canonical: https://jentic.com/apis/browser-use.com/browser-use # Browser Use Public API v4 The Browser Use API provisions cloud browser sessions and runs automated browser tasks on them for AI agents, then returns each run's status, output, and attachments. You start a run that drives a browser toward a goal, open and manage the underlying browser sessions, and reuse saved profiles, workspaces, and uploaded files across runs. Integrations connect third-party providers to a run, and extensions add custom browser capabilities to a session. ## For AI agents Start cloud browser sessions and automated browser runs, track their status and output, and reuse profiles, workspaces, and files. Authenticates with an API key in a request header. ## Scope Does not handle large-scale web crawling, proxy pool management, or structured data parsing. Use for running cloud browser sessions and automated browser tasks only. ## Capabilities - Start an automated browser run and track its status and output - Open and manage cloud browser sessions - List a browser's downloads and reuse saved browser profiles - Store files and workspaces that runs can read from - Connect third-party integration providers for a run - Install browser extensions into a session ## Use cases ### Agent-Driven Browser Automation An AI agent connected through Jentic starts a browser run toward a goal, polls its status, and reads back the output and any attachments, so the agent can complete web tasks that need a real browser without a person operating one. Saved profiles let the run reuse a logged-in state across invocations. Example prompt: Start a run that opens the target site, fills the form, and return the run's final output and status ### Reusable Browser Sessions and Profiles A workflow opens a cloud browser session and attaches a saved profile so repeated runs start from a signed-in state, then manages the session lifecycle and inspects its downloads. This keeps multi-step automations stable across runs without re-authenticating each time. Example prompt: Open a browser session with the saved profile, run the task, and list the files it downloaded ### Files and Workspaces for Runs A pipeline uploads files into a workspace and points runs at them, then collects each run's output attachments, so inputs and outputs live alongside the automation rather than in a separate store. Workspaces group related runs and their files together. Example prompt: Upload the input CSV to a workspace, start a run that uses it, and return the run's output attachments ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/runs` | Start a browser automation run | | GET | `/runs` | List browser runs | | GET | `/runs/{run_id}` | Get a run's details | | POST | `/browsers` | Open a cloud browser | | GET | `/sessions` | List browser sessions | | POST | `/profiles` | Create a reusable browser profile | | POST | `/workspaces` | Create a workspace for runs | ## Key resources - **Runs** — Start automated browser tasks and read their status, output, and attachments - **Sessions** — Create and manage the cloud browser sessions runs execute on - **Browsers** — Open browsers and inspect their downloads - **Profiles** — Save and reuse browser profiles for logged-in runs - **Workspaces** — Group runs and upload the files they read from ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 63 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 74 / 100 - Developer Experience & Jentic Compatibility: 63 / 100 - AI-Readiness & Agent Experience: 51 / 100 - Agent Usability: 94 / 100 - Security: 50 / 100 - AI Discoverability: 64 / 100 - **View full report:** https://jentic.com/apis/browser-use.com/browser-use/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the Browser Use API by hand means handling its API key header, managing the run, session, and browser lifecycle, and polling each run until it finishes. Through Jentic you install once, import Browser Use from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** You choose which operations your agent may call, so you can allow starting runs and reading their status while leaving destructive operations like session or profile deletion out. The run's target site travels in the request body, so rules bound which operations run rather than which page is visited. - **Credential handling:** Your Browser Use API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'run a browser task' or 'open a browser session', and Jentic returns the matching Browser Use operation with its input schema so the agent calls the right endpoint without reading the reference docs. ## Related APIs - **Browserbase API** — Managed headless browser sessions for automation and scraping - **Apify API** — Platform for running web automation and scraping actors in the cloud - **E2B API** — Cloud sandboxes for running agent-generated code ## FAQ ### Is there a Browser Use MCP server? You don't need an MCP server to give your agent the Browser Use API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent can start browser runs and read their output straight away, with no extra server to run and no tool definitions loaded into the agent's context. ### Can I limit what my agent is allowed to do with the Browser Use API? Yes. You choose which operations your agent may call, so you can allow starting runs and reading their status while leaving session deletion and profile removal out, and every call it makes is logged. The run's target travels in the request body, so your rules bound which operations run rather than which site is visited. ### What authentication does the Browser Use API use? The Browser Use API authenticates with an API key sent in the X-Browser-Use-Api-Key request header per its OpenAPI spec. Through Jentic the key is stored encrypted by your own instance and added to each request at call time, so it never appears in the agent's prompt or logs. ### Can I reuse a logged-in browser state across runs with the Browser Use API? Yes. You save a browser profile and attach it to a session, so repeated runs start from the same signed-in state instead of authenticating each time. The session operations let an agent open, inspect, and close those browsers as it works. ### What are the rate limits for the Browser Use API? The OpenAPI spec does not specify rate limits for the Browser Use API. For current limits and concurrency guidance, see the Browser Use documentation at https://docs.browser-use.com. ### How do I run a browser task with the Browser Use API through Jentic? Import the Browser Use API from the Jentic API Directory, then have your agent issue a request such as 'run a browser task on this site'. Jentic matches the intent to the start-run operation and returns its input schema so the agent builds a valid request, with your stored API key injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.