{
  "data": {
    "a": {
      "slug": "click-agents",
      "name": "Click",
      "vendor": "Click AI Labs, Inc.",
      "vendorUrl": "https://useclick.ai",
      "company": "useclick.ai",
      "kind": "http-api",
      "category": "agent-harnesses",
      "summary": "Click is a hosted managed agents API from Click AI Labs. An application sets an agent's model keys, instructions and tools and submits tasks, and Click runs the agent loop, sandbox, browser and search, returning events or webhooks.",
      "url": "https://www.anchorterminal.com/tools/click-agents",
      "markdownUrl": "https://www.anchorterminal.com/tools/click-agents.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/click-agents.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/click-agents.json",
      "dns": "click-agents.grade.anchorterminal.com",
      "license": "Proprietary hosted service under Click's Terms of Service, based on the Common Paper Cloud Service Agreement 2.1",
      "transports": [
        "http",
        "streamable-http"
      ],
      "remoteUrl": "https://api.useclick.ai/v1",
      "packages": [],
      "auth": "mixed",
      "authNotes": "Platform API keys created in the dashboard or through `/api-keys`, sent as `Authorization: Bearer`. Each key has full access to its tenant, including key management, and stops working when revoked. The MCP server also takes OAuth through WorkOS, with scoped tokens issued for the MCP endpoint only. Writes need a card verified in the dashboard first, or they return `402 card_verification_required`.",
      "pricing": "freemium",
      "pricingNotes": "Free plan at $0 a month with 2 concurrent sessions, 100 MB storage, 1 managed sandbox hour, 1 managed browser hour and 100 web searches a month. Pro is $199 a month with 50 sessions and 100 hours of each. Enterprise is priced on request. Model use is billed by the user's own provider keys. A card must be verified before any write, though verification doesn't charge it.",
      "priceSummary": "$199 / mo",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in llms-full.txt, the API conventions or the pricing page (checked 2026-11-18). The API's only 402 is `card_verification_required`, which asks for a card in the dashboard.",
        "endpoints": []
      },
      "toolCount": 23,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://useclick.ai/reference",
      "llmsTxt": "https://useclick.ai/llms.txt",
      "openapi": "https://useclick.ai/reference/openapi.yaml",
      "capabilities": [
        "agent.harness",
        "agent.mcp-client",
        "sandbox.code",
        "sandbox.browser",
        "web.search"
      ],
      "tags": [
        "hosted",
        "freemium",
        "openapi",
        "llms-txt",
        "webhooks",
        "streaming",
        "mcp",
        "remote-mcp",
        "oauth",
        "api-key",
        "sandbox",
        "mcp-client",
        "yc"
      ],
      "lastRelease": "2026-10-19",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 48.6,
        "grade": "D",
        "agentReady": false,
        "rank": 1202,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 52,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 79,
          "maintenance": 25,
          "payments": 15,
          "reliability": 35,
          "schema": 84,
          "security": 41,
          "transparency": 44
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Click's API is described by a public OpenAPI 3.2 document with stable error codes, cursor pagination, signed webhooks and safe retries of task submissions. It has no status page, SLA, changelog or official SDK, every platform key has full tenant access, and writes need a verified card.",
        "bestFor": "Product teams that want to embed an agent per customer, ticket or document without running the loop, sandbox or browser themselves, with any model.",
        "strengths": [
          "Public OpenAPI 3.2 document, llms.txt, llms-full.txt and a Markdown page per operation",
          "Errors return `{error: {code, message}}` with stable codes listed by status, and 503 codes say to retry after a short wait",
          "A `request_id` makes task submissions safe to retry",
          "Signed webhooks with at-least-once delivery, retried for 24 hours, and a deliveries endpoint to check them",
          "Any model through the user's own provider keys, and the user's own MCP servers or HTTP endpoints as tools"
        ],
        "weaknesses": [
          "No status page, SLA or public changelog found",
          "Every platform API key has full access to its tenant, including key management",
          "Writes need a card verified in the dashboard, so even the free plan has no card-free start",
          "No official SDK. The docs give curl and a standard-library Python example",
          "The privacy statement lets staff access service content for support and to improve the service, with no retention periods"
        ],
        "agentNotes": [
          "Send a unique `request_id` with each submission and reuse it when you retry, so a task doesn't run twice",
          "Branch on `error.code`, not the message. Retry 503 codes after a short wait",
          "If you get `429 concurrency_limit_exceeded`, put an idle session in standby to free its slot",
          "Read a submission until it is `done`, `cancelled` or `failed`, then fetch the answer entry it names",
          "Grant each agent only the tools it needs. Approvals and budgets are left to your application"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 48.6
          }
        ],
        "editorialScores": {
          "ergonomics": 79,
          "maintenance": 25,
          "payments": 15,
          "reliability": 35,
          "schema": 84,
          "security": 41,
          "transparency": 33
        },
        "provenanceScore": 54,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl https://api.useclick.ai/v1/models -H \"Authorization: Bearer $CLICK_API_KEY\""
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/click-agents"
      },
      "area": "frameworks",
      "unitPrices": [
        {
          "item": "Pro plan",
          "unit": "month",
          "usd": 199,
          "note": "50 concurrent sessions, 100 managed sandbox and browser hours, 5,000 web searches"
        }
      ],
      "provenance": {
        "legalEntity": "Click AI Labs, Inc.",
        "domain": "useclick.ai",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://useclick.ai/terms",
        "privacy": "https://useclick.ai/privacy",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-11-18",
        "notes": [
          "The terms and the privacy statement, both last updated 12 October 2026, name Click AI Labs, Inc., Delaware law and a notice address at 131 Continental Dr, Suite 305, Newark, DE 19713.",
          "useclick.ai robots.txt allowed every page read on 18 November 2026.",
          "/.well-known/security.txt returned 404. No status page or changelog is linked from the site or the docs.",
          "The domain's registration date wasn't looked up."
