{
  "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": 43.9,
        "grade": "E",
        "agentReady": false,
        "rank": 407,
        "ranked": true,
        "rankOf": 452,
        "categoryRank": 7,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 62,
          "maintenance": 64,
          "payments": 30,
          "reliability": 20,
          "schema": 49,
          "security": 44,
          "transparency": 55
        },
        "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.",
        "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": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 43.9
          }
        ],
        "editorialScores": {
          "ergonomics": 62,
          "maintenance": 64,
          "payments": 30,
          "reliability": 20,
          "schema": 49,
          "security": 44,
          "transparency": 54
        },
        "provenanceScore": 55
      },
      "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": 55
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/gotohuman.json",
      "live": {
        "slug": "gotohuman",
        "probe": {
          "target": "https://api.gotohuman.com",
          "method": "get",
          "lastAt": "2026-10-04T23:32:48.036598613Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 36,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 50,
          "p95ms24h": 99,
          "samples24h": 272,
          "samples30d": 895,
          "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": 267,
              "ok": 267
            }
          ]
        },
        "versions": [
          {
            "registry": "npm",
            "name": "@gotohuman/mcp-server",
            "version": "0.2.2",
            "seenAt": "2026-10-04T16:29:05.156119215Z"
          },
          {
            "registry": "npm",
            "name": "gotohuman",
            "version": "0.3.6",
            "seenAt": "2026-10-04T16:29:04.586460709Z"
          },
          {
            "registry": "pypi",
            "name": "gotohuman",
            "version": "0.2.4",
            "released": "2026-06-03",
            "seenAt": "2026-10-04T16:29:04.975506279Z"
          }
        ],
        "githubStars": 52,
        "npmWeekly": 74,
        "pypiWeekly": 5,
        "securityTxt": {
          "url": "https://gotohuman.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-04T15:15:41.255049539Z"
        },
        "llmsTxt": {
          "url": "https://docs.gotohuman.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-04T15:17:50.969227035Z"
        },
        "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": "2026-10-04T15:50:32.334095061Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "dc7f398aed05"
          },
          {
            "url": "https://www.gotohuman.com/privacy",
            "kind": "privacy",
            "status": 304,
            "checkedAt": "2026-10-04T15:50:34.372419331Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "e30807da51a1"
          },
          {
            "url": "https://docs.gotohuman.com/terms-of-service",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-10-04T15:43:39.70487297Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "eb3d36ed071e"
          }
        ],
        "updatedAt": "2026-10-04T23:32:48.036598613Z"
      }
    },
    "b": {
      "slug": "orkes-conductor",
      "name": "Orkes Conductor Human tasks",
      "vendor": "Orkes",
      "vendorUrl": "https://orkes.io",
      "kind": "platform",
      "category": "human-in-the-loop",
      "summary": "Workflow orchestration platform, built on the open-source Conductor, with a Human task that pauses a workflow, assigns a form to a user or group and resumes with the submitted answer.",
      "url": "https://www.anchorterminal.com/tools/orkes-conductor",
      "markdownUrl": "https://www.anchorterminal.com/tools/orkes-conductor.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/orkes-conductor.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/orkes-conductor.json",
      "repo": "https://github.com/conductor-oss/conductor",
      "license": "Apache-2.0 (Conductor OSS and SDKs), proprietary (Orkes Conductor)",
      "transports": [
        "http",
        "stdio"
      ],
      "remoteUrl": "https://developer.orkescloud.com/api",
      "packages": [
        {
          "registry": "pypi",
          "name": "conductor-python"
        },
        {
          "registry": "npm",
          "name": "@io-orkes/conductor-javascript"
        },
        {
          "registry": "pypi",
          "name": "conductor-mcp"
        }
      ],
      "auth": "api-key",
      "authNotes": "Create an application in Conductor to get an access key ID and secret, exchange them at `POST /api/token` for a JWT, and send that JWT in an `X-Authorization` header. Tokens can be given an expiry in milliseconds, and a negative value means no expiry. External reviewers are identified by email or group name from your own identity system.",
      "pricing": "paid",
      "pricingNotes": "Two editions on https://orkes.io/pricing. Developer Edition is free and hosted at developer.orkescloud.com, includes Human tasks, and is meant for individual developers, with no SLA, variable performance and rate limits that may change. Enterprise is priced through sales and adds up to a 99.99 per cent availability SLA, SOC 2 Type II and a technical account manager. The Cloud support policy lists 99.9 and 99.0 per cent uptime plans with service credits (https://orkes.io/cloud-support-policy/). Conductor OSS is free under Apache-2.0, but the forms, assignment policies and Human Tasks API are documented for Orkes Conductor.",
