{"id":"computer-use-browser-agent-evals","slug":"computer-use-browser-agent-evals","name":"Browser, WebArena & Desktop Computer-Use Agent Evaluation","shortName":"Computer-use & browser agent evals","problemStatement":"Benchmark web and desktop computer-use agents against realistic DOM/GUI tasks (WebArena, BrowserGym, OSWorld, VisualWebArena) with deterministic DOM/state checkpoints, session recordings, and step-budget limits.","whenNotTopPick":"Need full desktop OS (Ubuntu/X11) sandboxes for OSWorld GUI pixel/mouse/keyboard tasks — E2B Desktop; self-hosted OSS browser fleet to run thousands of free local WebArena episodes — Steel.dev; real iOS/Android handsets for mobile agent QA — BrowserStack; high-level managed browser-agent loop — Browser Use Cloud.","categoryIds":["cat-sandboxes-browsers","cat-observability"],"depotPickProviderId":"browserbase","depotPickRationale":"Browserbase provides deterministic headless Chromium sessions with Stagehand/Playwright control, full DOM/network/video session replay, and predictable concurrent session scaling ($20/mo Developer, $0.10–$0.12/browser-hr as of 2026-10-28) so WebArena and BrowserGym eval runs fail on agent mistakes rather than local browser flakes.","runnersUpIds":["e2b","steel-dev","browser-use","browserstack"],"weights":{"capabilityFit":0.26,"pricePerformance":0.16,"latencyReliability":0.18,"developerDx":0.16,"privacyPosture":0.1,"lockInRisk":0.06,"maturity":0.08},"methodologyNotes":"Scores session determinism, DOM/HAR trace capture for post-run grading, concurrency for parallel benchmark episodes, and clean teardown. Reference suites: WebArena (https://webarena.dev/), BrowserGym (https://github.com/ServiceNow/BrowserGym), and OSWorld (https://os-world.github.io/).","tags":["evals","browser","computer-use","webarena","osworld","browsergym","cua","benchmarking"],"scoreMargin":-0.24,"isNearTie":true,"pickConfidenceBand":"near_tie_co_pick","nearTie":{"isNearTie":true,"scoreMargin":-0.24,"threshold":0.35,"pickConfidenceBand":"near_tie_co_pick","coPickProviderId":"e2b","coPickProviderName":"E2B","coPickScore":8.63,"decidingFactor":"latencyReliability (8.8 vs 8.6)","methodologyWarning":"Top pick (8.39) and #2 runner-up (8.63) are separated by 0.24 points (<= 0.35 weight-sensitivity band). Treat them as co-picks and use the workload tie-breaker rule below rather than the raw composite decimal.","tieBreakerRule":"Need full desktop OS (Ubuntu/X11) sandboxes for OSWorld GUI pixel/mouse/keyboard tasks — E2B Desktop; self-hosted OSS browser fleet to run thousands of free local WebArena episodes — Steel.dev; real iOS/Android handsets for mobile agent QA — BrowserStack; high-level managed browser-agent loop — Browser Use Cloud."},"evidenceStatus":{"decisionRole":"independent_prior_and_candidate_generator","positioning":"The independent, agent-readable prior for choosing AI infrastructure — not a universal router, generic marketplace, or synthetic leaderboard.","freshnessThresholdDays":30,"freshness_policy":{"policy_version":"agentdepot.freshness_policy.v1","threshold_days":30},"freshness_state":"fresh","editorial_freshness_state":"fresh","unqualified_current_pick_allowed":true,"pick_qualification":"qualified_current_pick","promotionClass":"deterministic_source_reverified","evidenceClass":"editorial_prior","staleDowngraded":false,"effectiveConfidence":"high","confidenceHalfWidth":0.5,"pickScoreAgeDays":7,"editorialJudgmentAgeDays":9,"pricingAgeDays":7,"isPickScoreStale":false,"isPricingStale":false,"editorialJudgmentAsOf":"2026-10-19","pricingVerifiedAt":"2026-10-21","outcomeVerifiedAt":null,"effectiveVerifiedAsOf":"2026-10-21","downgradeReasons":[],"stalenessWarning":"Editorial judgment and deterministic pricing verification are both within the 30-day freshness