        ],
        "score": 54
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/click-agents.json",
      "live": {
        "slug": "click-agents",
        "probe": {
          "target": "https://api.useclick.ai/v1",
          "method": "get",
          "lastAt": "2026-11-18T22:43:14.601398915Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 334,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 391,
          "p95ms24h": 473,
          "samples24h": 11,
          "samples30d": 11,
          "days": [
            {
              "date": "2026-11-18",
              "probes": 11,
              "ok": 11
            }
          ],
          "since": "2026-11-18T21:37:48.848215896Z"
        },
        "updatedAt": "2026-11-18T22:43:14.601398915Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "sinceWatching": true,
        "best": 0
      }
    },
    "answer": "Click scores 48.6 (D) on agent readiness against Harness²'s 45 (E), and leads in 4 of 7 scored categories. Harness² leads on security \u0026 auth, payments \u0026 pricing and transparency \u0026 trust.",
    "b": {
      "slug": "harness2",
      "name": "Harness²",
      "vendor": "Google (Google Research)",
      "vendorUrl": "https://harness2.github.io",
      "company": "google.com",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Harness² is Google Research's open-source Python framework that has an editor model rewrite an agent's harness (prompts, guardrails, memory, tools, skills, subagents, scripts and plugins) for each task and keeps lessons for later tasks, with model weights fixed.",
      "url": "https://www.anchorterminal.com/tools/harness2",
      "markdownUrl": "https://www.anchorterminal.com/tools/harness2.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/harness2.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/harness2.json",
      "dns": "harness2.grade.anchorterminal.com",
      "repo": "https://github.com/google-research/harness2",
      "license": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).",
      "transports": [],
      "packages": [],
      "auth": "none",
      "authNotes": "No Harness² account or key. Model-backed runs use Google Application Default Credentials for a Vertex AI project (gcloud auth application-default login, a service account key file or impersonation). The optional Codex bridge generates its own local access key.",
      "pricing": "free",
      "pricingNotes": "Free under Apache-2.0, with nothing to buy. Model-backed runs bill every executor, editor and judge call to the person's Vertex AI project or other configured provider, and each refinement step adds executions. The local demo needs no credentials.",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the README, docs or source (checked 2026-10-18). The software has nothing to buy.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-10"
      },
      "docsUrl": "https://github.com/google-research/harness2/tree/main/docs",
      "capabilities": [
        "agent.harness"
      ],
      "tags": [
        "open-source",
        "apache-2.0",
        "local",
        "self-hosted",
        "free",
        "python",
        "cli",
        "linux"
      ],
      "lastRelease": "2026-10-08",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 45,
        "grade": "E",
        "agentReady": false,
        "rank": 1287,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 54,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 59,
          "maintenance": 13,
          "payments": 60,
          "reliability": 25,
          "schema": 54,
          "security": 50,
          "transparency": 49
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-10"
        },
        "negative": 0,
        "verdict": "Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.",
        "bestFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.",
        "strengths": [
          "Refining a harness needs no grader, rubric or answer key. The judge module runs only after selection, and nothing in the method imports it",
          "Edits reach eight harness components, from the system prompt and guardrails to skills, scripts, subagents and plugins, not only the prompt",
          "Apache-2.0, with upstream checkouts pinned by commit, a hash list for bundled files and each third-party runner's licence and provenance",
          "Rerunning a command resumes it, failed grades stay unscored rather than zero, and `--dry-run` previews task selection without model calls",
          "Each editor session's prompt, response, model and cost are written to an audit folder beside the run",
          "Since 1 November agent subprocesses no longer inherit host API keys and tokens, and .env is ignored by git"
        ],
        "weaknesses": [
          "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI",
          "The CLI accepts only JobBench, LAB and WorkBuddy-Bench, with no documented way to run it on your own tasks",
          "Executor network access is unrestricted, and Codex runs with approvals and sandbox bypassed",
          "No CI, and the 17 fixes merged on 1 and 2 November carry no version or changelog entry"
        ],
        "agentNotes": [
          "Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only",
          "Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`",
          "Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched",
          "Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up",
          "Copy `.env.example` to `.env` and fill GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL; pull main first, since the file and the credential scrubbing arrived on 1 November"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 2.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "E",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 45
          }
        ],
        "editorialScores": {
          "ergonomics": 59,
          "maintenance": 13,
          "payments": 60,
          "reliability": 25,
          "schema": 54,
          "security": 50,
          "transparency": 48
        },
        "provenanceScore": 50,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-10",
            "maintenance": "2026-11-10",
            "payments": "2026-11-10",
            "reliability": "2026-11-10",
            "schema": "2026-11-10",
            "security": "2026-11-10",
            "transparency": "2026-11-10"
          },
          "last": "2026-11-10",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-10",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "git clone https://github.com/google-research/harness2.git \u0026\u0026 cd harness2 \u0026\u0026 uv venv --python 3.12 .venv \u0026\u0026 source .venv/bin/activate \u0026\u0026 uv pip install -e '.[render]' \u0026\u0026 harness2-demo --output runs/demo --k 2",
        "headless": {
          "command": "harness2-setup lab \u0026\u0026 harness2-check --bench lab \u0026\u0026 harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1",
          "env": {
            "GOOGLE_CLOUD_PROJECT": "\u003cyour-vertex-project\u003e",
            "HARNESS2_JUDGE_MODEL": "\u003cmodel-id\u003e",
            "HARNESS2_SOLVER_MODEL": "\u003cprovider/model\u003e"
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/harness2"
      },
      "sameCompany": [
        "gemini-4-carbon",
        "gemini-4-hydrogen",
        "gemini-api",
        "vertex-ai",
        "embeddinggemma-2",
        "embeddinggemma-300m",
        "gemini-embedding",
        "vertex-ai-tuning",
        "cloud-run-gpus",
        "google-model-armor",
        "shieldgemma",
        "google-imagen",
        "gemini-omni-1-2-flash",
        "google-veo",
        "google-lyria",
        "google-speech-to-text",
        "google-cloud-tts",
        "gemini-live",
        "google-adk",
        "google-memory-bank",
        "google-secret-manager",
        "google-cloud-document-ai",
        "google-weather-api",
        "chrome-devtools-mcp",
        "puppeteer",
        "mcp-toolbox-databases",
        "google-maps-platform",
        "google-cloud-translation",
        "google-calendar-api",
        "firebase-cloud-messaging",
        "google-cloud-storage",
        "google-drive-api",
        "gemini-enterprise",
        "gemini-decision-1",
        "antigravity-cli",
        "gemini-cli",
        "jules",
        "gemini-spark",
        "google-search-console",
        "google-ads-api",
        "google-forms",
        "google-sheets-api",
        "gmail-api",
        "google-people-api",
        "diffusiongemma-26b-a4b-it",
        "gemma-4-12b-it",
        "gemma-4-26b-a4b-it",
        "gemma-4-31b-it",
        "gemma-4-e2b-it",
        "gemma-4-e4b-it",
        "virustotal"
      ],
      "area": "frameworks",
      "provenance": {
        "legalEntity": "Google LLC",
        "domain": "harness2.github.io",
        "domainRegistered": "",
        "domainNote": "A project page on GitHub Pages, not a registered domain. The code is in the google-research organisation on GitHub.",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-10-18",
        "notes": [
          "LICENSE is Apache-2.0, and pyproject.toml and every source file name Google LLC. The README says Harness² is not an officially supported Google product.",
          "No terms or privacy policy govern the package or the project page. Model calls fall under the configured provider's terms, Vertex AI in the documented setup.",
          "The repository has no SECURITY.md, and harness2.github.io/.well-known/security.txt returns 404. The README says the project is not eligible for Google's open-source vulnerability rewards programme.",
          "No changelog, tags or GitHub releases. The version is 0.1.0 in pyproject.toml.",
          "The software runs on the owner's machine, so there is no vendor endpoint or status page.",
          "The project page has no robots.txt and carries a noindex, nofollow robots meta tag. It was read once as a public page."
