{"id":"coding-agent-evals","slug":"coding-agent-evals","name":"Coding Agent, Repo Patch & Terminal Benchmark Harnesses (SWE-bench / Terminal-Bench)","shortName":"Coding & terminal agent evals","problemStatement":"Evaluate coding and CLI agents on real git repositories, multi-file patches, test suites, and shell tasks (SWE-bench Verified, Terminal-Bench) inside disposable sandboxes where untrusted generated code cannot touch the host.","whenNotTopPick":"Need persistent multi-container dev workspaces with sticky git worktrees across long horizons — Daytona; need bursty 500+ container parallelization or GPU-backed ML tasks (MLE-bench) — Modal; need the experiment/dataset scoreboard layer on top of sandbox runs — Braintrust; need a full PaaS with build pipelines — Northflank.","categoryIds":["cat-sandboxes-browsers","cat-observability"],"depotPickProviderId":"e2b","depotPickRationale":"E2B boots isolated Firecracker microVMs in ~150ms with per-second vCPU/GiB pricing ($0.000014/vCPU-s, $0.0000045/GiB-s as of 2026-10-28, up to 1,100 concurrent sandboxes on Pro++), making it the cleanest substrate for running SWE-bench Verified repo checkouts and Terminal-Bench test harnesses at scale.","runnersUpIds":["daytona","modal","braintrust","northflank"],"weights":{"capabilityFit":0.28,"pricePerformance":0.16,"latencyReliability":0.18,"developerDx":0.16,"privacyPosture":0.1,"lockInRisk":0.06,"maturity":0.06},"methodologyNotes":"Coding agent benchmarks are execution-bound: the grader is `git apply` + the repo's unit test suite inside a clean container. Never grade coding agents with LLM-as-judge alone when a deterministic test suite exists. Official benchmarks: SWE-bench Verified (https://www.swebench.com/) and Terminal-Bench (https://tbench.ai/).","tags":["evals","coding-agent","swe-bench","terminal-bench","sandbox","benchmarking"],"scoreMargin":0.34,"isNearTie":true,"pickConfidenceBand":"near_tie_co_pick","nearTie":{"isNearTie":true,"scoreMargin":0.34,"threshold":0.35,"pickConfidenceBand":"near_tie_co_pick","coPickProviderId":"daytona","coPickProviderName":"Daytona","coPickScore":8.31,"decidingFactor":"capabilityFit (9.4 vs 8.8)","methodologyWarning":"Top pick (8.65) and #2 runner-up (8.31) are separated by 0.34 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 persistent multi-container dev workspaces with sticky git worktrees across long horizons — Daytona; need bursty 500+ container parallelization or GPU-backed ML tasks (MLE-bench) — Modal; need the experiment/dataset scoreboard layer on top of sandbox runs — Braintrust; need a full PaaS with build pipelines — Northflank."},"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":"verified_outcome_backed","evidenceClass":"editorial_plus_verified_receipt","staleDowngraded":false,"effectiveConfidence":"high_verified","confidenceHalfWidth":0.35,"pickScoreAgeDays":0,"editorialJudgmentAgeDays":0,"pricingAgeDays":0,"isPickScoreStale":false,"isPricingStale":false,"editorialJudgmentAsOf":"2026-10-28","pricingVerifiedAt":"2026-10-28","outcomeVerifiedAt":"2026-10-28","effectiveVerifiedAsOf":"2026-10-28","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":["cs-64391106","cs-2e116f7d"],"otsAttestationHead":"b32634d5784cbfe663be0a16cce4f60a3ff1c3d4490437be00361cb4ae5d5d59","sourceCheckDate":"2026-10-28","activePricingRowsCount":13,"freeResourcesCount":1,"runnerUpPricingRowsCount":18},"claimProvenance":{"claim_id":"claim:coding-agent-evals:e2b:depot-pick","provider_id":"e2b","jtbd_id":"coding-agent-evals","primary_url":"https://www.e2b.dev/docs/use-cases/computer-use","source_type":"primary_docs","source_revision":"sha256:bc135daecff33794","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://e2b.dev","final_url":"https://e2b.dev","redirected":false,"http_status":200,"reachable":true,"source_type":"generic_homepage","is_claim_specific":false,"source_revision":"sha256:e308a43df7818e16","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://www.e2b.dev/docs/use-cases/computer-use","final_url":"https://www.e2b.dev/docs/use-cases/computer-use","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_docs","is_claim_specific":true,"source_revision":"sha256:bc135daecff33794","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":[8.3,9],"formattedScore":"8.7 ± 0.35 (8.3–9.0 · editorial_plus_verified_receipt)","evidenceClass":"editorial_plus_verified_receipt","promotionClass":"verified_outcome_backed","staleDowngraded":false,"freshState":"fresh","freshness_state":"fresh","effectiveConfidence":"high_verified","confidenceInterval":{"low":8.3,"mid":8.65,"high":9,"halfWidth":0.35,"confidenceLevel":0.8,"basis":"narrowed_verified_outcome_interval_0.35_backed_by_countersign_receipts"},"editorialJudgmentAsOf":"2026-10-28","sourceAgeDays":0,"pricingVerifiedAt":"2026-10-28","pricingAgeDays":0,"outcomeVerifiedAt":"2026-10-28","effectiveVerifiedAsOf":"2026-10-28","dissentingEvidence":["Per-sandbox-second costs add up","Less persistent than Daytona workspaces","Younger than hyperscalers","When not to use top pick: Need persistent multi-container dev workspaces with sticky git worktrees across long horizons — Daytona; need bursty 500+ container parallelization or GPU-backed ML tasks (MLE-bench) — Modal; need the experiment/dataset scoreboard layer on top of sandbox runs — Braintrust; need a full PaaS with build pipelines — Northflank.","Runner-up Daytona (daytona) is the primary alternative when constraints disqualify E2B."],"whatWouldChangePick":["Caller constraint matching: Need persistent multi-container dev workspaces with sticky git worktrees across long horizons — Daytona; need bursty 500+ container parallelization or GPU-backed ML tasks (MLE-bench) — Modal; need the experiment/dataset scoreboard layer on top of sandbox runs — Braintrust; need a full PaaS with build pipelines — Northflank.","Live quota or rate-limit exhaustion on e2b (pass ?exhausted=e2b or liveQuota.exhaustedProviders=[\"e2b\"] to promote daytona).","Active subscription or enterprise commit on daytona combined with low switching-cost tolerance (existingSubscriptions + switchingCost.maxMigrationEffort=\"low\").","Sourced price increase >20% on https://e2b.dev or unverified SKU drift detected by npm run check:sources."],"claimProvenance":{"claim_id":"claim:coding-agent-evals:e2b:depot-pick","provider_id":"e2b","jtbd_id":"coding-agent-evals","primary_url":"https://www.e2b.dev/docs/use-cases/computer-use","source_type":"primary_docs","source_revision":"sha256:bc135daecff33794","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://e2b.dev","final_url":"https://e2b.dev","redirected":false,"http_status":200,"reachable":true,"source_type":"generic_homepage","is_claim_specific":false,"source_revision":"sha256:e308a43df7818e16","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://www.e2b.dev/docs/use-cases/computer-use","final_url":"https://www.e2b.dev/docs/use-cases/computer-use","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_docs","is_claim_specific":true,"source_revision":"sha256:bc135daecff33794","observed_at":"2026-10-28","checked_at":"2026-10-28"}]},"calibratedScore":{"point":8.65,"band":[8.3,9],"interval":{"lower":8.3,"upper":9,"half_width":0.35},"score_kind":"experimental_calibrated_band","evidence_class":"experimental","confidence":"low","confidence_ceiling":"high","age_days":0,"dissent":["Per-sandbox-second costs add up","Less persistent than Daytona workspaces","Younger than hyperscalers","When not to use top pick: Need persistent multi-container dev workspaces with sticky git worktrees across long horizons — Daytona; need bursty 500+ container parallelization or GPU-backed ML tasks (MLE-bench) — Modal; need the experiment/dataset scoreboard layer on top of sandbox runs — Braintrust; need a full PaaS with build pipelines — Northflank.","Runner-up Daytona (daytona) is the primary alternative when constraints disqualify E2B."],"what_would_change_this":["Caller constraint matching: Need persistent multi-container dev workspaces with sticky git worktrees across long horizons — Daytona; need bursty 500+ container parallelization or GPU-backed ML tasks (MLE-bench) — Modal; need the experiment/dataset scoreboard layer on top of sandbox runs — Braintrust; need a full PaaS with build pipelines — Northflank.","Live quota or rate-limit exhaustion on e2b (pass ?exhausted=e2b or liveQuota.exhaustedProviders=[\"e2b\"] to promote daytona).","Active subscription or enterprise commit on daytona combined with low switching-cost tolerance (existingSubscriptions + switchingCost.maxMigrationEffort=\"low\").","Sourced price increase >20% on https://e2b.dev or unverified SKU drift detected by npm run