, stop is checked before every action, and shell commands are capped at 10 minutes | | Data | Chats, API keys, persistent Chrome profiles, the credential vault and skills live in AutoCua_data next to the checkout or the working directory, or where AutoCua_DATA_DIR points | | Releases | Tags v0.1.6 (30 October), v0.1.7 (31 October), v0.1.8 (3 November) and v0.1.9 (4 November) 2026, and a PyPI wheel per OS and architecture with the Rust extensions prebuilt | | Capabilities | browser.control, agent.run | | Tags | open-source, mit, python, computer-use, local, new | | JSON | https://www.anchorterminal.com/api/v1/tools/autocua.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: low. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 25 | 5.0 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 42 | 6.8 | | Agent ergonomics | 13% | 16.2 | 55 | 8.9 | | Security & auth | 14% | 17.5 | 38 | 6.7 | | Payments & pricing | 10% | 12.5 | 60 | 7.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 65 | 5.7 | | Transparency & trust (editorial 70, provenance 13) | 7% | 8.8 | 42 | 3.7 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **44.3 → E** | ### Why each score - Reliability 25 (checked 2026-11-06): Local package. Installs from PyPI as AutoCua with Python 3.10 or later and the supported platforms stated (20). No CI runs the tests; the only workflow, use_case_label.yml, labels issues (0). GitHub issues weren't read, so the open-issue line is scored absent (0). Four tags in a week with no changelog file (5). Version 0.1.9 (0). 20 + 0 + 0 + 5 + 0 = 25. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 42 (checked 2026-11-06): Framework reading. No API reference or typed interface beyond run_agent's documented arguments (5 of 25). No llms.txt (0). The README says what each mode drives and where it runs, and agent_capabilities.md lists what it can do (16 of 20). Modes and device are documented strings (6 of 15). Many examples, no documented errors (10 of 15). Tags without a changelog (5 of 15). 5 + 0 + 16 + 6 + 10 + 5 = 42. - Agent ergonomics 55 (checked 2026-11-06): Framework reading. One call with a mode, provider, model and task runs a whole agent (20 of 25). A separate compression agent splices handoff summaries in, and runs are capped and stoppable (15 of 20). Permission and blocked-input errors are reported specifically, with no error reference (8 of 20). No resume or retry semantics described (2 of 20). Sensible defaults (simulators unless device is set), Python only (10 of 15). 20 + 15 + 8 + 2 + 10 = 55. - Security & auth 38 (checked 2026-11-06): Framework reading (telemetry, approvals, guardrails, sandboxing). Provider keys stored in a local folder with Chrome profiles (10 of 30). The worker tools are an allow-list with no write tool, unseen ids are refused, downloads need a yes, but on Windows the model answers UAC elevation prompts itself through a kernel driver, with no person asked (6 of 20). The scraping ruleset has a prompt-injection instruction to log page text that gives instructions (10 of 15). Runs are logged in the app, with no audit log (7 of 15). No security policy, disclosure route or advisories found (5 of 20, for the vault and certificate handling). 10 + 6 + 10 + 7 + 5 = 38. - Payments & pricing 60 (checked 2026-11-06): Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 65 (checked 2026-11-06): v0.1.9 tagged on 4 November 2026 (30). Four tags in 90 days (20). Issues and pull requests weren't read (0 of 25). The PyPI wheel is current (15). No CI; dependencies pinned per OS in requirements files (0 of 10). 30 + 20 + 0 + 15 + 0 = 65. - Transparency & trust 42 (checked 2026-11-06): MIT (30). Says it sends data only to the chosen model provider and keeps everything else locally, and the source agrees (20 of 30). No deprecation policy (0). States no telemetry, and none was found (20). 30 + 20 + 0 + 20 = 70. Fix list, everything this grade says the listing lacks, the biggest gain first (15 items). What it covers is at https://www.anchorterminal.com/fixes/autocua.md (JSON https://www.anchorterminal.com/fixes/autocua.