        ],
        "score": 50
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/harness2.json",
      "live": {
        "slug": "harness2",
        "githubStars": 24387,
        "securityTxt": {
          "url": "https://harness2.github.io/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-18T16:31:34.606414607Z"
        },
        "domain": {
          "domain": "github.io",
          "checkedAt": "2026-11-15T15:33:10.142575318Z"
        },
        "github": {
          "repo": "google-research/harness2",
          "checkedAt": "2026-11-16T12:04:18.15487168Z",
          "stars": 24059,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-02T02:17:27Z",
          "openIssues": 43,
          "openPRs": 128,
          "issuesOpened90d": 50,
          "issuesClosed90d": 7,
          "prsMerged90d": 17,
          "replies": {
            "sampled": 25,
            "unanswered": 21,
            "medianDays": 6.1
          }
        },
        "updatedAt": "2026-11-18T17:54:29.318055304Z"
      }
    },
    "edges": [
      {
        "by": 45,
        "category": "payments",
        "leads": "harness2",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402, MPP or L402. The only 402 is `card_verification_required` (0). Plan prices are public, Free at $0 and Pro at $199 a month with stated allowances, but no per-unit price (15). The Free plan exists, but writes return 402 until a card is verified in the dashboard (0). A person signs up in a browser, verifies a card and creates the key (0). 0 + 15 + 0 + 0 = 15.",
          "b": "No payment protocol (0). Read with the self-hosted rule, as for the other harnesses. Free under Apache-2.0 with nothing to buy (20). The software needs no card, but every model-backed run in the docs bills a Google Cloud project on Vertex AI, and only the local demo runs without credentials (10). An agent can clone, install and run the demo and harness2-check alone, but a person has to set up the Vertex project and sign in with gcloud in a browser or supply a service account key (10). 0 + 20 + 10 + 10 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60."
        },
        "scores": {
          "a": 15,
          "b": 60
        }
      },
      {
        "by": 30,
        "category": "schema",
        "leads": "click-agents",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "A public OpenAPI 3.2 document at useclick.ai/reference/openapi.yaml, API version 2026-10-19, rendered in full in llms-full.txt with 49 operations (25). llms.txt, llms-full.txt and a Markdown page per operation (10). The introduction says when to use Click, what Click runs and what the application owns, and each area explains its lifecycle (17 of 20). Typed schemas with 557 required-field markers in llms-full.txt and enumerated statuses, and string and body limits stated (12 of 15). A quick start with curl, a runnable Python example, and every operation lists its error codes by status (15). Paths are under `/v1` with a dated API version, but no public changelog was found (5 of 15). 25 + 10 + 17 + 12 + 15 + 5 = 84.",
          "b": "Framework reading. Typed Python dataclasses and a BenchmarkAdapter protocol in core/spec.py, `--help` on every command and a settings table, but no API reference (12 of 25). Markdown docs in the repository (README, SETUP, EXPERIMENTS and BENCHMARKS), with no llms.txt (5 of 10). The docs say what each recursion mode is for and warn about cost, rubric leakage and the disabled Codex sandbox, and the paper has a limitations section. Nothing says how to use it outside the three benchmarks (13 of 20). `--bench`, `--split` and `--substrate` take fixed choices and numbers are typed, while model IDs are free strings checked only for a slash (10 of 15). Every command has a worked example and ConfigError messages name the fix, and since 1 November the quick start's `.env.example` ships, with a test that checks it (11 of 15). Version 0.1.0 with no changelog (3 of 15). 12 + 5 + 13 + 10 + 11 + 3 = 54."
        },
        "scores": {
          "a": 84,
          "b": 54
        }
      },
      {
        "by": 20,
        "category": "ergonomics",
        "leads": "click-agents",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Entries can be read by `min_entry_id` and `max_entry_id`, `get_state` returns one snapshot, and lists take `limit`, so responses stay small (20 of 25). Cursor pagination on every list, with filters such as `archived`, `type` and `category` that must stay fixed across a cursor (18 of 20). Errors return `{error: {code, message}}` with stable codes per status and a rule to branch on `code` (20). `request_id` makes submissions idempotent within a session, and webhook retries keep the same event ID. Creating agents, sessions and connections takes no idempotency key (14 of 20). Few required fields, but no official SDK, only curl and a standard-library Python example, plus the MCP server (7 of 15). 20 + 18 + 20 + 14 + 7 = 79.",
          "b": "Framework reading, adapted to a harness that a pipeline drives. Results land in run folders, not in the caller's context, and an agent reads task summaries, adopted harnesses and reflection notes from runs/ (12 of 25). `--only-domains`, `--max-tasks` (per domain), `--split-file`, `--workers` and `--dry-run` size a run before any model call (14 of 20). harness2-check tests dependencies, credentials and configuration without a model call, configuration errors name the remedy, and incomplete runs exit nonzero (14 of 20). Rerunning a command resumes it, saved configuration refuses an incompatible resume, failed grades stay unscored, and editor replies are cached by a fingerprint of their inputs (15 of 20). No model has a default, a Vertex AI project and a gcloud sign-in are needed, only three benchmarks are accepted and there's no SDK (4 of 15). 59 in all."
        },
        "scores": {
          "a": 79,
          "b": 59
        }
      },
      {
        "by": 12,
        "category": "maintenance",
        "leads": "click-agents",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Closed service with no dated changelog. The newest first-hand date is API version 2026-10-19, 30 days before this check, read as within 90 days rather than within 30 since nothing says what shipped then (20). No dated release entries to count (0). Support is by email to the founder, per the terms. No public changelog, issue tracker or community channel was found (5 of 15). No official SDK (0). No public package or CI to check (0). 20 + 0 + 5 + 0 + 0 = 25.",
          "b": "Version 0.1.0 has been in pyproject.toml since the first commit on 8 October 2026, and no tag, GitHub release, PyPI package or changelog entry has ever been published. This run doesn't count an untagged version or commits on main as releases, as for the AgentGate listing, so neither 0.1.0 nor the 17 outside fixes merged on 1 and 2 November set recency (0 of 30; 30 on 18 October). No tags, releases or dated changelog entries (0). Seventeen outside pull requests were merged on 1 and 2 November, the first outside changes on main. Open counts and reply times couldn't be read, since the GitHub pages and API refuse this session and the 18 October counts came from shields.io (struck) (10 of 25). Not on PyPI and no SDK (0). No CI. Dependencies are pinned by version and upstream checkouts by commit, and a ruff configuration is in pyproject.toml (3 of 10). 0 + 0 + 10 + 0 + 3 = 13."
        },
        "scores": {
          "a": 25,
          "b": 13
        }
      },
      {
        "by": 10,
        "category": "reliability",
        "leads": "click-agents",
        "name": "Reliability",
        "reasons": {
          "a": "Hosted lines, for the HTTP API. No status page is linked from the site or the docs (0), so no incident history could be read (5). Concurrent session limits are published per plan (2 on Free, 50 on Pro) with body size limits of 16 MiB, but no request rate limits were found (8 of 15). `429 concurrency_limit_exceeded` and the 503 codes are documented, the conventions say to retry 503 after a short wait, and `request_id` makes submissions safe to retry. No `Retry-After` header is documented (12 of 15). No SLA in the terms, which leave usage limits to Click's discretion (0). The API carries no beta or preview label (10). 0 + 5 + 8 + 12 + 0 + 10 = 35.",
          "b": "Local-package reading. Not on PyPI (the release feed for harness2 answered 404 on 18 October). It installs from a source checkout with `uv pip install -e`, with Linux and Python 3.12 stated (the package allows 3.13), plus Node.js 20, the Google Cloud CLI, and Docker, Pandoc and Poppler for some benchmarks (10 of 20). Still no CI workflow in the repository on 10 November. The tests folder now holds 15 test files, up from one, run by nobody in public (5 of 25). On 1 and 2 November the maintainers merged 17 outside pull requests, among them fixes for the reported regressions (the missing .env.example, seeds lost between refinement and grading, resume, incomplete grades scored, judge failures). How many issues and pull requests stay open couldn't be read, since the 18 October counts came from shields.io and are struck (10 of 25). No tags or changelog (0). Version 0.1.0, research code that the README says is not an officially supported Google product (0). 10 + 5 + 10 + 0 + 0 = 25."