threshold.","promotionGate":{"deterministicPricingCheck":true,"approvedScoreReaffirm":true,"pendingHumanReviewBlock":false,"zeroUnverifiedSkus":true,"costEfficiencyConsistent":true,"lockInAndReliabilityConsistent":true,"secondModelOrRuleAudit":true,"countersignReceiptIds":[],"otsAttestationHead":"b32634d5784cbfe663be0a16cce4f60a3ff1c3d4490437be00361cb4ae5d5d59","sourceCheckDate":"2026-10-27","activePricingRowsCount":9,"freeResourcesCount":0,"runnerUpPricingRowsCount":9},"claimProvenance":{"claim_id":"claim:computer-use-browser-agent-evals:browserbase:depot-pick","provider_id":"browserbase","jtbd_id":"computer-use-browser-agent-evals","primary_url":"https://www.browserbase.com/pricing","source_type":"primary_pricing","source_revision":"sha256:7bdb4e3bb1922460","observed_at":"2026-10-28","checked_at":"2026-10-28","claim_support_state":"claim_specific_supported","max_allowed_evidence_class":"replicated_outcome","defect_codes":[],"sources":[{"original_url":"https://www.browserbase.com","final_url":"https://www.browserbase.com","redirected":false,"http_status":200,"reachable":true,"source_type":"generic_homepage","is_claim_specific":false,"source_revision":"sha256:d9c43737d8cf5c2d","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://www.browserbase.com/pricing","final_url":"https://www.browserbase.com/pricing","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_pricing","is_claim_specific":true,"source_revision":"sha256:7bdb4e3bb1922460","observed_at":"2026-10-28","checked_at":"2026-10-28"}]},"verifiedOutcomeSummary":{"totalVerifiedReceipts":0,"byEvidenceTier":{"E0_ASSERTION":0,"E1_SOURCE_BOUND":0,"E2_DELIVERY":0,"E3_INDEPENDENT_OUTCOME":0,"E4_REPLICATED_OUTCOME":0},"bySubjectLayer":{"provider":0,"product":0,"model_version":0,"runtime_route":0}}},"pickScoreDetails":{"scoreRange":[7.89,8.89],"formattedScore":"8.4 ± 0.5 (7.9–8.9 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"freshState":"fresh","freshness_state":"fresh","effectiveConfidence":"high","confidenceInterval":{"low":7.89,"mid":8.39,"high":8.89,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"editorialJudgmentAsOf":"2026-10-28","sourceAgeDays":9,"pricingVerifiedAt":"2026-10-21","pricingAgeDays":7,"outcomeVerifiedAt":null,"effectiveVerifiedAsOf":"2026-10-21","dissentingEvidence":["Cost at high parallel sessions","Still need your own agent logic","Less self-host than Steel","When not to use top pick: Need full desktop OS (Ubuntu/X11) sandboxes for OSWorld GUI pixel/mouse/keyboard tasks — E2B Desktop; self-hosted OSS browser fleet to run thousands of free local WebArena episodes — Steel.dev; real iOS/Android handsets for mobile agent QA — BrowserStack; high-level managed browser-agent loop — Browser Use Cloud.","Runner-up E2B (e2b) is the primary alternative when constraints disqualify Browserbase."],"whatWouldChangePick":["Caller constraint matching: Need full desktop OS (Ubuntu/X11) sandboxes for OSWorld GUI pixel/mouse/keyboard tasks — E2B Desktop; self-hosted OSS browser fleet to run thousands of free local WebArena episodes — Steel.dev; real iOS/Android handsets for mobile agent QA — BrowserStack; high-level managed browser-agent loop — Browser Use Cloud.","Live quota or rate-limit exhaustion on browserbase (pass ?exhausted=browserbase or liveQuota.exhaustedProviders=[\"browserbase\"] to promote e2b).","Active subscription or enterprise commit on e2b combined with low switching-cost tolerance (existingSubscriptions + switchingCost.maxMigrationEffort=\"low\").","Sourced price increase >20% on https://www.browserbase.com or unverified SKU drift detected by npm run check:sources."],"claimProvenance":{"claim_id":"claim:computer-use-browser-agent-evals:browserbase:depot-pick","provider_id":"browserbase","jtbd_id":"computer-use-browser-agent-evals","primary_url":"https://www.browserbase.com/pricing","source_type":"primary_pricing","source_revision":"sha256:7bdb4e3bb1922460","observed_at":"2026-10-28","checked_at":"2026-10-28","claim_support_state":"claim_specific_supported","max_allowed_evidence_class":"replicated_outcome","defect_codes":[],"sources":[{"original_url":"https://www.browserbase.com","final_url":"https://www.browserbase.com","redirected":false,"http_status":200,"reachable":true,"source_type":"generic_homepage","is_claim_specific":false,"source_revision":