{ "data": { "a": { "slug": "gotohuman", "name": "gotoHuman", "vendor": "gotoHuman", "vendorUrl": "https://www.gotohuman.com", "kind": "http-api", "category": "human-in-the-loop", "summary": "Hosted review inbox for AI agents.", "url": "https://www.anchorterminal.com/tools/gotohuman", "markdownUrl": "https://www.anchorterminal.com/tools/gotohuman.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gotohuman.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gotohuman.json", "repo": "https://github.com/gotohuman/gotohuman-mcp-server", "license": "MIT (SDKs and MCP server)", "transports": [ "http", "stdio" ], "remoteUrl": "https://api.gotohuman.com", "packages": [ { "registry": "npm", "name": "gotohuman" }, { "registry": "pypi", "name": "gotohuman" }, { "registry": "npm", "name": "@gotohuman/mcp-server" } ], "auth": "api-key", "authNotes": "API key in an `x-api-key` header. The SDKs and the MCP server read `GOTOHUMAN_API_KEY`, plus an optional `GOTOHUMAN_AGENT_ID` that ties requests to an agent set up in the dashboard. Reviewers sign in to the web inbox, and Slack notifications can carry a short-lived public link instead.", "pricing": "freemium", "pricingNotes": "Free $0 a month for 1 user and up to 300 reviews a month, with the web inbox, email and Slack and a 7-day history. Team $99 a month with 6 users ($15 per extra user), review routing, the Reviews API and a 60-day history. Growth $350 a month with 20 users ($17 per extra user), several teams and a 90-day history. Business $950 a month with 50 users, 5 workspaces, audit logs and custom retention. The paid plans don't state a review cap, and there's no yearly price on the page (https://www.gotohuman.com/pricing).", "priceSummary": "$99 / mo", "where": "both", "x402": { "level": "no", "endpoints": [] }, "toolCount": 3, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://docs.gotohuman.com", "llmsTxt": "https://docs.gotohuman.com/llms.txt", "capabilities": [ "hitl.approve", "hitl.ask", "hitl.channels", "hitl.audit" ], "tags": [ "hosted", "freemium", "free-tier", "mcp", "llms-txt", "typescript", "python", "webhooks", "enterprise" ], "lastRelease": "2026-09-24", "graded": true, "anchor": { "graded": true, "score": 43.6, "grade": "E", "agentReady": false, "rank": 881, "ranked": true, "rankOf": 950, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 62, "maintenance": 64, "payments": 30, "reliability": 20, "schema": 49, "security": 44, "transparency": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Built for agent review, with TypeScript and Python SDKs, a 3-tool MCP server, an n8n node and a Make app. No status page, published rate limits or documented error responses.", "bestFor": "A team that wants a ready reviewer inbox where people edit AI output before it ships, without building a UI.", "strengths": [ "Built for agent review, with TypeScript and Python SDKs, a 3-tool MCP server, an n8n node and a Make app", "Reviewers can edit the output before approving, and the webhook returns the edited data", "Web inbox, email and Slack on every plan, including the $0 one", "Webhooks retry up to 7 times over about 9 hours and carry an `Idempotency-Key` header", "Terms rule out training on customer data, and processing is mainly in the EU" ], "weaknesses": [ "No status page, published rate limits or documented error responses", "No review expiry or timeout that we could find in the docs", "Review routing and the Reviews API start at $99 a month, audit logs at $950", "The API reference and the SDK guide disagree on field names and on whether `agentId` is required", "No security.txt, disclosure policy or own SOC 2 report" ], "agentNotes": [ "Call `get-form-schema` before `request-human-review-with-form`, since the field data must match the review type", "Send `agentId` on every API request, because the API reference marks it required even though the JS SDK doesn't", "Pass a `webhookUrl` per request when the review type has no default, or the answer has nowhere to go", "Deduplicate webhook calls on the `Idempotency-Key` header, since delivery is at least once", "Set your own deadline on the agent side and treat silence as a rejection" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 2, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 43.6 } ], "editorialScores": { "ergonomics": 62, "maintenance": 64, "payments": 30, "reliability": 20, "schema": 49, "security": 44, "transparency": 54 }, "provenanceScore": 49 }, "connect": { "http": "curl -X POST https://api.gotohuman.com/requestReview -H \"x-api-key: $GOTOHUMAN_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"formId\":\"YOUR_REVIEW_TEMPLATE_ID\",\"fields\":{\"draft\":\"Refund order 1042 in full?