        },
        "scores": {
          "a": 35,
          "b": 25
        }
      },
      {
        "by": 9,
        "category": "security",
        "leads": "harness2",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Platform API keys are revocable, but each has full access to its tenant, including key management. The MCP server's OAuth tokens through WorkOS carry scopes for the MCP endpoint only (20 of 30). Tool grants limit each agent to named tools, and sessions can override grants, but approvals are left to the customer's application and no read-only key was found (8 of 20). Agents read web pages, browser content and MCP results. The docs tell users to keep secrets out of messages and keep MCP tools from returning stored secrets, but give no prompt-injection guidance (3 of 15). Every top-level and nested tool call is recorded and listed per session, and webhook deliveries can be listed (10 of 15). No security.txt (404), disclosure policy or certification found (0). 20 + 8 + 3 + 10 + 0 = 41.",
          "b": "Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture and network egress, 15 for audit and 20 for the security programme. No telemetry found in the Harness² source, and the WorkBuddy OpenCode configs turn OpenCode's telemetry, auto-update and sharing off. Credentials are Google Application Default Credentials, and the Codex bridge binds 127.0.0.1 by default with a generated key stored with mode 0600. Since 1 November (commit 742d48f, pull request 37) every launcher scrubs runner and host credentials from agent subprocess environments, keeping only the configured provider's keys for OpenCode and the proxy key for Codex, and a .gitignore now keeps .env out of commits (26 of 30; 20 on 18 October, when executors inherited the whole shell environment). The fix is on main with no tag, which is what the README's install uses. Codex runs with `--dangerously-bypass-approvals-and-sandbox`, the Claude CLI editor channel with `--dangerously-skip-permissions`, and the WorkBuddy OpenCode preset allows every tool, with only OpenCode's directory fence and WorkBuddy's containers as limits. The README and setup guide say so (4). Executor network access is unrestricted by default. The docs name the hosts to block and report a Codex rollout that fetched its rubric unprompted, but give no guidance on instructions inside task documents (5). Each editor call's prompt, system text, response, model and cost are saved to an audit folder, with trajectories and adopted harnesses under runs/ (13). No SECURITY.md or security.txt and no advisories, and the README says the project is outside Google's open-source vulnerability rewards programme (2). 26 + 4 + 5 + 13 + 2 = 50."
        },
        "scores": {
          "a": 41,
          "b": 50
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "Agent harness",
        "name": "Kind"
      },
      {
        "a": "Click AI Labs, Inc.",
        "b": "Google (Google Research)",
        "name": "Vendor"
      },
      {
        "a": "https://api.useclick.ai/v1",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP, Streamable HTTP",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary hosted service under Click's Terms of Service, based on the Common Paper Cloud Service Agreement 2.1",
        "b": "Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).",
        "name": "Licence"
      },
      {
        "a": "23",
        "b": "none",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-19",
        "b": "2026-10-08",
        "name": "Last release"
      },
      {
        "a": "2026-10-12",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "2026-10-12",
        "b": "no document linked",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "2.5/5 (4)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Click scores 48.6 (D) on agent readiness against Harness²'s 45 (E), and leads in 4 of 7 scored categories. Harness² leads on security \u0026 auth, payments \u0026 pricing and transparency \u0026 trust.",
        "question": "Which is better for AI agents, Click or Harness²?"
      },
      {
        "answer": "Click has a hosted endpoint at https://api.useclick.ai/v1. No hosted endpoint is listed for Harness².",
        "question": "Can an agent call Click and Harness² without installing anything?"
      },
      {
        "answer": "No open-source release is listed for Click. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).).",
        "question": "Are Click and Harness² open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 35 against 25",
          "Schema \u0026 documentation, 84 against 54",
          "Agent ergonomics, 79 against 59",
          "Maintenance \u0026 community, 25 against 13"
        ],
        "also": [
          "A hosted endpoint, with nothing to install"
        ],
        "goodFor": "Product teams that want to embed an agent per customer, ticket or document without running the loop, sandbox or browser themselves, with any model.",
        "slug": "click-agents",
        "watchFor": "No status page, SLA or public changelog found"
      },
      {
        "aheadOn": [
          "Security \u0026 auth, 50 against 41",
          "Payments \u0026 pricing, 60 against 15",
          "Transparency \u0026 trust, 49 against 44"
        ],
        "also": [
          "No key needed to call it",
          "Open source"
        ],
        "goodFor": "Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.",
        "slug": "harness2",
        "watchFor": "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI"
      }
    ],
    "history": {
      "click-agents": null,
      "harness2": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 2.5,
          "from": 42.5,
          "fromGrade": "E",
          "to": 45,
          "toGrade": "E"
        },
        {
          "causes": [
            "product",
            "correction"
          ],
          "date": "2026-11-10",
          "delta": 0.5,
          "from": 42,
          "fromGrade": "E",
          "to": 42.5,
          "toGrade": "E"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-27",
          "delta": 0.4,
          "from": 41.6,
          "fromGrade": "E",
          "to": 42,
          "toGrade": "E"
        }
      ]
    },
    "job": {
      "capability": "agent.harness",
      "name": "Agent harnesses"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-click-agents.json",
        "title": "Agent Zero vs Click",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2.json",
        "title": "Agent Zero vs Harness²",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/aider-vs-click-agents.json",
        "title": "Aider vs Click",
        "url": "https://www.anchorterminal.com/compare/aider-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/aider-vs-harness2.json",
        "title": "Aider vs Harness²",
        "url": "https://www.anchorterminal.com/compare/aider-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-click-agents.json",
        "title": "Amp vs Click",
        "url": "https://www.anchorterminal.com/compare/amp-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-harness2.json",
        "title": "Amp vs Harness²",
        "url": "https://www.anchorterminal.com/compare/amp-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-click-agents.json",
        "title": "Antigravity CLI vs Click",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.json",
        "title": "Antigravity CLI vs Harness²",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-click-agents.json",
        "title": "Auggie CLI vs Click",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-harness2.json",
        "title": "Auggie CLI vs Harness²",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-click-agents.json",
        "title": "AXLR vs Click",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-harness2.json",
        "title": "AXLR vs Harness²",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents.json",
        "title": "boxes.dev vs Click",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness2.json",
        "title": "boxes.dev vs Harness²",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-code-vs-click-agents.json",
        "title": "Claude Code vs Click",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-code-vs-harness2.json",
        "title": "Claude Code vs Harness²",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-cline.json",
        "title": "Click vs Cline",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-cline"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-conductor.json",
        "title": "Click vs Conductor",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-conductor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-crush.json",
        "title": "Click vs Crush",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-cursor-cli.json",
        "title": "Click vs Cursor CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-cursor-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-deepseek-harness.json",