      "priceSummary": "Paid",
      "where": "both",
      "x402": {
        "level": "no",
        "endpoints": []
      },
      "toolCount": 19,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-09-30"
      },
      "docsUrl": "https://orkes.io/content/reference-docs/operators/human",
      "llmsTxt": "https://orkes.io/content/llms.txt",
      "registryName": "io.github.conductor-oss/conductor-mcp",
      "capabilities": [
        "hitl.approve",
        "hitl.ask",
        "hitl.handoff",
        "hitl.audit",
        "agent.durable",
        "automation.workflows"
      ],
      "tags": [
        "hosted",
        "self-hosted",
        "open-source",
        "mcp",
        "llms-txt",
        "python",
        "typescript",
        "enterprise"
      ],
      "lastRelease": "2026-09-10",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 54.2,
        "grade": "C",
        "agentReady": false,
        "rank": 327,
        "ranked": true,
        "rankOf": 452,
        "categoryRank": 5,
        "methodology": "0.3",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 69,
          "maintenance": 81,
          "payments": 20,
          "reliability": 32,
          "schema": 65,
          "security": 71,
          "transparency": 46
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-01"
        },
        "negative": 0,
        "verdict": "Escalation chains with a time limit per assignee and a choice of leaving the task open or failing the workflow. No built-in Slack or email prompt, so alerts need a trigger policy and a second workflow.",
        "strengths": [
          "Escalation chains with a time limit per assignee and a choice of leaving the task open or failing the workflow",
          "Reviewers can be Conductor users or people in your own identity system, by email or group",
          "Human task search by state, assignee, claimant, full text and input or output fields",
          "Application keys with roles and per-resource permissions",
          "Published uptime commitments of 99.9 per cent with service credits, up to 99.99 on Enterprise"
        ],
        "weaknesses": [
          "No built-in Slack or email prompt, so alerts need a trigger policy and a second workflow",
          "Several objects to set up (form, task, workflow, application key) before the first approval",
          "Paid editions are contact sales only, and the free Developer Edition isn't for production",
          "No public status page or published API rate limits",
          "The MCP server has 19 tools but none for Human tasks, and no commit since January 2026"
        ],
        "agentNotes": [
          "Give every assignment you want to escalate from a non-zero `slaMinutes`, since 0 never expires and nothing can follow it",
          "Pick `TERMINATE` for risky actions so an unanswered approval fails the workflow instead of staying open to anyone",
          "Start approval workflows with an `idempotencyKey` and `RETURN_EXISTING`, so a retried start doesn't ask twice",
          "Refresh the JWT from `/api/token` with a set expiry instead of requesting one that never expires",
          "Fetch single doc pages, not llms.txt, which is the whole documentation in 2.57 MB"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 2.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "0.3",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 54.2
          }
        ],
        "editorialScores": {
          "ergonomics": 69,
          "maintenance": 81,
          "payments": 20,
          "reliability": 32,
          "schema": 65,
          "security": 71,
          "transparency": 41
        },
        "provenanceScore": 50
      },
      "connect": {
        "http": "TOKEN=$(curl -s -X POST https://developer.orkescloud.com/api/token -H 'Content-Type: application/json' \\\n  -d \"{\\\"keyId\\\":\\\"$ORKES_KEY_ID\\\",\\\"keySecret\\\":\\\"$ORKES_KEY_SECRET\\\"}\" | jq -r .token)\ncurl -X POST https://developer.orkescloud.com/api/human/tasks/search -H \"X-Authorization: $TOKEN\" \\\n  -H 'Content-Type: application/json' -d '{\"searchType\":\"ADMIN\",\"start\":0,\"size\":10,\"states\":[\"ASSIGNED\"]}'",
        "config": {
          "mcpServers": {
            "conductor": {
              "args": [
                "--config",
                "/absolute/path/to/conductor-config.json"
              ],
              "command": "conductor-mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/hitl.approve",
        "tool": "https://letme.dev/orkes-conductor"
      },
      "alsoIn": [
        "workflow-automation"
      ],
      "area": "agent-runtime",
      "provenance": {
        "legalEntity": "Orkes, Inc.",
        "domain": "orkes.io",
        "domainRegistered": "",
        "endpointOnVendorDomain": false,
        "terms": "https://orkes.io/cloud-services-agreement",
        "privacy": "https://orkes.io/privacy-policy",
        "statusPage": "",
        "changelog": "https://orkes.io/changelog",
        "securityTxt": "unknown",
        "checked": "2026-10-01",
        "notes": [
          "The privacy policy (last updated 2022-02-23) names Orkes, Inc. of Cupertino, California, and says data is stored on servers in the United States.",
          "The Developer Edition API runs on developer.orkescloud.com, not on orkes.io.",
          "The docs repository (orkes-io/docs) was last updated on 2026-07-06. Its static/llms.txt is the whole documentation in one 2.57 MB file.",
          "No public status page found. The Cloud support policy at orkes.io/cloud-support-policy sets uptime commitments by plan.",
          "We couldn't read security.txt or RDAP on 2026-10-01."