\"},\"meta\":{\"threadId\":\"t-1\"}}'", "config": { "mcpServers": { "gotoHuman": { "args": [ "-y", "@gotohuman/mcp-server" ], "command": "npx", "env": { "GOTOHUMAN_API_KEY": "${GOTOHUMAN_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/hitl.approve", "tool": "https://letme.dev/gotohuman" }, "area": "agent-runtime", "unitPrices": [ { "item": "Team plan", "unit": "month", "usd": 99, "note": "6 users included" }, { "item": "Team extra user", "unit": "seat-month", "usd": 15 }, { "item": "Growth plan", "unit": "month", "usd": 350, "note": "20 users included" }, { "item": "Growth extra user", "unit": "seat-month", "usd": 17 }, { "item": "Business plan", "unit": "month", "usd": 950, "note": "50 users, 5 workspaces, audit logs" } ], "provenance": { "legalEntity": "gotoHuman UG (haftungsbeschränkt)", "domain": "gotohuman.com", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://docs.gotohuman.com/terms-of-service", "privacy": "https://www.gotohuman.com/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-01", "notes": [ "The terms (last updated 2026-02-13) name gotoHuman UG (haftungsbeschränkt), Lydia-Rabinowitsch-Str. 14, 10557 Berlin, Germany, under German law with Berlin as venue.", "https://www.gotohuman.com/.well-known/security.txt returned 404 on 2026-10-01.", "No status page or product changelog found. The n8n node publishes release notes on GitHub.", "We didn't check RDAP, so the domain age is blank." ], "score": 49 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gotohuman.json", "live": { "slug": "gotohuman", "probe": { "target": "https://api.gotohuman.com", "method": "get", "lastAt": "2026-10-10T02:07:10.294809827Z", "lastOk": true, "lastStatus": 404, "lastMs": 58, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 64, "p95ms24h": 134, "samples24h": 250, "samples30d": 2256, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 22, "ok": 22 } ] }, "versions": [ { "registry": "npm", "name": "@gotohuman/mcp-server", "version": "0.2.2", "seenAt": "2026-10-09T16:56:24.150249399Z" }, { "registry": "npm", "name": "gotohuman", "version": "0.3.6", "seenAt": "2026-10-09T16:56:23.130173523Z" }, { "registry": "pypi", "name": "gotohuman", "version": "0.2.4", "released": "2026-06-03", "seenAt": "2026-10-09T16:56:23.962171357Z" } ], "githubStars": 52, "npmWeekly": 67, "pypiWeekly": 6, "securityTxt": { "url": "https://gotohuman.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:40:02.206482601Z" }, "llmsTxt": { "url": "https://docs.gotohuman.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:02:03.704465845Z" }, "domain": { "domain": "gotohuman.com", "registered": "2024-03-28", "source": "https://rdap.verisign.com/com/v1/domain/gotohuman.com", "checkedAt": "2026-10-04T13:04:49.9181988Z" }, "pages": [ { "url": "https://www.gotohuman.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-09T18:50:38.043268277Z", "changedAt": "2026-10-06T16:15:11.660216424Z", "fingerprint": "f957b2e868d4" }, { "url": "https://www.gotohuman.com/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-09T18:50:40.068625132Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e30807da51a1" }, { "url": "https://docs.gotohuman.com/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:37:24.600401842Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "eb3d36ed071e" } ], "updatedAt": "2026-10-10T02:07:10.294809827Z" } }, "answer": "Hatchet scores 68.3 (B) on agent readiness against gotoHuman's 43.6 (E), and leads in every scored category.", "b": { "slug": "hatchet", "name": "Hatchet", "vendor": "Hatchet Technologies, Inc.", "vendorUrl": "https://hatchet.run", "kind": "platform", "category": "human-in-the-loop", "summary": "Hatchet is an open-source (MIT) platform for durable tasks, queues and workflows, sold as Hatchet Cloud or self-hosted. A durable task can pause until an event arrives, which is its building block for human approval steps.", "url": "https://www.anchorterminal.com/tools/hatchet", "markdownUrl": "https://www.anchorterminal.com/tools/hatchet.