"sha256:d9c43737d8cf5c2d","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://www.browserbase.com/pricing","final_url":"https://www.browserbase.com/pricing","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_pricing","is_claim_specific":true,"source_revision":"sha256:7bdb4e3bb1922460","observed_at":"2026-10-28","checked_at":"2026-10-28"}]},"calibratedScore":{"point":8.39,"band":[7.89,8.89],"interval":{"lower":7.89,"upper":8.89,"half_width":0.5},"score_kind":"source_bound_prior_band","evidence_class":"source_bound","confidence":"medium","confidence_ceiling":"medium","age_days":7,"dissent":["Cost at high parallel sessions","Still need your own agent logic","Less self-host than Steel","When not to use top pick: Need full desktop OS (Ubuntu/X11) sandboxes for OSWorld GUI pixel/mouse/keyboard tasks — E2B Desktop; self-hosted OSS browser fleet to run thousands of free local WebArena episodes — Steel.dev; real iOS/Android handsets for mobile agent QA — BrowserStack; high-level managed browser-agent loop — Browser Use Cloud.","Runner-up E2B (e2b) is the primary alternative when constraints disqualify Browserbase."],"what_would_change_this":["Caller constraint matching: Need full desktop OS (Ubuntu/X11) sandboxes for OSWorld GUI pixel/mouse/keyboard tasks — E2B Desktop; self-hosted OSS browser fleet to run thousands of free local WebArena episodes — Steel.dev; real iOS/Android handsets for mobile agent QA — BrowserStack; high-level managed browser-agent loop — Browser Use Cloud.","Live quota or rate-limit exhaustion on browserbase (pass ?exhausted=browserbase or liveQuota.exhaustedProviders=[\"browserbase\"] to promote e2b).","Active subscription or enterprise commit on e2b combined with low switching-cost tolerance (existingSubscriptions + switchingCost.maxMigrationEffort=\"low\").","Sourced price increase >20% on https://www.browserbase.com or unverified SKU drift detected by npm run check:sources."],"subject_layer":"provider"},"subject_ref":{"layer":"provider","provider_id":"browserbase","product_id":"browserbase-core","model_id":null,"version":null,"route_class":null,"inheritance_policy":"no_cross_layer_inheritance"}},"runtimeRoutes":[{"routeId":"computer-use-browser-agent-evals:browserbase:primary","roleForJob":"depot_pick","provider":{"id":"browserbase","slug":"browserbase","name":"Browserbase","website":"https://www.browserbase.com","status":"active"},"model":{"representativeModelId":"Developer browser hour overage","skuId":"browserbase-developer-browser-hour","unit":"usd_per_browser_hour","amountUsd":0.12,"sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"managed_cloud_service","endpointPattern":"https://www.browserbase.com (managed cloud service)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Browserbase Direct API","routeType":"first_party","tradeoff":"Direct vendor SDK/REST contract; pair with runner-up for multi-vendor failover."}]},"accountAndQuota":{"freeTierAvailable":false,"freeTierSummary":null,"rateLimitsSummary":"Free: Free Plan $0/mo … 3 concurrent browsers - 1 browser hour - 3 Agent runs included - 1,000 S","subscriptionFirstEligible":true,"documentedPlansCount":3},"regions":{"supportedRegions":["us","global"],"multiRegionFailover":true,"euResidencyAvailable":true},"toolSchemaSupport":{"strictJsonSchema":true,"parallelToolCalls":false,"mcpServerAvailable":true,"streamingSupported":true},"latencyTier":{"tier":"interactive_sub_1s","latencyReliabilityScore":8.8,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":7.5,"zeroDataRetentionAvailable":false,"trainsOnApiDataByDefault":false,"hipaaEligible":false,"selfHostable":false},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":9,"unverifiedSkus":0,"liveFailoverTargetId":"e2b"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:browserbase:Developer browser hour overage:managed_cloud_service:us","provider_id":"browserbase","product_id":"browserbase-core","model_id":"Developer browser hour