check:sources."],"subject_layer":"provider"},"subject_ref":{"layer":"provider","provider_id":"e2b","product_id":"e2b-core","model_id":null,"version":null,"route_class":null,"inheritance_policy":"no_cross_layer_inheritance"}},"runtimeRoutes":[{"routeId":"coding-agent-evals:e2b:primary","roleForJob":"depot_pick","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":"daytona"},"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":"coding-agent-evals:daytona:primary","roleForJob":"runner_up","provider":{"id":"daytona","slug":"daytona","name":"Daytona","website":"https://daytona.io","status":"active"},"model":{"representativeModelId":"vCPU","skuId":"daytona-vcpu","unit":"usd_per_vcpu_hour","amountUsd":0.0504,"sourceUrl":"https://www.daytona.io/pricing","asOf":"2026-10-27"},"servingRoute":{"primaryRouteType":"self_hosted_or_oss_compatible","endpointPattern":"https://daytona.io (self hosted or oss compatible)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Daytona 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=daytona","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":8.2,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":8,"zeroDataRetentionAvailable":true,"trainsOnApiDataByDefault":false,"hipaaEligible":false,"selfHostable":true},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":20,"unverifiedSkus":0,"liveFailoverTargetId":"e2b"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:daytona:vCPU:self_hosted_or_oss_compatible:global","provider_id":"daytona","product_id":"daytona-core","model_id":"vCPU","version":"2026-10-27","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:daytona:vCPU:direct_api:global","provider_id":"daytona","product_id":"daytona-core","model_id":"vCPU","version":"2026-10-27","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":"coding-agent-evals:modal:primary","roleForJob":"runner_up","provider":{"id":"modal","slug":"modal","name":"Modal","website":"https://modal.com","status":"active"},"model":{"representativeModelId":"Nvidia B300","skuId":"modal-nvidia-b300-usd-per-gpu-second","unit":"usd_per_gpu_second","amountUsd":0.001972,"sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27"},"servingRoute":{"primaryRouteType":"managed_cloud_service","endpointPattern":"https://modal.com (managed cloud service)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Modal 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=modal","subscriptionFirstEligible":true,"documentedPlansCount":0},"regions":{"supportedRegions":["us","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":7.8,"zeroDataRetentionAvailable":false,"trainsOnApiDataByDefault":false,"hipaaEligible":false,"selfHostable":false},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":18,"unverifiedSkus":0,"liveFailoverTargetId":"e2b"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:modal:Nvidia B300:managed_cloud_service:us","provider_id":"modal","product_id":"modal-core","model_id":"Nvidia B300","version":"2026-10-27","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:modal:Nvidia B300:direct_api:us","provider_id":"modal","product_id":"modal-core","model_id":"Nvidia B300","version":"2026-10-27","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":"coding-agent-evals:braintrust:primary","roleForJob":"runner_up","provider":{"id":"braintrust","slug":"braintrust","name":"Braintrust","website":"https://www.braintrust.dev","status":"active"},"model":{"representativeModelId":"Braintrust Primary Runtime","skuId":null,"unit":null,"amountUsd":null,"sourceUrl":"https://www.braintrust.dev","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"managed_cloud_service","endpointPattern":"https://www.braintrust.dev (managed cloud service)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Braintrust 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":"Starter: Starter For everyone $0 / month - $10 credits + tok rates - 1 GB processed data + $4/GB - ","subscriptionFirstEligible":true,"documentedPlansCount":2},"regions":{"supportedRegions":["us","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,"zeroDataRetentionAvailable":true,"trainsOnApiDataByDefault":false,"hipaaEligible":false,"selfHostable":false},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":0,"unverifiedSkus":0,"liveFailoverTargetId":"e2b"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:braintrust:braintrust-primary:managed_cloud_service:us","provider_id":"braintrust","product_id":"braintrust-core","model_id":"braintrust-primary","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:braintrust:braintrust-primary:direct_api:us","provider_id":"braintrust","product_id":"braintrust-core","model_id":"braintrust-primary","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"}]}],"depth":{"whenNotToUse":{"text":"Need persistent multi-container dev workspaces with sticky git worktrees across long horizons — Daytona; need bursty 500+ container parallelization or GPU-backed ML tasks (MLE-bench) — Modal; need the experiment/dataset scoreboard layer on top of sandbox runs — Braintrust; need a full PaaS with build pipelines — Northflank.