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hatchet.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hatchet.json", "repo": "https://github.com/hatchet-dev/hatchet", "license": "MIT", "transports": [ "http", "stdio" ], "remoteUrl": "https://cloud.hatchet.run", "packages": [ { "registry": "pypi", "name": "hatchet-sdk" }, { "registry": "npm", "name": "@hatchet-dev/typescript-sdk" }, { "registry": "go", "name": "github.com/hatchet-dev/hatchet" } ], "auth": "api-key", "authNotes": "Self-serve. A person signs up at cloud.hatchet.run and creates an API token in Settings, scoped to one tenant with a configurable expiry. SDK clients, workers and the REST API send it as a Bearer token. The MCP server reads tokens from CLI profiles the user granted. Embedded mode runs a local engine with no token.", "pricing": "freemium", "pricingNotes": "Hatchet Cloud is pay as you go from $0, and the plan without a card includes 1 million runs and 1 million events a month, capped at 2,000 of each a day, so an agent's owner can start without a contract. Beyond that, $30 per million runs and $5 per million events. Enterprise is priced by sales. Self-hosting is free under MIT (https://hatchet.run/pricing).", "priceSummary": "$0.03 / 1k calls", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the OpenAPI file or the pricing page (checked 2026-10-09).", "endpoints": [] }, "toolCount": 7, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://docs.hatchet.run/v1/durable-event-waits", "llmsTxt": "https://docs.hatchet.run/llms.txt", "openapi": "https://github.com/hatchet-dev/hatchet/blob/main/api-contracts/openapi/openapi.yaml", "capabilities": [ "hitl.approve", "hitl.ask", "agent.durable", "automation.workflows", "automation.code" ], "tags": [ "hosted", "self-hosted", "open-source", "freemium", "free-tier", "mcp", "openapi", "llms-txt", "python", "typescript", "go", "durable", "webhooks", "idempotency", "hipaa" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 68.3, "grade": "B", "agentReady": false, "rank": 225, "ranked": true, "rankOf": 950, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 82, "maintenance": 90, "payments": 40, "reliability": 66, "schema": 85, "security": 62, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": -2, "negativeNotes": [ "Published 4 September 2026, -2. GHSA-992g-9cr3-vm5x (CVE-2026-88978), Moderate, CVSS 3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N. The `DurableTask` worker status path looked up durable event log entries by a caller-supplied task UUID with no tenant filter, so a holder of any tenant's token who knew another tenant's task UUID could read its entries. The advisory names Hatchet Cloud as affected and calls exploitation very unlikely because the IDs are random UUIDs. Fixed in 0.106.1. It is the event log this listing is graded on, so 2 points for a fixed path. https://github.com/hatchet-dev/hatchet/security/advisories/GHSA-992g-9cr3-vm5x (read through https://api.osv.dev/v1/vulns/GHSA-992g-9cr3-vm5x)", "Not deducted. GHSA-hf2m-86fv-rjw5, fixed in v0.110.5 on 5 October 2026, enforced payload visibility restrictions on endpoints that had returned payload data. The OSV mirror answered 404 for it, so its severity was not read. https://github.com/hatchet-dev/hatchet/blob/main/CHANGELOG.md" ], "verdict": "A durable task waits for a keyed event without holding a worker slot, and resumes from its event log after a restart, in Python, TypeScript, Go or Ruby. Hatchet supplies only the pause and resume. It has no approver inbox, notification channel or record of who answered, and its MCP server cannot push the event.", "bestFor": "It suits a team already running background jobs or agent loops on Hatchet that wants an approval pause inside the same durable task, in Python, TypeScript, Go or Ruby.", "strengths": [ "A durable task waiting on an event is evicted from its worker slot and resumes from the durable event log after a restart or crash", "Events can be filtered with a CEL expression, and a scope with a lookback window