overage","version":"2026-10-28","route_class":"managed_cloud_service","region":"us","score_status":"layer_evidenced","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"},"distinctRouteSubjects":[{"layer":"runtime_route","subject_id":"runtime_route:browserbase:Developer browser hour overage:direct_api:us","provider_id":"browserbase","product_id":"browserbase-core","model_id":"Developer browser hour overage","version":"2026-10-28","route_class":"direct_api","region":"us","score_status":"layer_evidenced","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"}]},{"routeId":"computer-use-browser-agent-evals:e2b:primary","roleForJob":"runner_up","provider":{"id":"e2b","slug":"e2b","name":"E2B","website":"https://e2b.dev","status":"active"},"model":{"representativeModelId":"Pro","skuId":"e2b-pro-usd-per-month","unit":"usd_per_month","amountUsd":150,"sourceUrl":"https://e2b.dev/pricing","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"self_hosted_or_oss_compatible","endpointPattern":"https://e2b.dev (self hosted or oss compatible)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"E2B Direct API","routeType":"first_party","tradeoff":"Direct vendor SDK/REST contract; pair with runner-up for multi-vendor failover."}]},"accountAndQuota":{"freeTierAvailable":true,"freeTierSummary":"E2B SDK (oss, asOf 2026-10-25)","rateLimitsSummary":"Hobby: Hobby FREE /$100 of usage in credits + Usage Costs … $100 one-time usage credit Sessions u","subscriptionFirstEligible":true,"documentedPlansCount":4},"regions":{"supportedRegions":["us","eu","global"],"multiRegionFailover":true,"euResidencyAvailable":true},"toolSchemaSupport":{"strictJsonSchema":true,"parallelToolCalls":false,"mcpServerAvailable":true,"streamingSupported":true},"latencyTier":{"tier":"standard_1s_to_5s","latencyReliabilityScore":8.6,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":8.5,"zeroDataRetentionAvailable":true,"trainsOnApiDataByDefault":false,"hipaaEligible":true,"selfHostable":true},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":13,"unverifiedSkus":0,"liveFailoverTargetId":"browserbase"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:e2b:Pro:self_hosted_or_oss_compatible:us","provider_id":"e2b","product_id":"e2b-core","model_id":"Pro","version":"2026-10-28","route_class":"self_hosted_or_oss_compatible","region":"us","score_status":"unknown","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"},"distinctRouteSubjects":[{"layer":"runtime_route","subject_id":"runtime_route:e2b:Pro:direct_api:us","provider_id":"e2b","product_id":"e2b-core","model_id":"Pro","version":"2026-10-28","route_class":"direct_api","region":"us","score_status":"layer_evidenced","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"}]},{"routeId":"computer-use-browser-agent-evals:steel-dev:primary","roleForJob":"runner_up","provider":{"id":"steel-dev","slug":"steel-dev","name":"Steel.dev","website":"https://steel.dev","status":"active"},"model":{"representativeModelId":"Launch browser hours","skuId":"steel-launch-browser-hour","unit":"usd_per_browser_hour","amountUsd":0.1,"sourceUrl":"https://docs.steel.dev/overview/pricinglimits","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"self_hosted_or_oss_compatible","endpointPattern":"https://steel.dev (self hosted or oss compatible)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Steel.dev Direct API","routeType":"first_party","tradeoff":"Direct vendor SDK/REST contract; pair with runner-up for multi-vendor failover."}]},"accountAndQuota":{"freeTierAvailable":false,"freeTierSummary":null,"rateLimitsSummary":"See /api/limits?provider=steel-dev","subscriptionFirstEligible":true,"documentedPlansCount":0},"regions":{"supportedRegions":["global"],"multiRegionFailover":true,"euResidencyAvailable":true},"toolSchemaSupport":{"strictJsonSchema":true,"parallelToolCalls":false,"mcpServerAvailable":true,"streamingSupported":true},"latencyTier":{"tier":"standard_1s_to_5s","latencyReliabilityScore":8,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":8.5,"zeroDataRetentionAvailable":true,"trainsOnApiDataByDefault":false,"hipaaEligible":true,"selfHostable":true},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":9,"unverifiedSkus":0,"liveFailoverTargetId":"browserbase"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:steel-dev:Launch