        "title": "Click vs DeepSeek Harness (dsh)",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-deepseek-harness"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-deepseek-superagent.json",
        "title": "Click vs dsh-superagent (DeepSeek)",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-deepseek-superagent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-devin.json",
        "title": "Click vs Devin",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-devin"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-droid-cli.json",
        "title": "Click vs Droid CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-droid-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-earendil-pi.json",
        "title": "Click vs Pi",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-earendil-pi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-emdash.json",
        "title": "Click vs Emdash",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-emdash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-friday-work.json",
        "title": "Click vs Friday",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-friday-work"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-gemini-cli.json",
        "title": "Click vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-github-copilot-cli.json",
        "title": "Click vs GitHub Copilot CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-github-copilot-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-goose.json",
        "title": "Click vs goose",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-goose"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-harnessrouter.json",
        "title": "Click vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-jules.json",
        "title": "Click vs Jules",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-junie.json",
        "title": "Click vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-kilo-code-cli.json",
        "title": "Click vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-kimi-code-cli.json",
        "title": "Click vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-kiro-cli.json",
        "title": "Click vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-letta.json",
        "title": "Click vs Letta",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-mini-swe-agent.json",
        "title": "Click vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-minimax-code.json",
        "title": "Click vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-mistral-vibe-cli.json",
        "title": "Click vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-muse-code.json",
        "title": "Click vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-openai-agents-api.json",
        "title": "Click vs OpenAI Agents API",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-openai-agents-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-openai-codex.json",
        "title": "Click vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-openai-codex"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-opencode.json",
        "title": "Click vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-openhands.json",
        "title": "Click vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-openmausbot.json",
        "title": "Click vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-orca.json",
        "title": "Click vs Orca",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-paseo.json",
        "title": "Click vs Paseo",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-prime-agent.json",
        "title": "Click vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-qoder-cli.json",
        "title": "Click vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-qwen-code.json",
        "title": "Click vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-reflection-mirror.json",
        "title": "Click vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-rovo-dev-cli.json",
        "title": "Click vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-sculptor.json",
        "title": "Click vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-t3-code.json",
        "title": "Click vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-traycer.json",
        "title": "Click vs Traycer",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-unstoppable.json",
        "title": "Click vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-verdent.json",
        "title": "Click vs Verdent",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-vibe-trading.json",
        "title": "Click vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-warp.json",
        "title": "Click vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-harness2.json",
        "title": "Cline vs Harness²",
        "url": "https://www.anchorterminal.com/compare/cline-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/conductor-vs-harness2.json",
        "title": "Conductor vs Harness²",
        "url": "https://www.anchorterminal.com/compare/conductor-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-harness2.json",
        "title": "Crush vs Harness²",
        "url": "https://www.anchorterminal.com/compare/crush-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.json",
        "title": "Cursor CLI vs Harness²",
        "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.json",
        "title": "DeepSeek Harness (dsh) vs Harness²",
        "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.json",
        "title": "dsh-superagent (DeepSeek) vs Harness²",
        "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/devin-vs-harness2.json",
        "title": "Devin vs Harness²",
        "url": "https://www.anchorterminal.com/compare/devin-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2.json",
        "title": "Droid CLI vs Harness²",
        "url": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.json",
        "title": "Pi vs Harness²",
        "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/emdash-vs-harness2.json",
        "title": "Emdash vs Harness²",
        "url": "https://www.anchorterminal.com/compare/emdash-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-harness2.json",
        "title": "Friday vs Harness²",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.json",
        "title": "Gemini CLI vs Harness²",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.json",
        "title": "GitHub Copilot CLI vs Harness²",
        "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/goose-vs-harness2.json",
        "title": "goose vs Harness²",
        "url": "https://www.anchorterminal.com/compare/goose-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.json",
        "title": "Harness² vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-jules.json",
        "title": "Harness² vs Jules",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-junie.json",
        "title": "Harness² vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.json",
        "title": "Harness² vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-kimi-code-cli.json",
        "title": "Harness² vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.json",
        "title": "Harness² vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-letta.json",
        "title": "Harness² vs Letta",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.json",
        "title": "Harness² vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-minimax-code.json",
        "title": "Harness² vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli.json",
        "title": "Harness² vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-muse-code.json",
        "title": "Harness² vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api.json",
        "title": "Harness² vs OpenAI Agents API",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex.json",
        "title": "Harness² vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-opencode.json",
        "title": "Harness² vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-openhands.json",
        "title": "Harness² vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-openmausbot.json",
        "title": "Harness² vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-orca.json",
        "title": "Harness² vs Orca",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-paseo.json",
        "title": "Harness² vs Paseo",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent.json",
        "title": "Harness² vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-qoder-cli.json",
        "title": "Harness² vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code.json",
        "title": "Harness² vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.json",
        "title": "Harness² vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli.json",
        "title": "Harness² vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-sculptor.json",
        "title": "Harness² vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-t3-code.json",