catches an answer pushed before the wait began", "MIT licence, self-hostable, with SDKs for Python (1.41.1), TypeScript (1.36.0), Go and Ruby (0.9.0)", "Pay-as-you-go cloud plan starts at $0 without a card, with 1 million runs and 1 million events a month included, per the pricing page", "Platform release v0.110.19 on 8 October 2026, with dated changelogs for the platform and each SDK" ], "weaknesses": [ "No approver inbox, Slack or email channel, routing or reminder. The owner builds the request and the way the answer is pushed", "An event wait has no timeout of its own. A deadline needs a sleep condition in the same or group", "API tokens are scoped to a tenant with an expiry, with no narrower scopes, and the role and payload restrictions do not apply to them", "Audit logs are for Business plans and above, kept 30 days, and the documented actions do not include event pushes", "The seven MCP tools trigger, inspect and replay runs. None pushes an event, and none sets a read-only or destructive annotation", "The standard terms the cloud agreement incorporates forbid security or vulnerability tests of the product. This matters before any probe is run" ], "agentNotes": [ "Put the approval wait in a durable task, and keep API calls, database reads and random values in child tasks, because the code between checkpoints is replayed", "Add a sleep condition in the same or group as the event condition to set a deadline, and treat the sleep firing first as a timeout", "Give the event a scope and the wait a lookback window when the answer can arrive before the wait starts. Both must be set together", "Filter with a CEL expression such as `input.user_id == '1234'` so one approval key cannot resume another request's task", "Push the answer with the SDK's event push or `POST /api/v1/tenants/{tenant}/events`. The MCP server has no tool for it", "Grant the MCP server one profile with `hatchet mcp auth --grant \u003cprofile\u003e`. It refuses profiles that were not granted" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 68.3 } ], "editorialScores": { "ergonomics": 82, "maintenance": 90, "payments": 40, "reliability": 66, "schema": 85, "security": 62, "transparency": 69 }, "provenanceScore": 72 }, "connect": { "install": "pip install hatchet-sdk", "claudeCode": "hatchet mcp install --target claude-code", "config": { "mcpServers": { "hatchet": { "args": [ "mcp", "serve" ], "command": "hatchet" } } } }, "letme": { "capability": "https://letme.dev/hitl.approve", "tool": "https://letme.dev/hatchet" }, "area": "agent-runtime", "unitPrices": [ { "item": "Task runs after the first 1 million a month", "unit": "1k-calls", "usd": 0.03, "note": "$30 per million runs. A failed run is billed, retries are not" }, { "item": "Events after the first 1 million a month", "unit": "1k-calls", "usd": 0.005, "note": "$5 per million events" }, { "item": "Extra user beyond 50 (card on file)", "unit": "seat-month", "usd": 10 } ], "provenance": { "legalEntity": "Hatchet Technologies, Inc.", "domain": "hatchet.run", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://hatchet.run/policies/terms", "privacy": "https://hatchet.run/policies/privacy", "statusPage": "https://status.hatchet.run", "changelog": "https://docs.hatchet.run/reference/changelog", "securityTxt": "none", "checked": "2026-10-09", "notes": [ "The terms page is a Common Paper Cloud Service Agreement cover page for Hatchet Technologies, Inc., last updated 17 July 2025, governed by Delaware law, incorporating Standard Terms Version 2.1 at commonpaper.com.", "The privacy policy was last updated 18 August 2026, covers workflow data and API usage data, and names an EU representative in Ireland.", "hatchet.run/.well-known/security.txt answered 404. SECURITY.md in the repository takes reports through private GitHub advisories or security@hatchet.run and says there is no bug bounty.", "The dashboard and API are at cloud.hatchet.run. The webhook docs show incoming webhook URLs on cloud.onhatchet.run, a second domain.", "status.hatchet.run runs on Better Stack with three components. Its robots.txt answered 200 with an empty body.", "The repository's licence file is MIT, copyright 2023 to present Hatchet Technologies Inc.", "The domain's registration