browser hours:self_hosted_or_oss_compatible:global","provider_id":"steel-dev","product_id":"steel-dev-core","model_id":"Launch browser hours","version":"2026-10-28","route_class":"self_hosted_or_oss_compatible","region":"global","score_status":"unknown","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"},"distinctRouteSubjects":[{"layer":"runtime_route","subject_id":"runtime_route:steel-dev:Launch browser hours:direct_api:global","provider_id":"steel-dev","product_id":"steel-dev-core","model_id":"Launch browser hours","version":"2026-10-28","route_class":"direct_api","region":"global","score_status":"layer_evidenced","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"}]},{"routeId":"computer-use-browser-agent-evals:browser-use:primary","roleForJob":"runner_up","provider":{"id":"browser-use","slug":"browser-use","name":"Browser Use Cloud","website":"https://browser-use.com","status":"active"},"model":{"representativeModelId":"Browsers","skuId":"browser-use-browser-hour","unit":"usd_per_browser_hour","amountUsd":0.02,"sourceUrl":"https://docs.browser-use.com/cloud/pricing","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"self_hosted_or_oss_compatible","endpointPattern":"https://browser-use.com (self hosted or oss compatible)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Browser Use Cloud Direct API","routeType":"first_party","tradeoff":"Direct vendor SDK/REST contract; pair with runner-up for multi-vendor failover."}]},"accountAndQuota":{"freeTierAvailable":false,"freeTierSummary":null,"rateLimitsSummary":"See /api/limits?provider=browser-use","subscriptionFirstEligible":true,"documentedPlansCount":0},"regions":{"supportedRegions":["global","us"],"multiRegionFailover":true,"euResidencyAvailable":true},"toolSchemaSupport":{"strictJsonSchema":true,"parallelToolCalls":false,"mcpServerAvailable":false,"streamingSupported":true},"latencyTier":{"tier":"standard_1s_to_5s","latencyReliabilityScore":7,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":6.5,"zeroDataRetentionAvailable":false,"trainsOnApiDataByDefault":false,"hipaaEligible":false,"selfHostable":true},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":3,"unverifiedSkus":0,"liveFailoverTargetId":"browserbase"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:browser-use:Browsers:self_hosted_or_oss_compatible:global","provider_id":"browser-use","product_id":"browser-use-core","model_id":"Browsers","version":"2026-10-28","route_class":"self_hosted_or_oss_compatible","region":"global","score_status":"unknown","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"},"distinctRouteSubjects":[{"layer":"runtime_route","subject_id":"runtime_route:browser-use:Browsers:direct_api:global","provider_id":"browser-use","product_id":"browser-use-core","model_id":"Browsers","version":"2026-10-28","route_class":"direct_api","region":"global","score_status":"layer_evidenced","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"}]}],"depth":{"whenNotToUse":{"text":"Need full desktop OS (Ubuntu/X11) sandboxes for OSWorld GUI pixel/mouse/keyboard tasks — E2B Desktop; self-hosted OSS browser fleet to run thousands of free local WebArena episodes — Steel.dev; real iOS/Android handsets for mobile agent QA — BrowserStack; high-level managed browser-agent loop — Browser Use Cloud.