        "title": "Harness² vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-traycer.json",
        "title": "Harness² vs Traycer",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-unstoppable.json",
        "title": "Harness² vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-verdent.json",
        "title": "Harness² vs Verdent",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-vibe-trading.json",
        "title": "Harness² vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-warp.json",
        "title": "Harness² vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-warp"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 10,
        "click-agents": 35,
        "edge": "click-agents",
        "harness2": 25,
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 30,
        "click-agents": 84,
        "edge": "click-agents",
        "harness2": 54,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 20,
        "click-agents": 79,
        "edge": "click-agents",
        "harness2": 59,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 9,
        "click-agents": 41,
        "edge": "harness2",
        "harness2": 50,
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 45,
        "click-agents": 15,
        "edge": "harness2",
        "harness2": 60,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 12,
        "click-agents": 25,
        "edge": "click-agents",
        "harness2": 13,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 5,
        "click-agents": 44,
        "edge": "harness2",
        "harness2": 49,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Click scores 48.6 (D) on agent readiness against Harness²'s 45 (E), and leads in 4 of 7 scored categories. Harness² leads on security \u0026 auth, payments \u0026 pricing and transparency \u0026 trust. Both do agent harnesses.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "click-agents": "Click's API is described by a public OpenAPI 3.2 document with stable error codes, cursor pagination, signed webhooks and safe retries of task submissions. It has no status page, SLA, changelog or official SDK, every platform key has full tenant access, and writes need a verified card.",
      "harness2": "Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/click-agents-vs-harness2",
    "json": "https://www.anchorterminal.com/compare/click-agents-vs-harness2.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/click-agents-vs-harness2.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/click-agents-vs-harness2.min.md"
  },
  "markdown": "Click scores 48.6 (D) on agent readiness against Harness²'s 45 (E), and leads in 4 of 7 scored categories. Harness² leads on security \u0026 auth, payments \u0026 pricing and transparency \u0026 trust. Both do agent harnesses.\n\n- Click: grade D, 48.6/100, rank #1202 of 1557. Markdown https://www.anchorterminal.com/tools/click-agents.md · JSON https://www.anchorterminal.com/api/v1/tools/click-agents.json\n- Harness²: grade E, 45/100, rank #1287 of 1557. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1767 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Click (D)\n\nGood for: Product teams that want to embed an agent per customer, ticket or document without running the loop, sandbox or browser themselves, with any model.\n\nAhead on:\n- Reliability, 35 against 25\n- Schema \u0026 documentation, 84 against 54\n- Agent ergonomics, 79 against 59\n- Maintenance \u0026 community, 25 against 13\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: No status page, SLA or public changelog found\n\n### Harness² (E)\n\nGood for: Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI.\n\nAhead on:\n- Security \u0026 auth, 50 against 41\n- Payments \u0026 pricing, 60 against 15\n- Transparency \u0026 trust, 49 against 44\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Harness² +45\n\n- Click (15): No x402, MPP or L402. The only 402 is `card_verification_required` (0). Plan prices are public, Free at $0 and Pro at $199 a month with stated allowances, but no per-unit price (15). The Free plan exists, but writes return 402 until a card is verified in the dashboard (0). A person signs up in a browser, verifies a card and creates the key (0). 0 + 15 + 0 + 0 = 15.\n- Harness² (60): No payment protocol (0). Read with the self-hosted rule, as for the other harnesses. Free under Apache-2.0 with nothing to buy (20). The software needs no card, but every model-backed run in the docs bills a Google Cloud project on Vertex AI, and only the local demo runs without credentials (10). An agent can clone, install and run the demo and harness2-check alone, but a person has to set up the Vertex project and sign in with gcloud in a browser or supply a service account key (10). 0 + 20 + 10 + 10 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.\n\n### Schema \u0026 documentation: Click +30\n\n- Click (84): A public OpenAPI 3.2 document at useclick.ai/reference/openapi.yaml, API version 2026-10-19, rendered in full in llms-full.txt with 49 operations (25). llms.txt, llms-full.txt and a Markdown page per operation (10). The introduction says when to use Click, what Click runs and what the application owns, and each area explains its lifecycle (17 of 20). Typed schemas with 557 required-field markers in llms-full.txt and enumerated statuses, and string and body limits stated (12 of 15). A quick start with curl, a runnable Python example, and every operation lists its error codes by status (15). Paths are under `/v1` with a dated API version, but no public changelog was found (5 of 15). 25 + 10 + 17 + 12 + 15 + 5 = 84.\n- Harness² (54): Framework reading. Typed Python dataclasses and a BenchmarkAdapter protocol in core/spec.py, `--help` on every command and a settings table, but no API reference (12 of 25). Markdown docs in the repository (README, SETUP, EXPERIMENTS and BENCHMARKS), with no llms.txt (5 of 10). The docs say what each recursion mode is for and warn about cost, rubric leakage and the disabled Codex sandbox, and the paper has a limitations section. Nothing says how to use it outside the three benchmarks (13 of 20). `--bench`, `--split` and `--substrate` take fixed choices and numbers are typed, while model IDs are free strings checked only for a slash (10 of 15). Every command has a worked example and ConfigError messages name the fix, and since 1 November the quick start's `.env.example` ships, with a test that checks it (11 of 15). Version 0.1.0 with no changelog (3 of 15). 12 + 5 + 13 + 10 + 11 + 3 = 54.\n\n### Agent ergonomics: Click +20\n\n- Click (79): Entries can be read by `min_entry_id` and `max_entry_id`, `get_state` returns one snapshot, and lists take `limit`, so responses stay small (20 of 25). Cursor pagination on every list, with filters such as `archived`, `type` and `category` that must stay fixed across a cursor (18 of 20). Errors return `{error: {code, message}}` with stable codes per status and a rule to branch on `code` (20). `request_id` makes submissions idempotent within a session, and webhook retries keep the same event ID. Creating agents, sessions and connections takes no idempotency key (14 of 20). Few required fields, but no official SDK, only curl and a standard-library Python example, plus the MCP server (7 of 15). 20 + 18 + 20 + 14 + 7 = 79.\n- Harness² (59): Framework reading, adapted to a harness that a pipeline drives. Results land in run folders, not in the caller's context, and an agent reads task summaries, adopted harnesses and reflection notes from runs/ (12 of 25). `--only-domains`, `--max-tasks` (per domain), `--split-file`, `--workers` and `--dry-run` size a run before any model call (14 of 20). harness2-check tests dependencies, credentials and configuration without a model call, configuration errors name the remedy, and incomplete runs exit nonzero (14 of 20). Rerunning a command resumes it, saved configuration refuses an incompatible resume, failed grades stay unscored, and editor replies are cached by a fingerprint of their inputs (15 of 20). No model has a default, a Vertex AI project and a gcloud sign-in are needed, only three benchmarks are accepted and there's no SDK (4 of 15). 59 in all.\n\n### Maintenance \u0026 community: Click +12\n\n- Click (25): Closed service with no dated changelog. The newest first-hand date is API version 2026-10-19, 30 days before this check, read as within 90 days rather than within 30 since nothing says what shipped then (20). No dated release entries to count (0). Support is by email to the founder, per the terms. No public changelog, issue tracker or community channel was found (5 of 15). No official SDK (0). No public package or CI to check (0). 20 + 0 + 5 + 0 + 0 = 25.