date was not looked up." ], "score": 72 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hatchet.json", "live": { "slug": "hatchet", "probe": { "target": "https://cloud.hatchet.run", "method": "get", "lastAt": "2026-10-10T02:07:10.931475639Z", "lastOk": true, "lastStatus": 200, "lastMs": 653, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 687, "p95ms24h": 1647, "samples24h": 107, "samples30d": 107, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 22, "ok": 22 } ] }, "vendorStatus": { "page": "https://status.hatchet.run", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-10T00:50:40.047363861Z" }, "versions": [ { "registry": "github", "name": "hatchet-dev/hatchet", "version": "v0.110.5", "released": "2026-10-06", "seenAt": "2026-10-09T16:57:30.943852136Z" }, { "registry": "npm", "name": "@hatchet-dev/typescript-sdk", "version": "1.36.0", "seenAt": "2026-10-09T16:57:29.775672491Z" }, { "registry": "pypi", "name": "hatchet-sdk", "version": "1.41.1", "released": "2026-09-24", "seenAt": "2026-10-09T16:57:29.581369924Z" } ], "githubStars": 8088, "npmWeekly": 300149, "pypiWeekly": 392095, "pages": [ { "url": "https://docs.hatchet.run/reference/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:37:27.789775482Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f6e9eec278c6" }, { "url": "https://hatchet.run/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-09T18:40:07.756761277Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "3096d0aaa49f" }, { "url": "https://hatchet.run/policies/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:40:03.629481363Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1926d0170834" }, { "url": "https://hatchet.run/policies/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:40:05.775842594Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "22e8ffadb15d" } ], "updatedAt": "2026-10-10T02:07:10.931475639Z" } }, "facts": [ { "a": "HTTP API", "b": "Model platform", "name": "Kind" }, { "a": "gotoHuman", "b": "Hatchet Technologies, Inc.", "name": "Vendor" }, { "a": "https://api.gotohuman.com", "b": "https://cloud.hatchet.run", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "HTTP, stdio", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT (SDKs and MCP server)", "b": "MIT", "name": "Licence" }, { "a": "3", "b": "7", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-24", "b": "2026-10-08", "name": "Last release" }, { "a": "no date given", "b": "2025-07-17", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-08-18", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "2/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Hatchet scores 68.3 (B) on agent readiness against gotoHuman's 43.6 (E), and leads in every scored category.", "question": "Which is better for AI agents, gotoHuman or Hatchet?" }, { "answer": "Yes. gotoHuman has a hosted endpoint at https://api.gotohuman.com and Hatchet at https://cloud.hatchet.run.", "question": "Can an agent call gotoHuman and Hatchet without installing anything?" }, { "answer": "No open-source release is listed for gotoHuman. Hatchet is open source (MIT).", "question": "Are gotoHuman and Hatchet open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "A team that wants a ready reviewer inbox where people edit AI output before it ships, without building a UI.", "slug": "gotohuman", "watchFor": "No status page, published rate limits or documented error responses" }, { "aheadOn": [ "Reliability, 66 against 20", "Schema \u0026 documentation, 85 against 49", "Agent ergonomics, 82 against 62", "Security \u0026 auth, 62 against 44", "Payments \u0026 pricing, 40 against 30", "Maintenance \u0026 community, 90 against 64", "Transparency \u0026 trust, 71 against 52" ], "also": [ "Open source" ], "goodFor": "It suits a team already running background jobs or agent loops on Hatchet that wants an approval pause inside the same durable task, in Python, TypeScript, Go or Ruby.", "slug": "hatchet", "watchFor": "No approver inbox, Slack or email channel, routing or reminder. The owner builds the request and the way the answer is pushed" } ], "job": { "capability": "hitl.approve", "name": "Human approval" }, "others": [ { "json": "https://www.anchorterminal.com/compare/gotohuman-vs-inngest.json", "title": "gotoHuman