Kit · 2026-10-03
Browser agent
browser
Completes a task by reading and operating a website in a browser, then stops before a consequential submit unless confirmation exists.
Needs below are the JTBD ids already listed on this class, capped at 6. The pick is the current Depot Pick. The cheapest line is that job's matching sourced SKU, or unavailable. A free row is listed only when its jtbd ids include that job. This page does not rescore. Agents that cannot spend use ?cost=free and must not treat the paid pick as free.
GET /api/kit?class=browser · ?cost=free · all kits · class JSON
Depot Pick: browserbase · score as of 2026-10-19 · /api/jtbds/cloud-browser
Depot Pick for cloud-browser: browserbase (asOf 2026-10-19). See GET /api/jtbds/cloud-browser + GET /api/methodology.
pickIsNotPriceWinner: true
Cheapest matching SKU: browser-use · Browsers · 0.02 usd_per_browser_hour · not a per-million-token rate. min sourced browser-hour among candidates; lowest browser-hour tier per provider; not quality-adjusted; proxy per GB, CAPTCHA solves, monthly plans, and chat tokens were not included
Pick is not a price winner. browserbase matching USD per browser-hour is 0.1; cheapest among candidates is browser-use at 0.02.
Free resources
freeMatch: jtbd
- Playwright · playwright · dev_tool · oss
Depot Pick: anchor-browser · score as of 2026-09-14 · /api/jtbds/computer-use-browser
Depot Pick for computer-use-browser: anchor-browser (asOf 2026-09-14). See GET /api/jtbds/computer-use-browser + GET /api/methodology.
pickIsNotPriceWinner: true
Cheapest matching SKU: browser-use · Browsers · 0.02 usd_per_browser_hour · not a per-million-token rate. min sourced browser-hour among candidates; lowest browser-hour tier per provider; not quality-adjusted; proxy per GB, CAPTCHA solves, monthly plans, and chat tokens were not included
Pick is not a price winner. anchor-browser matching USD per browser-hour is 0.09; cheapest among candidates is browser-use at 0.02.
Free resources
freeMatch: jtbd
- browser-use · browser-use · dev_tool · oss
- Camoufox · camoufox · free_browser · oss
- Playwright · playwright · dev_tool · oss
Depot Pick: browser-use · score as of 2026-09-14 · /api/jtbds/browser-agent-loop
Depot Pick for browser-agent-loop: browser-use (asOf 2026-09-14). See GET /api/jtbds/browser-agent-loop + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: browser-use · Browsers · 0.02 usd_per_browser_hour · not a per-million-token rate. min sourced browser-hour among candidates; lowest browser-hour tier per provider; not quality-adjusted; proxy per GB, CAPTCHA solves, monthly plans, and chat tokens were not included
Pick is the cheapest matching USD per browser-hour among candidates (0.02).
Free resources
freeMatch: jtbd
- browser-use · browser-use · dev_tool · oss
- WebArena · webarena · free_data · oss
Depot Pick: browserbase · score as of 2026-10-19 · /api/jtbds/web-agent
Depot Pick for web-agent: browserbase (asOf 2026-10-19). See GET /api/jtbds/web-agent + GET /api/methodology.
pickIsNotPriceWinner: true
Cheapest matching SKU: browser-use · Browsers · 0.02 usd_per_browser_hour · not a per-million-token rate. min sourced browser-hour among candidates; lowest browser-hour tier per provider; not quality-adjusted; proxy per GB, CAPTCHA solves, monthly plans, and chat tokens were not included
Pick is not a price winner. browserbase matching USD per browser-hour is 0.1; cheapest among candidates is browser-use at 0.02.
Free resources
freeMatch: jtbd
- browser-use · browser-use · dev_tool · oss
- BrowserGym · browsergym · free_data · oss
- Crawl4AI · crawl4ai · free_browser · oss
Depot Pick: steel-dev · score as of 2026-09-14 · /api/jtbds/self-host-browser
Depot Pick for self-host-browser: steel-dev (asOf 2026-09-14). See GET /api/jtbds/self-host-browser + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: steel-dev · Scale browser hours · 0.08 usd_per_browser_hour · not a per-million-token rate. min sourced browser-hour among candidates; lowest browser-hour tier per provider; not quality-adjusted; proxy per GB, CAPTCHA solves, monthly plans, and chat tokens were not included
Only 1 candidate has a matching USD per browser-hour; nothing was compared, so pickIsPriceWinner is null.
Depot Pick: firecrawl · score as of 2026-10-19 · /api/jtbds/web-scrape
Depot Pick for web-scrape: firecrawl (asOf 2026-10-19). See GET /api/jtbds/web-scrape + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: unavailable — Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Free resources
freeMatch: jtbd
- Crawl4AI · crawl4ai · free_browser · oss
Failure modes
Prompt injection prompt-injection
Compare each tool call to the original user task. If the call only makes sense given text that arrived from a fetched page, file, or message, stop and ask. Record which source the instruction came from. This catalog does not store payloads or attack steps.
Tool loop tool-loop
Hash the last several tool names and arguments. Stop when the same call repeats and the observation did not change. Cap tool calls per task.
GUI grounding miss gui-grounding-miss
After each GUI action, compare the resulting screen or accessibility tree to the control the plan named. Stop when they differ.
Partial tool success partial-tool-success
Require a per-item status and a failure count. Success for the task requires the failed count to be zero or explicitly handed to a retry queue.
Non-determinism non-determinism
Run the task more than once and compare the end state, not a single transcript. Record the trial count next to any success rate you cite.
Confirmation skip confirmation-skip
Gate those tool names on an approval id recorded before the call. A missing approval is a failure even if the downstream tool returns success.
Hallucinated tool arguments hallucinated-tool-args
Reject a call that fails the current schema or names an unknown id, and do that before the tool runs a side effect.
Collateral side effects collateral-side-effects
Snapshot the workspace or app state, then diff it against an allowlist. A passing check plus an unexpected diff is a failure.
Over-refusal over-refusal
Log refusals separately from successes. Review a sample against the written policy. Do not treat a refusal as a pass, and do not weaken a safety check to raise the pass rate.
Instruction drift instruction-drift
Restate the stop condition in the trace. End the run when it is met. Review long traces for steps that do not serve the original task.
Benchmark protocol mismatch benchmark-protocol-mismatch
Store assisted-or-not, subset, and harness version beside every cited score. Refuse a ranking that mixes those fields.