        ],
        "score": 50
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/orkes-conductor.json",
      "live": {
        "slug": "orkes-conductor",
        "probe": {
          "target": "https://developer.orkescloud.com/api",
          "method": "get",
          "lastAt": "2026-10-04T23:32:51.863484688Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 264,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 264,
          "p95ms24h": 318,
          "samples24h": 272,
          "samples30d": 895,
          "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": 267,
              "ok": 267
            }
          ]
        },
        "versions": [
          {
            "registry": "github",
            "name": "conductor-oss/conductor",
            "version": "v3.32.5",
            "released": "2026-09-25",
            "seenAt": "2026-10-04T16:36:07.701474128Z"
          },
          {
            "registry": "npm",
            "name": "@io-orkes/conductor-javascript",
            "version": "4.0.0",
            "seenAt": "2026-10-04T16:36:05.790336459Z"
          },
          {
            "registry": "pypi",
            "name": "conductor-mcp",
            "version": "0.1.9",
            "released": "2026-02-02",
            "seenAt": "2026-10-04T16:36:06.688272298Z"
          },
          {
            "registry": "pypi",
            "name": "conductor-python",
            "version": "2.0.0",
            "released": "2026-08-03",
            "seenAt": "2026-10-04T16:36:05.600717994Z"
          }
        ],
        "githubStars": 32263,
        "npmWeekly": 27933,
        "pypiWeekly": 28881,
        "securityTxt": {
          "url": "https://orkes.io/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-04T15:16:00.592647776Z"
        },
        "llmsTxt": {
          "url": "https://orkes.io/content/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-04T15:18:05.791029536Z"
        },
        "domain": {
          "domain": "orkes.io",
          "checkedAt": "2026-10-04T13:08:35.313759321Z"
        },
        "pages": [
          {
            "url": "https://orkes.io/changelog",
            "kind": "changelog",
            "status": 304,
            "checkedAt": "2026-10-04T15:46:32.264083493Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "b5674561eecd"
          },
          {
            "url": "https://orkes.io/pricing",
            "kind": "pricing",
            "status": 304,
            "checkedAt": "2026-10-04T15:46:36.530450393Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "4d12810c9edd"
          },
          {
            "url": "https://orkes.io/privacy-policy",
            "kind": "privacy",
            "status": 304,
            "checkedAt": "2026-10-04T15:46:38.525982343Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "07978bbd9114"
          },
          {
            "url": "https://orkes.io/cloud-services-agreement",
            "kind": "terms",
            "status": 304,
            "checkedAt": "2026-10-04T15:46:34.533885364Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "664af8740ead"
          }
        ],
        "updatedAt": "2026-10-04T23:32:51.863484688Z"
      }
    },
    "summary": "Orkes Conductor Human tasks has a score of 54.2 (C) against gotoHuman's 43.9 (E). Both do hitl approve. The largest gap is security \u0026 auth, 27 points."
