Harness Hub
All startups

Browserbase

Headless browser infrastructure built for AI agents.

Browserbase runs fleets of headless browsers as an API — sessions, proxies, stealth, debugging — so agents can act on the web without operators managing browser infrastructure. Also builds the Stagehand SDK.

Pros & cons

Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.

Pros

  • DocsProvides managed headless browsers; the $20/month Developer plan includes 25 concurrent browsers and 100 browser hours.[1]
  • MetadataIts Stagehand SDK is MIT-licensed (about 26k stars), with TypeScript, Python and Go SDKs.[1]
  • DocsPaid plans include automatic captcha solving, proxies and session recordings.[1][2]

Cons

  • DocsThe free tier is 1 browser hour with 15-minute sessions and no captcha solving or stealth.[1]
  • DocsCosts add up across browser hours, proxy traffic ($10-12/GB), Fetch/Search calls and model tokens.[1][2]
  • DocsAdvanced stealth is only on the custom-priced Scale plan, and competitor Skyvern reports that Cloudflare Enterprise and Akamai can still block sessions.[1][2]
  • Independent testStagehand's LLM-driven actions add token cost and make runs non-deterministic.[1]
Best for
Teams running browser agents at scale that do not want to operate their own browser fleet.
Watch out for
Add up total cost across every billing dimension before you scale.

Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction

People

Open roles (16)

All 16 roles

Their open-source work

browserbase/stagehand

An AI browsing SDK built on Playwright — act, extract, observe.

Maintained by Browserbase

@browserbasehq/stagehan…released

Activity

Last push
· today
Latest release
@browserbasehq/stagehand@3.7.4
· 3d ago
Last 90 days
4 releases
  1. @browserbasehq/stagehand@3.7.4

    · 3d ago

    Patch Changes #3150 69c2440 Thanks @miguelg719! - Fix OpenAI strict-schema rejection of the nullable act action while still stripping unknown keys when parsing. #3114 f6b3d85 Thanks @miguelg719! - Fix CAPTCHA awareness options for local Browserbase attachments and forward them…

  2. stagehand-server-v3/v3.7.7stagehand/server-v3 v3.7.7

    · 4w ago

    What's Changed fix(v3): set additionalProperties false on nullable act action schema by @miguelg719 in https://github.com/browserbase/stagehand/pull/3150 fix(v3): honor CAPTCHA awareness options for local attachments by @miguelg719 in…

  3. @browserbasehq/stagehand@3.7.3

    · 2mo ago

    Patch Changes #2842 f86e609 Thanks @seanmcguire12! - update the MCP SDK to v1.30 and refresh supporting dependency versions #2836 94a0ee4 Thanks @seanmcguire12! - fix cross-frame xpaths building logic for coordinates inside of iframes.

  4. stagehand-server-v3/v3.7.6stagehand/server-v3 v3.7.6

    · 2mo ago

    What's Changed Version Packages by @github-actions[bot] in https://github.com/browserbase/stagehand/pull/2778 [V3]: rm docs pkg by @seanmcguire12 in https://github.com/browserbase/stagehand/pull/2830 [V3]: fix xpath building logic for coordinates inside of iframes by…

  5. stagehand-server-v3/v3.7.5stagehand/server-v3 v3.7.5

    · 3mo ago

    What's Changed Contrib/2384 by @miguelg719 in https://github.com/browserbase/stagehand/pull/2385 chore(release): retarget release automation from main to v3 by @miguelg719 in https://github.com/browserbase/stagehand/pull/2660 fix(v3): normalize CUA coordinates to actual…

Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.

On X

Posts by the company and its team, shown as plain text; “Load on X” loads X's script for that post, which may set cookies.

  • Running browsers at scale does not mean just booting Chromium up in a sandbox. You have to go directly to the browser itself and customize it to work great for your agents.

    We're able to patch, build, and deploy Chromium across our cluster faster than Google rolls out Chrome… https://t.co/fbInuEbhpc

    Open on X

Follow @browserbase on X · The X feed

E2B

Open-source sandboxes for running AI-generated code.

E2B gives agents secure, isolated cloud micro-VMs to execute code and commands — the execution runtime layer of the harness, used by many coding and data-analysis agents.

4 pros · 3 cons

Elastic sandboxes for running AI-generated code.

Daytona provides secure, OCI-compatible sandbox 'computers' that spin up in under 90ms — with snapshots for persistent agent state. In 2026 it moved core development to a private codebase while continuing to run as a commercial platform.

3 pros · 4 cons

The integration layer: hundreds of managed tools your agents can call.

Composio handles auth, schemas, observability and reliability for the external SaaS tools an agent uses — 'plumbing for agentic actions' across Slack, GitHub, Salesforce and 250+ other surfaces.

4 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

Maintains · 2

Similar entries · 1

Mentioned in · 2

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.