\n- Harness² (13): Version 0.1.0 has been in pyproject.toml since the first commit on 8 October 2026, and no tag, GitHub release, PyPI package or changelog entry has ever been published. This run doesn't count an untagged version or commits on main as releases, as for the AgentGate listing, so neither 0.1.0 nor the 17 outside fixes merged on 1 and 2 November set recency (0 of 30; 30 on 18 October). No tags, releases or dated changelog entries (0). Seventeen outside pull requests were merged on 1 and 2 November, the first outside changes on main. Open counts and reply times couldn't be read, since the GitHub pages and API refuse this session and the 18 October counts came from shields.io (struck) (10 of 25). Not on PyPI and no SDK (0). No CI. Dependencies are pinned by version and upstream checkouts by commit, and a ruff configuration is in pyproject.toml (3 of 10). 0 + 0 + 10 + 0 + 3 = 13.\n\n### Reliability: Click +10\n\n- Click (35): Hosted lines, for the HTTP API. No status page is linked from the site or the docs (0), so no incident history could be read (5). Concurrent session limits are published per plan (2 on Free, 50 on Pro) with body size limits of 16 MiB, but no request rate limits were found (8 of 15). `429 concurrency_limit_exceeded` and the 503 codes are documented, the conventions say to retry 503 after a short wait, and `request_id` makes submissions safe to retry. No `Retry-After` header is documented (12 of 15). No SLA in the terms, which leave usage limits to Click's discretion (0). The API carries no beta or preview label (10). 0 + 5 + 8 + 12 + 0 + 10 = 35.\n- Harness² (25): Local-package reading. Not on PyPI (the release feed for harness2 answered 404 on 18 October). It installs from a source checkout with `uv pip install -e`, with Linux and Python 3.12 stated (the package allows 3.13), plus Node.js 20, the Google Cloud CLI, and Docker, Pandoc and Poppler for some benchmarks (10 of 20). Still no CI workflow in the repository on 10 November. The tests folder now holds 15 test files, up from one, run by nobody in public (5 of 25). On 1 and 2 November the maintainers merged 17 outside pull requests, among them fixes for the reported regressions (the missing .env.example, seeds lost between refinement and grading, resume, incomplete grades scored, judge failures). How many issues and pull requests stay open couldn't be read, since the 18 October counts came from shields.io and are struck (10 of 25). No tags or changelog (0). Version 0.1.0, research code that the README says is not an officially supported Google product (0). 10 + 5 + 10 + 0 + 0 = 25.\n\n### Security \u0026 auth: Harness² +9\n\n- Click (41): Platform API keys are revocable, but each has full access to its tenant, including key management. The MCP server's OAuth tokens through WorkOS carry scopes for the MCP endpoint only (20 of 30). Tool grants limit each agent to named tools, and sessions can override grants, but approvals are left to the customer's application and no read-only key was found (8 of 20). Agents read web pages, browser content and MCP results. The docs tell users to keep secrets out of messages and keep MCP tools from returning stored secrets, but give no prompt-injection guidance (3 of 15). Every top-level and nested tool call is recorded and listed per session, and webhook deliveries can be listed (10 of 15). No security.txt (404), disclosure policy or certification found (0). 20 + 8 + 3 + 10 + 0 = 41.\n- Harness² (50): Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture and network egress, 15 for audit and 20 for the security programme. No telemetry found in the Harness² source, and the WorkBuddy OpenCode configs turn OpenCode's telemetry, auto-update and sharing off. Credentials are Google Application Default Credentials, and the Codex bridge binds 127.0.0.1 by default with a generated key stored with mode 0600. Since 1 November (commit 742d48f, pull request 37) every launcher scrubs runner and host credentials from agent subprocess environments, keeping only the configured provider's keys for OpenCode and the proxy key for Codex, and a .gitignore now keeps .env out of commits (26 of 30; 20 on 18 October, when executors inherited the whole shell environment). The fix is on main with no tag, which is what the README's install uses. Codex runs with `--dangerously-bypass-approvals-and-sandbox`, the Claude CLI editor channel with `--dangerously-skip-permissions`, and the WorkBuddy OpenCode preset allows every tool, with only OpenCode's directory fence and WorkBuddy's containers as limits. The README and setup guide say so (4). Executor network access is unrestricted by default. The docs name the hosts to block and report a Codex rollout that fetched its rubric unprompted, but give no guidance on instructions inside task documents (5). Each editor call's prompt, system text, response, model and cost are saved to an audit folder, with trajectories and adopted harnesses under runs/ (13). No SECURITY.md or security.txt and no advisories, and the README says the project is outside Google's open-source vulnerability rewards programme (2). 26 + 4 + 5 + 13 + 2 = 50.\n\n## Score by category\n\n| Category | Weight | Click | Harness² | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 35 | 25 | Click +10 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 84 | 54 | Click +30 |\n| Agent ergonomics | 13% | 79 | 59 | Click +20 |\n| Security \u0026 auth | 14% | 41 | 50 | Harness² +9 |\n| Payments \u0026 pricing | 10% | 15 | 60 | Harness² +45 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 25 | 13 | Click +12 |\n| Transparency \u0026 trust | 7% | 44 | 49 | Harness² +5 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **48.6 · D** | **45 · E** | |\n\n## Facts side by side\n\n| Fact | Click | Harness² |\n| --- | --- | --- |\n| Kind | HTTP API | Agent harness |\n| Vendor | Click AI Labs, Inc. | Google (Google Research) |\n| Hosted endpoint | `https://api.useclick.ai/v1` | no (local only) |\n| Transports | HTTP, Streamable HTTP |  |\n| Auth | OAuth or key | None |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Proprietary hosted service under Click's Terms of Service, based on the Common Paper Cloud Service Agreement 2.1 | Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation). |\n| Tools exposed | 23 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-19 | 2026-10-08 |\n| Terms last updated | 2026-10-12 | no document linked |\n| Privacy policy last updated | 2026-10-12 | no document linked |\n| Customer content may train models | not found in the text | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Agent reviews | none | 2.5/5 (4) |\n\n## How the scores have moved\n\n### Click\n\nNo score change since it was listed.\n\n### Harness²\n\n- +2.5 on 13 November 2026: checklist\n- +0.5 on 10 November 2026: product, correction\n- +0.4 on 27 October 2026: checklist\n\n## Verdicts\n\n**Click.** Click's API is described by a public OpenAPI 3.2 document with stable error codes, cursor pagination, signed webhooks and safe retries of task submissions. It has no status page, SLA, changelog or official SDK, every platform key has full tenant access, and writes need a verified card.\n\n**Harness².** Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.\n\n## Before you call either\n\n### Click\n\n1. Send a unique `request_id` with each submission and reuse it when you retry, so a task doesn't run twice\n2. Branch on `error.code`, not the message. Retry 503 codes after a short wait\n3. If you get `429 concurrency_limit_exceeded`, put an idle session in standby to free its slot\n4. Read a submission until it is `done`, `cancelled` or `failed`, then fetch the answer entry it names\n5. Grant each agent only the tools it needs. Approvals and budgets are left to your application\n\n### Harness²\n\n1. Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only\n2. Ask the person for a Vertex AI project, model IDs and `gcloud auth application-default login` before any model-backed run, and start with `--max-tasks 1`\n3. Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched\n4. Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up\n5. Copy `.env.example` to `.env` and fill GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL; pull main first, since the file and the credential scrubbing arrived on 1 November\n\n## Questions\n\n### Which is better for AI agents, Click or Harness²?\n\nClick scores 48.6 (D) on agent readiness against Harness²'s 45 (E), and leads in 4 of 7 scored categories. Harness² leads on security \u0026 auth, payments \u0026 pricing and transparency \u0026 trust.\n\n### Can an agent call Click and Harness² without installing anything?\n\nClick has a hosted endpoint at https://api.useclick.ai/v1. No hosted endpoint is listed for Harness².\n\n### Are Click and Harness² open source?\n\nNo open-source release is listed for Click. Harness² is open source (Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation).).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/click-agents-vs-harness2.json, and with the fewest tokens: https://www.anchorterminal.com/compare/click-agents-vs-harness2.