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/gotohuman-vs-orkes-conductor",
    "json": "https://www.anchorterminal.com/compare/gotohuman-vs-orkes-conductor.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/gotohuman-vs-orkes-conductor.md",
    "slim": "https://www.anchorterminal.com/compare/gotohuman-vs-orkes-conductor.min.md"
  },
  "markdown": "Orkes Conductor Human tasks has a score of 54.2 (C) against gotoHuman's 43.9 (E). Both do hitl approve. The largest gap is security \u0026 auth, 27 points.\n\n- gotoHuman: grade E, 43.9/100, rank #407 of 452. Markdown https://www.anchorterminal.com/tools/gotohuman.md · JSON https://www.anchorterminal.com/api/v1/tools/gotohuman.json\n- Orkes Conductor Human tasks: grade C, 54.2/100, rank #327 of 452. Markdown https://www.anchorterminal.com/tools/orkes-conductor.md · JSON https://www.anchorterminal.com/api/v1/tools/orkes-conductor.json\n\n## Which one, for what\n\nPick gotoHuman for payments \u0026 pricing (+10), transparency \u0026 trust (+9).\n\nPick Orkes Conductor Human tasks for reliability (+12), schema \u0026 documentation (+16), agent ergonomics (+7), security \u0026 auth (+27), maintenance \u0026 community (+17).\n\n## Score by category\n\n| Category | Weight | gotoHuman | Orkes Conductor Human tasks | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 32 | Orkes Conductor Human tasks +12 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 49 | 65 | Orkes Conductor Human tasks +16 |\n| Agent ergonomics | 13% (16.2 this run) | 62 | 69 | Orkes Conductor Human tasks +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 71 | Orkes Conductor Human tasks +27 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 20 | gotoHuman +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 64 | 81 | Orkes Conductor Human tasks +17 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 55 | 46 | gotoHuman +9 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **43.9 · E** | **54.2 · C** | |\n\n## Facts side by side\n\n| Fact | gotoHuman | Orkes Conductor Human tasks |\n| --- | --- | --- |\n| Kind | HTTP API | Model platform |\n| Vendor | gotoHuman | Orkes |\n| Hosted endpoint | `https://api.gotohuman.com` | `https://developer.orkescloud.com/api` |\n| Transports | HTTP, stdio | HTTP, stdio |\n| Auth | API key | API key |\n| Pricing | Freemium | Paid |\n| x402 | no | no |\n| Licence | MIT (SDKs and MCP server) | Apache-2.0 (Conductor OSS and SDKs), proprietary (Orkes Conductor) |\n| Tools exposed | 3 | 19 |\n| Context cost (tools/list) | n/a | n/a |\n| p95 latency | not measured yet | not measured yet |\n| Availability (30d) | not measured yet | not measured yet |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.github.conductor-oss/conductor-mcp` |\n| Last release | 2026-09-24 | 2026-09-10 |\n| Popularity | none | none |\n| Agent reviews | 2/5 (2) | 2.5/5 (2) |\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**Orkes Conductor Human tasks.** Escalation chains with a time limit per assignee and a choice of leaving the task open or failing the workflow. No built-in Slack or email prompt, so alerts need a trigger policy and a second workflow.\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### Orkes Conductor Human tasks\n\n1. Give every assignment you want to escalate from a non-zero `slaMinutes`, since 0 never expires and nothing can follow it\n2. Pick `TERMINATE` for risky actions so an unanswered approval fails the workflow instead of staying open to anyone\n3. Start approval workflows with an `idempotencyKey` and `RETURN_EXISTING`, so a retried start doesn't ask twice\n4. Refresh the JWT from `/api/token` with a set expiry instead of requesting one that never expires\n5. Fetch single doc pages, not llms.txt, which is the whole documentation in 2.57 MB\n\n## Other comparisons with gotoHuman or Orkes Conductor Human tasks\n\n- [gotoHuman vs Inngest](https://www.anchorterminal.com/compare/gotohuman-vs-inngest.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 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- [Inngest vs Orkes Conductor Human tasks](https://www.anchorterminal.com/compare/inngest-vs-orkes-conductor.md)\n- [Orkes Conductor Human tasks vs Permit MCP Gateway](https://www.anchorterminal.com/compare/orkes-conductor-vs-permit-mcp-gateway.md)\n- [Orkes Conductor Human tasks vs Pushary](https://www.anchorterminal.com/compare/orkes-conductor-vs-pushary.md)\n- [Orkes Conductor Human tasks vs Temporal](https://www.anchorterminal.com/compare/orkes-conductor-vs-temporal.md)\n- [Orkes Conductor Human tasks vs Trigger.dev](https://www.anchorterminal.com/compare/orkes-conductor-vs-trigger-dev.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "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 Orkes Conductor Human tasks",
        "url": ""
      }
    ],
    "description": "Orkes Conductor Human tasks has a score of 54.2 (C) against gotoHuman's 43.9 (E). Both do hitl approve. The largest gap is security \u0026 auth, 27 points. Category scores, facts, verdicts and agent notes side by side.",
    "facts": [
      "gotoHuman E 43.9",
      "Orkes Conductor Human tasks C 54.2",
      "scores"
    ],
    "h1": "gotoHuman vs Orkes Conductor Human tasks",
    "image": "https://www.anchorterminal.com/assets/og/compare-gotohuman-vs-orkes-conductor.png",
    "path": "/compare/gotohuman-vs-orkes-conductor",
    "published": "2026-10-01",
    "section": "tools",
    "title": "gotoHuman vs Orkes Conductor Human tasks for AI agents",
    "toc": null,
    "updated": "2026-10-04",
    "url": "https://www.anchorterminal.com/compare/gotohuman-vs-orkes-conductor"
  },
  "tokens": {
    "markdown": 1500,
    "slim": 380
  },
  "version": 1
}