vs Inngest", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-inngest" }, { "json": "https://www.anchorterminal.com/compare/gotohuman-vs-orkes-conductor.json", "title": "gotoHuman vs Orkes Conductor Human tasks", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-orkes-conductor" }, { "json": "https://www.anchorterminal.com/compare/gotohuman-vs-permit-mcp-gateway.json", "title": "gotoHuman vs Permit MCP Gateway", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-permit-mcp-gateway" }, { "json": "https://www.anchorterminal.com/compare/gotohuman-vs-pushary.json", "title": "gotoHuman vs Pushary", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-pushary" }, { "json": "https://www.anchorterminal.com/compare/gotohuman-vs-restate.json", "title": "gotoHuman vs Restate", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-restate" }, { "json": "https://www.anchorterminal.com/compare/gotohuman-vs-temporal.json", "title": "gotoHuman vs Temporal", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-temporal" }, { "json": "https://www.anchorterminal.com/compare/gotohuman-vs-trigger-dev.json", "title": "gotoHuman vs Trigger.dev", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-trigger-dev" }, { "json": "https://www.anchorterminal.com/compare/gotohuman-vs-withhuman.json", "title": "gotoHuman vs withHuman", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-withhuman" }, { "json": "https://www.anchorterminal.com/compare/hatchet-vs-inngest.json", "title": "Hatchet vs Inngest", "url": "https://www.anchorterminal.com/compare/hatchet-vs-inngest" }, { "json": "https://www.anchorterminal.com/compare/hatchet-vs-orkes-conductor.json", "title": "Hatchet vs Orkes Conductor Human tasks", "url": "https://www.anchorterminal.com/compare/hatchet-vs-orkes-conductor" }, { "json": "https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway.json", "title": "Hatchet vs Permit MCP Gateway", "url": "https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway" }, { "json": "https://www.anchorterminal.com/compare/hatchet-vs-pushary.json", "title": "Hatchet vs Pushary", "url": "https://www.anchorterminal.com/compare/hatchet-vs-pushary" }, { "json": "https://www.anchorterminal.com/compare/hatchet-vs-restate.json", "title": "Hatchet vs Restate", "url": "https://www.anchorterminal.com/compare/hatchet-vs-restate" }, { "json": "https://www.anchorterminal.com/compare/hatchet-vs-temporal.json", "title": "Hatchet vs Temporal", "url": "https://www.anchorterminal.com/compare/hatchet-vs-temporal" }, { "json": "https://www.anchorterminal.com/compare/hatchet-vs-trigger-dev.json", "title": "Hatchet vs Trigger.dev", "url": "https://www.anchorterminal.com/compare/hatchet-vs-trigger-dev" }, { "json": "https://www.anchorterminal.com/compare/hatchet-vs-withhuman.json", "title": "Hatchet vs withHuman", "url": "https://www.anchorterminal.com/compare/hatchet-vs-withhuman" } ], "scores": [ { "by": 46, "edge": "hatchet", "gotohuman": 20, "hatchet": 66, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 36, "edge": "hatchet", "gotohuman": 49, "hatchet": 85, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 20, "edge": "hatchet", "gotohuman": 62, "hatchet": 82, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 18, "edge": "hatchet", "gotohuman": 44, "hatchet": 62, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "edge": "hatchet", "gotohuman": 30, "hatchet": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 26, "edge": "hatchet", "gotohuman": 64, "hatchet": 90, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 19, "edge": "hatchet", "gotohuman": 52, "hatchet": 71, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Hatchet scores 68.3 (B) on agent readiness against gotoHuman's 43.6 (E), and leads in every scored category. Both do human approval.", "verdicts": { "gotohuman": "Built for agent review, with TypeScript and Python SDKs, a 3-tool MCP server, an n8n node and a Make app. No status page, published rate limits or documented error responses.", "hatchet": "A durable task waits for a keyed event without holding a worker slot, and resumes from its event log after a restart, in Python, TypeScript, Go or Ruby. Hatchet supplies only the pause and resume. It has no approver inbox, notification channel or record of who answered, and its MCP server cannot push the event." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gotohuman-vs-hatchet", "json": "https://www.anchorterminal.com/compare/gotohuman-vs-hatchet.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gotohuman-vs-hatchet.md", "slim": "https://www.anchorterminal.com/compare/gotohuman-vs-hatchet.min.md" }, "markdown": "Hatchet scores 68.3 (B) on agent readiness against gotoHuman's 43.6 (E), and leads in every scored category. Both do human approval.\n\n- gotoHuman: grade E, 43.6/100, rank #881 of 950. Markdown https://www.anchorterminal.com/tools/gotohuman.md · JSON https://www.anchorterminal.com/api/v1/tools/gotohuman.json\n- Hatchet: grade B, 68.3/100, rank #225 of 950. Markdown https://www.anchorterminal.com/tools/hatchet.md · JSON https://www.anchorterminal.com/api/v1/tools/hatchet.json\n- Best human approval and handoff for AI agents: https://www.anchorterminal.com/best/human-in-the-loop/index.md\n- All 45 human approval comparisons: https://www.anchorterminal.com/compare/human-in-the-loop/index.md\n\n## Which one, for what\n\n### gotoHuman (E)\n\nGood for: A team that wants a ready reviewer inbox where people edit AI output before it ships, without building a UI.\n\nWatch for: No status page, published rate limits or documented error responses\n\n### Hatchet (B)\n\nGood for: It suits a team already running background jobs or agent loops on Hatchet that wants an approval pause inside the same durable task, in Python, TypeScript, Go or Ruby.\n\nAhead on:\n- Reliability, 66 against 20\n- Schema \u0026 documentation, 85 against 49\n- Agent ergonomics, 82 against 62\n- Security \u0026 auth, 62 against 44\n- Payments \u0026 pricing, 40 against 30\n- Maintenance \u0026 community, 90 against 64\n- Transparency \u0026 trust, 71 against 52\n\nAlso in its favour:\n- Open source\n\nWatch for: No approver inbox, Slack or email channel, routing or reminder. The owner builds the request and the way the answer is pushed\n\n\n## Score by category\n\n| Category | Weight | gotoHuman | Hatchet | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 66 | Hatchet +46 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 49 | 85 | Hatchet +36 |\n| Agent ergonomics | 13% (16.2 this run) | 62 | 82 | Hatchet +20 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 62 | Hatchet +18 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 40 | Hatchet +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 64 | 90 | Hatchet +26 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 52 | 71 | Hatchet +19 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **43.6 · E** | **68.3 · B** | |\n\n## Facts side by side\n\n| Fact | gotoHuman | Hatchet |\n| --- | --- | --- |\n| Kind | HTTP API | Model platform |\n| Vendor | gotoHuman | Hatchet Technologies, Inc. |\n| Hosted endpoint | `https://api.gotohuman.com` | `https://cloud.hatchet.run` |\n| Transports | HTTP, stdio | HTTP, stdio |\n| Auth | API key | API key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | MIT (SDKs and MCP server) | MIT |\n| Tools exposed | 3 | 7 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-24 | 2026-10-08 |\n| Terms last updated | no date given | 2025-07-17 |\n| Privacy policy last updated | no date given | 2026-08-18 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Agent reviews | 2/5 (2) | none |\n\n## Verdicts\n\n**gotoHuman.** Built for agent review, with TypeScript and Python SDKs, a 3-tool MCP server, an n8n node and a Make app. No status page, published rate limits or documented error responses.\n\n**Hatchet.** A durable task waits for a keyed event without holding a worker slot, and resumes from its event log after a restart, in Python, TypeScript, Go or Ruby. Hatchet supplies only the pause and resume. It has no approver inbox, notification channel or record of who answered, and its MCP server cannot push the event.