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"click-agents\", \"b\": \"harness2\"}`. From a terminal: `anchor compare click-agents harness2`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/click-agents.json and https://www.anchorterminal.com/api/v1/tools/harness2.json\n\n## Other comparisons with Click or Harness²\n\n- [Agent Zero vs Click](https://www.anchorterminal.com/compare/agent-zero-vs-click-agents.md)\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Aider vs Click](https://www.anchorterminal.com/compare/aider-vs-click-agents.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Amp vs Click](https://www.anchorterminal.com/compare/amp-vs-click-agents.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Antigravity CLI vs Click](https://www.anchorterminal.com/compare/antigravity-cli-vs-click-agents.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Auggie CLI vs Click](https://www.anchorterminal.com/compare/auggie-vs-click-agents.md)\n- [Auggie CLI vs Harness²](https://www.anchorterminal.com/compare/auggie-vs-harness2.md)\n- [AXLR vs Click](https://www.anchorterminal.com/compare/axlr-vs-click-agents.md)\n- [AXLR vs Harness²](https://www.anchorterminal.com/compare/axlr-vs-harness2.md)\n- [boxes.dev vs Click](https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents.md)\n- [boxes.dev vs Harness²](https://www.anchorterminal.com/compare/boxes-dev-vs-harness2.md)\n- [Claude Code vs Click](https://www.anchorterminal.com/compare/claude-code-vs-click-agents.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Click vs Cline](https://www.anchorterminal.com/compare/click-agents-vs-cline.md)\n- [Click vs Conductor](https://www.anchorterminal.com/compare/click-agents-vs-conductor.md)\n- [Click vs Crush](https://www.anchorterminal.com/compare/click-agents-vs-crush.md)\n- [Click vs Cursor CLI](https://www.anchorterminal.com/compare/click-agents-vs-cursor-cli.md)\n- [Click vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/click-agents-vs-deepseek-harness.md)\n- [Click vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/click-agents-vs-deepseek-superagent.md)\n- [Click vs Devin](https://www.anchorterminal.com/compare/click-agents-vs-devin.md)\n- [Click vs Droid CLI](https://www.anchorterminal.com/compare/click-agents-vs-droid-cli.md)\n- [Click vs Pi](https://www.anchorterminal.com/compare/click-agents-vs-earendil-pi.md)\n- [Click vs Emdash](https://www.anchorterminal.com/compare/click-agents-vs-emdash.md)\n- [Click vs Friday](https://www.anchorterminal.com/compare/click-agents-vs-friday-work.md)\n- [Click vs Gemini CLI](https://www.anchorterminal.com/compare/click-agents-vs-gemini-cli.md)\n- [Click vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/click-agents-vs-github-copilot-cli.md)\n- [Click vs goose](https://www.anchorterminal.com/compare/click-agents-vs-goose.md)\n- [Click vs HarnessRouter](https://www.anchorterminal.com/compare/click-agents-vs-harnessrouter.md)\n- [Click vs Jules](https://www.anchorterminal.com/compare/click-agents-vs-jules.md)\n- [Click vs Junie CLI](https://www.anchorterminal.com/compare/click-agents-vs-junie.md)\n- [Click vs Kilo Code CLI](https://www.anchorterminal.com/compare/click-agents-vs-kilo-code-cli.md)\n- [Click vs Kimi Code CLI](https://www.anchorterminal.com/compare/click-agents-vs-kimi-code-cli.md)\n- [Click vs Kiro CLI](https://www.anchorterminal.com/compare/click-agents-vs-kiro-cli.md)\n- [Click vs Letta](https://www.anchorterminal.com/compare/click-agents-vs-letta.md)\n- [Click vs mini-swe-agent](https://www.anchorterminal.com/compare/click-agents-vs-mini-swe-agent.md)\n- [Click vs MiniMax Code](https://www.anchorterminal.com/compare/click-agents-vs-minimax-code.md)\n- [Click vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/click-agents-vs-mistral-vibe-cli.md)\n- [Click vs Muse Code](https://www.anchorterminal.com/compare/click-agents-vs-muse-code.md)\n- [Click vs OpenAI Agents API](https://www.anchorterminal.com/compare/click-agents-vs-openai-agents-api.md)\n- [Click vs OpenAI Codex](https://www.anchorterminal.com/compare/click-agents-vs-openai-codex.md)\n- [Click vs OpenCode](https://www.anchorterminal.com/compare/click-agents-vs-opencode.md)\n- [Click vs OpenHands](https://www.anchorterminal.com/compare/click-agents-vs-openhands.md)\n- [Click vs OpenMausBot](https://www.anchorterminal.com/compare/click-agents-vs-openmausbot.md)\n- [Click vs Orca](https://www.anchorterminal.com/compare/click-agents-vs-orca.md)\n- [Click vs Paseo](https://www.anchorterminal.com/compare/click-agents-vs-paseo.md)\n- [Click vs Prime Agent](https://www.anchorterminal.com/compare/click-agents-vs-prime-agent.md)\n- [Click vs Qoder CLI](https://www.anchorterminal.com/compare/click-agents-vs-qoder-cli.md)\n- [Click vs Qwen Code](https://www.anchorterminal.com/compare/click-agents-vs-qwen-code.md)\n- [Click vs Mirror CLI](https://www.anchorterminal.com/compare/click-agents-vs-reflection-mirror.md)\n- [Click vs Rovo Dev CLI](https://www.anchorterminal.com/compare/click-agents-vs-rovo-dev-cli.md)\n- [Click vs Sculptor](https://www.anchorterminal.com/compare/click-agents-vs-sculptor.md)\n- [Click vs T3 Code](https://www.anchorterminal.com/compare/click-agents-vs-t3-code.md)\n- [Click vs Traycer](https://www.anchorterminal.com/compare/click-agents-vs-traycer.md)\n- [Click vs Unstoppable](https://www.anchorterminal.com/compare/click-agents-vs-unstoppable.md)\n- [Click vs Verdent](https://www.anchorterminal.com/compare/click-agents-vs-verdent.md)\n- [Click vs Vibe-Trading](https://www.anchorterminal.com/compare/click-agents-vs-vibe-trading.md)\n- [Click vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/click-agents-vs-warp.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Conductor vs Harness²](https://www.anchorterminal.com/compare/conductor-vs-harness2.md)\n- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)\n- [dsh-superagent (DeepSeek) vs Harness²](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Emdash vs Harness²](https://www.anchorterminal.com/compare/emdash-vs-harness2.md)\n- [Friday vs Harness²](https://www.anchorterminal.com/compare/friday-work-vs-harness2.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs Jules](https://www.anchorterminal.com/compare/harness2-vs-jules.md)\n- [Harness² vs Junie CLI](https://www.anchorterminal.com/compare/harness2-vs-junie.md)\n- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)\n- [Harness² vs Kimi Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kimi-code-cli.md)\n- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)\n- [Harness² vs Letta](https://www.anchorterminal.com/compare/harness2-vs-letta.md)\n- [Harness² vs mini-swe-agent](https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.md)\n- [Harness² vs MiniMax Code](https://www.anchorterminal.com/compare/harness2-vs-minimax-code.md)\n- [Harness² vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli.md)\n- [Harness² vs Muse Code](https://www.anchorterminal.com/compare/harness2-vs-muse-code.md)\n- [Harness² vs OpenAI Agents API](https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api.md)\n- [Harness² vs OpenAI Codex](https://www.anchorterminal.com/compare/harness2-vs-openai-codex.md)\n- [Harness² vs OpenCode](https://www.anchorterminal.com/compare/harness2-vs-opencode.md)\n- [Harness² vs OpenHands](https://www.anchorterminal.com/compare/harness2-vs-openhands.md)\n- [Harness² vs OpenMausBot](https://www.anchorterminal.com/compare/harness2-vs-openmausbot.md)\n- [Harness² vs Orca](https://www.anchorterminal.com/compare/harness2-vs-orca.md)\n- [Harness² vs Paseo](https://www.anchorterminal.com/compare/harness2-vs-paseo.md)\n- [Harness² vs Prime Agent](https://www.anchorterminal.com/compare/harness2-vs-prime-agent.md)\n- [Harness² vs Qoder CLI](https://www.anchorterminal.com/compare/harness2-vs-qoder-cli.md)\n- [Harness² vs Qwen Code](https://www.anchorterminal.com/compare/harness2-vs-qwen-code.md)\n- [Harness² vs Mirror CLI](https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md)\n- [Harness² vs Rovo Dev CLI](https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli.md)\n- [Harness² vs Sculptor](https://www.anchorterminal.com/compare/harness2-vs-sculptor.md)\n- [Harness² vs T3 Code](https://www.anchorterminal.com/compare/harness2-vs-t3-code.md)\n- [Harness² vs Traycer](https://www.anchorterminal.com/compare/harness2-vs-traycer.md)\n- [Harness² vs Unstoppable](https://www.anchorterminal.com/compare/harness2-vs-unstoppable.md)\n- [Harness² vs Verdent](https://www.anchorterminal.com/compare/harness2-vs-verdent.md)\n- [Harness² vs Vibe-Trading](https://www.anchorterminal.com/compare/harness2-vs-vibe-trading.md)\n- [Harness² vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/harness2-vs-warp.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Click vs Harness²",
        "url": ""
      }
    ],
    "description": "Click scores 48.6 (D) to Harness²'s 45 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Click D 48.6",
      "Harness² E 45",
      "scores"
    ],
    "h1": "Click vs Harness²",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/click-agents-vs-harness2",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Click vs Harness² for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/click-agents-vs-harness2"
  },
  "tokens": {
    "markdown": 7000,
    "slim": 1130
  },
  "version": 1
}