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"daytona","name":"Daytona","overallForJob":8.31,"pickOverallForJob":8.65,"beatsPickOn":["pricePerformance","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":4,"runnerUpLockInRisk":3,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":["open source (provider tag `oss`)"],"pickNotes":[],"selfHostFallback":[],"migration":"Runner-up Daytona has lower stored lock-in risk (3 vs 4, 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":13,"pricingRowsReconfirmed":13,"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":"exit:self_host_or_open_weights","recommendedProviderId":"daytona","activeModelOrSku":"daytona-sandbox-vcpu-second","reason":"Need persistent multi-container dev workspaces with sticky git worktrees across long horizons — Daytona"},{"ifConstraint":"escape_hatch_clause_2","recommendedProviderId":"modal","activeModelOrSku":"modal-h100-gpu-second","reason":"need bursty 500+ container parallelization or GPU-backed ML tasks (MLE-bench) — Modal"},{"ifConstraint":"escape_hatch_clause_3","recommendedProviderId":"braintrust","activeModelOrSku":"braintrust-pro","reason":"need the experiment/dataset scoreboard layer on top of sandbox runs — Braintrust"},{"ifConstraint":"escape_hatch_clause_4","recommendedProviderId":"northflank","activeModelOrSku":"northflank-vcpu-hour","reason":"need a full PaaS with build pipelines — Northflank."}],"bootstrap":{"authType":"api_key","envVars":["E2B_API_KEY"],"signupUrl":"https://e2b.dev/dashboard","apiKeyUrl":"https://e2b.dev/dashboard?tab=keys","docsUrl":"https://e2b.dev/docs/quickstart","mcpServer":"npx -y @e2b/mcp-server","cliInit":"npm install -g @e2b/cli && e2b auth login","sdkInstall":{"npm":"npm install @e2b/code-interpreter","pip":"pip install e2b-code-interpreter"},"installCommand":"npm install @e2b/code-interpreter","activeModelOrSku":"e2b-sandbox-1vcpu-per-s","canonicalSnippet":"import { Sandbox } from \"@e2b/code-interpreter\";\nconst sbx = await Sandbox.create({ apiKey: process.env.E2B_API_KEY });\nawait sbx.runCode(\"print(2 + 2)\");\nawait sbx.kill();","verifyCommand":"e2b sandbox list"},"quickstartSpec":{"installCommand":"npm install @e2b/code-interpreter","envVars":["E2B_API_KEY"],"activeModelOrSku":"e2b-sandbox-1vcpu-per-s","canonicalSnippet":"import { Sandbox } from \"@e2b/code-interpreter\";\nconst sbx = await Sandbox.create({ apiKey: process.env.E2B_API_KEY });\nawait sbx.runCode(\"print(2 + 2)\");\nawait sbx.kill();","sdkInstall":{"npm":"npm install @e2b/code-interpreter","pip":"pip install e2b-code-interpreter"},"verifyCommand":"e2b sandbox list","apiKeyUrl":"https://e2b.dev/dashboard?tab=keys","docsUrl":"https://e2b.dev/docs/quickstart","mcpServer":"npx -y @e2b/mcp-server","bootstrapReason":null},"operationalGotchas":[{"code":"cold_start_p99_cliff","severity":"info","summary":"Custom Docker templates without pre-warmed snapshots incur cold image pull latency on first boot; use e2b template build to snapshot warm filesystem state.","sourceDate":"2026-10-27"}],"relatedPacks":[],"depotPick":{"id":"e2b","slug":"e2b","name":"E2B","tagline":"Depot default code sandbox for agents. Use for untrusted code; Daytona when you need persistent…","overall":8.65},"runnersUp":[{"id":"daytona","slug":"daytona","name":"Daytona","tagline":"Choose when agents need sticky filesystems and full dev environments. E2B for disposable code exec. Confirm…","overall":8.31},{"id":"modal","slug":"modal","name":"Modal","tagline":"Depot darling for Python agent backends and bursty GPU jobs. If you think in functions not VMs, start here.","overall":8.52},{"id":"braintrust","slug":"braintrust","name":"Braintrust","tagline":"Depot pick when evals are the product quality gate. Pair with Helicone/Langfuse for cheap request logs if…","overall":8.32},{"id":"northflank","slug":"northflank","name":"Northflank","tagline":"Choose when the agent needs a whole app platform, not just a code jail. E2B for pure sandboxes; Railway for…","overall":7.56}]}