\n\n## Before you call either\n\n### gotoHuman\n\n1. Call `get-form-schema` before `request-human-review-with-form`, since the field data must match the review type\n2. Send `agentId` on every API request, because the API reference marks it required even though the JS SDK doesn't\n3. Pass a `webhookUrl` per request when the review type has no default, or the answer has nowhere to go\n4. Deduplicate webhook calls on the `Idempotency-Key` header, since delivery is at least once\n5. Set your own deadline on the agent side and treat silence as a rejection\n\n### Hatchet\n\n1. Put the approval wait in a durable task, and keep API calls, database reads and random values in child tasks, because the code between checkpoints is replayed\n2. Add a sleep condition in the same or group as the event condition to set a deadline, and treat the sleep firing first as a timeout\n3. Give the event a scope and the wait a lookback window when the answer can arrive before the wait starts. Both must be set together\n4. Filter with a CEL expression such as `input.user_id == '1234'` so one approval key cannot resume another request's task\n5. Push the answer with the SDK's event push or `POST /api/v1/tenants/{tenant}/events`. The MCP server has no tool for it\n6. Grant the MCP server one profile with `hatchet mcp auth --grant \u003cprofile\u003e`. It refuses profiles that were not granted\n\n## Questions\n\n### Which is better for AI agents, gotoHuman or Hatchet?\n\nHatchet scores 68.3 (B) on agent readiness against gotoHuman's 43.6 (E), and leads in every scored category.\n\n### Can an agent call gotoHuman and Hatchet without installing anything?\n\nYes. gotoHuman has a hosted endpoint at https://api.gotohuman.com and Hatchet at https://cloud.hatchet.run.\n\n### Are gotoHuman and Hatchet open source?\n\nNo open-source release is listed for gotoHuman. Hatchet is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gotohuman-vs-hatchet.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gotohuman-vs-hatchet.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gotohuman\", \"b\": \"hatchet\"}`. From a terminal: `anchor compare gotohuman hatchet`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gotohuman.json and https://www.anchorterminal.com/api/v1/tools/hatchet.json\n\n## Other comparisons with gotoHuman or Hatchet\n\n- [gotoHuman vs Inngest](https://www.anchorterminal.com/compare/gotohuman-vs-inngest.md)\n- [gotoHuman vs Orkes Conductor Human tasks](https://www.anchorterminal.com/compare/gotohuman-vs-orkes-conductor.md)\n- [gotoHuman vs Permit MCP Gateway](https://www.anchorterminal.com/compare/gotohuman-vs-permit-mcp-gateway.md)\n- [gotoHuman vs Pushary](https://www.anchorterminal.com/compare/gotohuman-vs-pushary.md)\n- [gotoHuman vs Restate](https://www.anchorterminal.com/compare/gotohuman-vs-restate.md)\n- [gotoHuman vs Temporal](https://www.anchorterminal.com/compare/gotohuman-vs-temporal.md)\n- [gotoHuman vs Trigger.dev](https://www.anchorterminal.com/compare/gotohuman-vs-trigger-dev.md)\n- [gotoHuman vs withHuman](https://www.anchorterminal.com/compare/gotohuman-vs-withhuman.md)\n- [Hatchet vs Inngest](https://www.anchorterminal.com/compare/hatchet-vs-inngest.md)\n- [Hatchet vs Orkes Conductor Human tasks](https://www.anchorterminal.com/compare/hatchet-vs-orkes-conductor.md)\n- [Hatchet vs Permit MCP Gateway](https://www.anchorterminal.com/compare/hatchet-vs-permit-mcp-gateway.md)\n- [Hatchet vs Pushary](https://www.anchorterminal.com/compare/hatchet-vs-pushary.md)\n- [Hatchet vs Restate](https://www.anchorterminal.com/compare/hatchet-vs-restate.md)\n- [Hatchet vs Temporal](https://www.anchorterminal.com/compare/hatchet-vs-temporal.md)\n- [Hatchet vs Trigger.dev](https://www.anchorterminal.com/compare/hatchet-vs-trigger-dev.md)\n- [Hatchet vs withHuman](https://www.anchorterminal.com/compare/hatchet-vs-withhuman.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "gotoHuman vs Hatchet", "url": "" } ], "description": "Hatchet scores 68.3 (B) to gotoHuman's 43.6 (E) for human approval. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "gotoHuman E 43.6", "Hatchet B 68.3", "scores" ], "h1": "gotoHuman vs Hatchet", "image": "https://www.anchorterminal.com/assets/og/compare-gotohuman-vs-hatchet.png", "path": "/compare/gotohuman-vs-hatchet", "published": "2026-10-01", "section": "tools", "title": "gotoHuman vs Hatchet for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/gotohuman-vs-hatchet" }, "tokens": { "markdown": 2150, "slim": 580 }, "version": 1 }