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "autocua", "plan": "read"}`, free while the beta runs ### What we couldn't check - unchecked: GitHub issues and pull requests (not read), and the PyPI release history (registry JSON not requested) - Who runs it. The licence names Ashish Yadav and most commits are from FunctionFreak; no company or site found - Model-decided UAC elevation on Windows scored as a security weakness, not a deduction, since the README discloses it ### Sources - repository README, pyproject.toml, licence, workflows and tags, cloned at c7ca4db: (seen 2026-11-06) - same repository under the AutoCua organisation, main branch matching: (seen 2026-11-06) - lead, Agent Tools Today for 5 November 2026: (seen 2026-11-06) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/autocua/history.json - 2026-11-06: graded 44.3 E (methodology 0.7) ## Who's behind it (provenance 13/100, checked 2026-11-06) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | not found | 0/20 | | Domain age | github.com, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | nothing hosted, so the MIT licence stands in | 10/10 | | Privacy policy | nothing hosted, not scored | n/a | | Status page | not found | 0/10 | | Changelog | not found | 0/10 | | security.txt | not found | 0/10 | | People named | not researched yet | n/a | | Support route | not researched yet | n/a | The licence names Ashish Yadav as copyright holder; most commits are from the GitHub user FunctionFreak. No company, site or terms were found. github.com/AutoCua/AutoCua and github.com/ComputerUseAgent/AutoCua serve the same main branch, so one is a rename or mirror of the other. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full. **Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored. ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Strengths - One run_agent call drives the desktop, a terminal, your Chrome, or an iOS or Android device - Element picking from accessibility trees and OCR instead of pixel coordinates - Credentials typed from a vault so the model never sees them, in the browser and phone agents - No telemetry, and nothing downloaded without a yes on the terminal - MIT licence, a pip wheel per OS and architecture, and 60 models across ten providers ## Weaknesses - Two weeks old at version 0.1.9, with no changelog file - No CI running the tests; the only workflow labels issues - On Windows the model answers UAC elevation prompts itself through a kernel input driver - Keeps API keys and logged-in Chrome profiles in a local folder next to the checkout - No API reference beyond the README ## Before you call it (notes for agents) 1. pip install AutoCua, then call run_agent with a mode such as "web use" or "computer use", a provider, a model and a task 2. Run it on a machine or account you can afford to lose; it drives real input and keeps logged-in browser profiles 3. On Windows, don't install the Interception driver unless you accept the model deciding UAC prompts 4. Set AutoCua_DATA_DIR to keep keys and profiles somewhere private 5. Phones go over USB from a script; Wi-Fi only through the desktop app ## Get started Install: ```bash pip install AutoCua # then, in Python: # from AutoCua.agent_launcher import run_agent # run_agent(mode="web use", provider="openrouter", model="gemini-3.8-flash", task="Open wikipedia.org and summarise today's featured article.") ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Browser Use | A | 80.3 | 9 | browser.control | yes | https://www.anchorterminal.com/tools/browser-use.md | | Chrome DevTools MCP | BB | 72.4 | 112 | browser.control | no | https://www.anchorterminal.com/tools/chrome-devtools-mcp.md | | Browserbase | BB | 72.3 | 116 | browser.control | yes | https://www.anchorterminal.com/tools/browserbase.md | | Steel | BB | 71.5 | 140 | browser.control | yes | https://www.anchorterminal.com/tools/steel.md | | Selenium | BB | 70.8 | 168 | browser.control | no | https://www.anchorterminal.com/tools/selenium.md | | Puppeteer | BB | 70.7 | 172 | browser.control | no | https://www.anchorterminal.com/tools/puppeteer.