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"e2b","name":"E2B","overallForJob":8.63,"pickOverallForJob":8.39,"beatsPickOn":["capabilityFit","pricePerformance","privacyPosture","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":5,"runnerUpLockInRisk":4,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[{"text":"Playwright/Puppeteer compatible","field":"strengths"},{"text":"Less self-host than Steel","field":"weaknesses"}],"selfHostFallback":[],"migration":"Runner-up E2B has lower stored lock-in risk (4 vs 5, 0–10, higher = more lock-in).","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"freshness":{"pick":{"score":{"asOf":"2026-10-28","ageDays":1,"stale":false,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-10-28","ageDays":1,"stale":false,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-28","sourceUrls":2,"sourcesReachable":2,"pricingRows":9,"pricingRowsReconfirmed":6,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}}},"whenNotTopPickRules":[{"ifConstraint":"escape_hatch_clause_1","recommendedProviderId":"e2b","activeModelOrSku":"e2b-sandbox-1vcpu-per-s","reason":"Need full desktop OS (Ubuntu/X11) sandboxes for OSWorld GUI pixel/mouse/keyboard tasks — E2B Desktop"},{"ifConstraint":"budget:cost_floor_priority","recommendedProviderId":"steel-dev","activeModelOrSku":"steel-session-hour","reason":"self-hosted OSS browser fleet to run thousands of free local WebArena episodes — Steel.dev"},{"ifConstraint":"escape_hatch_clause_3","recommendedProviderId":"browserstack","activeModelOrSku":"browserstack-automate","reason":"real iOS/Android handsets for mobile agent QA — BrowserStack"},{"ifConstraint":"escape_hatch_clause_4","recommendedProviderId":"browser-use","activeModelOrSku":"browser-use-cloud-step","reason":"high-level managed browser-agent loop — Browser Use Cloud."}],"bootstrap":{"authType":"api_key","envVars":["BROWSERBASE_API_KEY","BROWSERBASE_PROJECT_ID"],"signupUrl":"https://www.browserbase.com/sign-up","apiKeyUrl":"https://www.browserbase.com/settings","docsUrl":"https://docs.browserbase.com/introduction/what-is-browserbase","mcpServer":"npx -y @browserbasehq/mcp-server-browserbase","cliInit":null,"sdkInstall":{"npm":"npm install @browserbasehq/sdk","pip":"pip install browserbase"},"installCommand":"npm install @browserbasehq/sdk","activeModelOrSku":"browserbase-developer-plan","canonicalSnippet":"import Browserbase from \"@browserbasehq/sdk\";\nconst bb = new Browserbase({ apiKey: process.env.BROWSERBASE_API_KEY! });","verifyCommand":"curl -sS https://api.browserbase.com/v1/sessions -H \"X-BB-API-Key: $BROWSERBASE_API_KEY\""},"quickstartSpec":{"installCommand":"npm install @browserbasehq/sdk","envVars":["BROWSERBASE_API_KEY","BROWSERBASE_PROJECT_ID"],"activeModelOrSku":"browserbase-developer-plan","canonicalSnippet":"import Browserbase from \"@browserbasehq/sdk\";\nconst bb = new Browserbase({ apiKey: process.env.BROWSERBASE_API_KEY! });","sdkInstall":{"npm":"npm install @browserbasehq/sdk","pip":"pip install browserbase"},"verifyCommand":"curl -sS https://api.browserbase.com/v1/sessions -H \"X-BB-API-Key: $BROWSERBASE_API_KEY\"","apiKeyUrl":"https://www.browserbase.com/settings","docsUrl":"https://docs.browserbase.com/introduction/what-is-browserbase","mcpServer":"npx -y @browserbasehq/mcp-server-browserbase","bootstrapReason":null},"operationalGotchas":[{"code":"hidden_spend_tier_gates","severity":"warning","summary":"Cost at high parallel sessions","sourceDate":"2026-10-28"},{"code":"hidden_spend_tier_gates","severity":"warning","summary":"Still need your own agent logic","sourceDate":"2026-10-28"}],"relatedPacks":[],"depotPick":{"id":"browserbase","slug":"browserbase","name":"Browserbase","tagline":"Depot default for agents that need a real browser. Pair with Stagehand/Browser Use for the reasoning loop.","overall":8.39},"runnersUp":[{"id":"e2b","slug":"e2b","name":"E2B","tagline":"Depot default code sandbox for agents. Use for untrusted code; Daytona when you need persistent…","overall":8.63},{"id":"steel-dev","slug":"steel-dev","name":"Steel.dev","tagline":"Pick Steel when you need to self-host browsers or hate SaaS lock-in. Browserbase wins on polish.","overall":8.29},{"id":"browser-use","slug":"browser-use","name":"Browser Use Cloud","tagline":"Pick when you want an agent-native browser loop, not just a hosted Chromium. Browserbase still wins pure…","overall":7.44},{"id":"browserstack","slug":"browserstack","name":"BrowserStack","tagline":"Depot pick for mobile-computer-use on real phones. Cua if you only need Android VMs; AWS Device Farm if you…","overall":8.03}]}