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - Shown on Hacker News on 4 November 2026, the day v0.1.9 was tagged. The repository's first commit is 20 October 2026, with about 150 commits since (source: ) - Acts through each operating system's own input layer and an accessibility tree fused with OCR, so the model picks numbered elements instead of coordinates, per the README (source: ) - On Windows, a UAC elevation prompt is put to the model as an allow-or-decline step and answered through the Interception kernel input driver, which you install yourself (source: ) - Says it sends nothing anywhere except to the chosen model provider, and Telegram if you connect it; the source has no analytics library (source: ) - The README's badges and links point to github.com/AutoCua/AutoCua, which serves the same main branch as ComputerUseAgent/AutoCua (source: ) - #8 of 9 in Best desktop and mobile app automation for AI agents: https://www.anchorterminal.com/best/desktop-automation/index.md - All 48 desktop comparisons: https://www.anchorterminal.com/compare/desktop-automation/index.md ## Compare - [agent-browser vs AutoCua](https://www.anchorterminal.com/compare/agent-browser-vs-autocua.md): B 64.1 vs E 44.3 - [Airtop vs AutoCua](https://www.anchorterminal.com/compare/airtop-vs-autocua.md): C 54.5 vs E 44.3 - [Anchor Browser vs AutoCua](https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.md): C 60.1 vs E 44.3 - [AutoCua vs Browser Use](https://www.anchorterminal.com/compare/autocua-vs-browser-use.md): E 44.3 vs A 80.3 - [AutoCua vs Browserless](https://www.anchorterminal.com/compare/autocua-vs-browserless.md): E 44.3 vs B 67.9 - [AutoCua vs BxPlaywright](https://www.anchorterminal.com/compare/autocua-vs-bx-playwright.md): E 44.3 vs C 55 - [AutoCua vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/autocua-vs-chrome-devtools-mcp.md): E 44.3 vs BB 72.4 - [AutoCua vs Functionize MCP server](https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.md): E 44.3 vs E 44.6 - [AutoCua vs Hyperbrowser](https://www.anchorterminal.com/compare/autocua-vs-hyperbrowser.md): E 44.3 vs B 67.7 - [AutoCua vs Kane CLI](https://www.anchorterminal.com/compare/autocua-vs-kane-cli.md): E 44.3 vs C 55.3 - [AutoCua vs Lightpanda](https://www.anchorterminal.com/compare/autocua-vs-lightpanda.md): E 44.3 vs C 56.2 - [AutoCua vs Notte](https://www.anchorterminal.com/compare/autocua-vs-notte.md): E 44.3 vs C 59.7 - [AutoCua vs Playwright MCP](https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp.md): E 44.3 vs B 63.7 - [AutoCua vs Pomerado](https://www.anchorterminal.com/compare/autocua-vs-pomerado.md): E 44.3 vs B 62.5 - [AutoCua vs Puppeteer](https://www.anchorterminal.com/compare/autocua-vs-puppeteer.md): E 44.3 vs BB 70.7 - [AutoCua vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/autocua-vs-puppeteer-reference-server-archived.md): E 44.3 vs F 30.8 - [AutoCua vs Robocorp](https://www.anchorterminal.com/compare/autocua-vs-robocorp.md): E 44.3 vs B 65.5 - [AutoCua vs Selenium](https://www.anchorterminal.com/compare/autocua-vs-selenium.md): E 44.3 vs BB 70.8 - [AutoCua vs Skyvern](https://www.anchorterminal.com/compare/autocua-vs-skyvern.md): E 44.3 vs C 57.5 - [AutoCua vs Steel](https://www.anchorterminal.com/compare/autocua-vs-steel.md): E 44.3 vs BB 71.5 - [AutoCua vs TinyFish](https://www.anchorterminal.com/compare/autocua-vs-tinyfish.md): E 44.3 vs B 68.2 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from the front page of github.com/computeruseagent or of one of its repositories, or the README at the root of github.com/ComputerUseAgent/AutoCua. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "autocua", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html AutoCua on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![AutoCua on Anchor Terminal](https://www.anchorterminal.com/badges/autocua.svg)](https://www.anchorterminal.com/tools/autocua) ``` Plain link: ```html AutoCua on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say AutoCua is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/autocua-dark.png - Light: https://www.anchorterminal.com/assets/share/autocua-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp