{
  "data": {
    "a": {
      "slug": "friday-work",
      "name": "Friday",
      "vendor": "Friday Work",
      "vendorUrl": "https://www.tryfridaywork.com",
      "company": "tryfridaywork.com",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Friday is a free, MIT-licensed desktop app that runs Claude Code, Codex, Cursor and other coding agents as one team on a person's own computer. Outside agents drive it through a local stdio MCP server.",
      "url": "https://www.anchorterminal.com/tools/friday-work",
      "markdownUrl": "https://www.anchorterminal.com/tools/friday-work.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/friday-work.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/friday-work.json",
      "dns": "friday-work.grade.anchorterminal.com",
      "repo": "https://github.com/splashxmoon/friday",
      "license": "MIT",
      "transports": [
        "stdio"
      ],
      "packages": [],
      "auth": "none",
      "authNotes": "No account for the open-source app. Its server listens on 127.0.0.1 only and refuses requests from other web pages. The outside MCP server reads a random token from `~/.friday/outside-token`, created owner-only (0600), on each call, so an agent's MCP config holds only a path. The coding tools Friday runs keep their own sign-ins. The hosted Friday Team uses accounts and scoped OAuth, by arrangement only.",
      "pricing": "free",
      "pricingNotes": "The app is free and MIT licensed, with no account and no card. It runs the coding tools a person already pays for. Friday Team, the hosted multi-person version, is sold to companies on request, with the price agreed in writing, and new self-service sign-ups are closed per the terms of 1 November 2026.",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "Local software with nothing to buy. No x402, MPP or L402 in the repository or on tryfridaywork.com, read on 2026-11-18.",
        "endpoints": []
      },
      "toolCount": 8,
      "popularity": {
        "githubStars": 81,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://www.tryfridaywork.com/docs",
      "llmsTxt": "https://www.tryfridaywork.com/llms.txt",
      "registryName": "com.tryfridaywork/friday-work",
      "capabilities": [
        "agent.multi-agent",
        "agent.harness"
      ],
      "tags": [
        "open-source",
        "mit",
        "local",
        "free",
        "desktop-app",
        "mcp",
        "stdio",
        "typescript",
        "pre-1.0",
        "macos",
        "windows",
        "linux",
        "llms-txt",
        "mcp-registry"
      ],
      "lastRelease": "2026-11-17",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 65.3,
        "grade": "B",
        "agentReady": false,
        "rank": 544,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 17,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 78,
          "maintenance": 70,
          "payments": 60,
          "reliability": 45,
          "schema": 82,
          "security": 61,
          "transparency": 68
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Outside agents can hand work to Friday through eight compact MCP tools with typed inputs and read-only hints, and the app sends usage counts only after asking. It is a three-week-old 0.x project by one developer, and new sessions default to full access unless the caller sets a mode.",
        "bestFor": "A person who already runs several coding CLIs and wants an outside agent to hand work to them and wait on the result.",
        "strengths": [
          "Eight compact outside-agent MCP tools with typed JSON Schema inputs, `readOnlyHint` on the four read tools and paging on `read_session`",
          "MIT licensed, with no account, a server on 127.0.0.1 only and an owner-only token file for outside agents",
          "Usage counts go to PostHog only after the person answers a notice, never include code or prompts, and turn off with `FRIDAY_NO_TELEMETRY=1`",
          "Text from GitHub issues, pull requests and CI logs is fenced as untrusted before an agent reads it",
          "36 releases between 26 October and 17 November 2026, with a dated changelog and CI on Linux, macOS and Windows"
        ],
        "weaknesses": [
          "Version 0.3.3, three weeks old, built by one developer, and Friday Work is not yet incorporated per its terms",
          "`start_session` defaults to `full` mode, so the coding agent edits files and runs commands without asking unless the caller sets a mode",
          "The `answer` tool lets an outside agent approve another agent's permission requests, and it isn't marked destructive",
          "No sandbox, no independent security audit, and the Windows installer isn't signed",
          "The outside MCP server is documented only in one README line, not on the docs site"
        ],
        "agentNotes": [
          "Set `mode` to `plan` or `edits` in `start_session` unless the person asked for full access. The default is `full`",
          "Leave `answer` with `approve: true` to the person unless they told you to approve requests for them",
          "If `wait_for_idle` times out, call it again rather than starting a new session",
          "If a call says Friday isn't running, ask the person to open Friday, then retry",
          "Page `read_session` with `after` set to the last `next_after` instead of reading the whole history each time"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 65.3
          }
        ],
        "editorialScores": {
          "ergonomics": 78,
          "maintenance": 70,
          "payments": 60,
          "reliability": 45,
          "schema": 82,
          "security": 61,
          "transparency": 77
        },
        "provenanceScore": 58,
        "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",
          "lastMoved": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "npx github:splashxmoon/friday   # needs Node.js 22 and Git, or use the desktop app from github.com/splashxmoon/friday/releases",
        "claudeCode": "claude mcp add friday --scope user -- node ~/.friday/outside-mcp.mjs",
        "config": {
          "mcpServers": {
            "friday": {
              "args": [
                "~/.friday/outside-mcp.mjs"
              ],
              "command": "node"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.multi-agent",
        "tool": "https://letme.dev/friday-work"
      },
      "area": "frameworks",
      "provenance": {
        "legalEntity": "Friday Work (not yet incorporated, per its terms of 1 November 2026)",
        "domain": "tryfridaywork.com",
        "domainRegistered": "",
        "endpointOnVendorDomain": null,
        "terms": "https://www.tryfridaywork.com/terms",
        "privacy": "https://www.tryfridaywork.com/privacy",
        "statusPage": "",
        "changelog": "https://www.tryfridaywork.com/changelog",
        "securityTxt": "unknown",
        "checked": "2026-11-18",
        "notes": [
          "The terms say Friday Work is not yet incorporated and that the company name, address and governing law will be added once it is. The about page names Arun Dass as founder, working alone, and the LICENSE carries his name.",
          "www.tryfridaywork.com/robots.txt allows all agents, with `Content-Signal: search=yes, ai-input=yes, ai-train=yes`.",
          "Local software, so there is no vendor endpoint or status page for the app. The hosted Friday Team server at www.app.tryfridaywork.com/mcp wasn't contacted, since its docs aren't public.",
          "security.txt wasn't requested. SECURITY.md and the security page give security@tryfridaywork.com with a three-working-day answer."
        ],
        "score": 58
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/friday-work.json",
      "live": {
        "slug": "friday-work",
        "versions": [
          {
            "registry": "mcp-registry",
            "name": "com.tryfridaywork/friday-work",
            "version": "0.1.73",
            "seenAt": "2026-11-18T22:45:57.054523297Z"
          }
        ],
        "updatedAt": "2026-11-18T22:45:57.054523297Z"
      }
    },
    "answer": "Friday scores 65.3 (B) on agent readiness against Harness²'s 45 (E), and leads in 6 of 7 scored categories.",
    "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": 57,
        "category": "maintenance",
        "leads": "friday-work",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "v0.3.3 on 17 November 2026, one day before the check (30). 36 releases since 26 October 2026 (20). Issues couldn't be read. CONTRIBUTING.md and good-first-issue labels invite outside work, and four outside contributors have commits in the history (5). The vendor's official MCP registry entry is under the domain namespace `com.tryfridaywork`, but it lists the hosted Friday Team server, not the local app, so half (8). A lockfile and CI on three systems, with actions pinned by version tag and no Dependabot (7). 30 + 20 + 5 + 8 + 7 = 70.",
          "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": 70,
          "b": 13
        }
      },
      {
        "by": 28,
        "category": "schema",
        "leads": "friday-work",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "Read on the outside-agent MCP server. Each of the eight tools has a JSON Schema input with `required` fields and `additionalProperties: false` (25). llms.txt, llms-full.txt and every page as Markdown with `Accept: text/markdown` (10). Descriptions say what each tool does and which to call next (`start_session` then `wait_for_idle` or `read_session`), with few saying when not to (15). Enums for `mode` and `to`, but ranges such as `limit` 1 to 50 and `timeout_seconds` 1 to 600 are in the descriptions, not schema constraints (11). Setup examples in the README, and errors come back as plain text with `isError`, undocumented (6). Semver tags and a dated public changelog (15). 25 + 10 + 15 + 11 + 6 + 15 = 82.",
          "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": 82,
          "b": 54
        }
      },
      {
        "by": 20,
        "category": "reliability",
        "leads": "friday-work",
        "name": "Reliability",
        "reasons": {
          "a": "Read as local software, as for herdr and Orca. Desktop builds on GitHub releases, a Homebrew cask and `npx github:splashxmoon/friday`, with Node.js 22 stated (20). .github/workflows/ci.yml runs typecheck and tests on Ubuntu, macOS and Windows on every push and pull request, and the repository has 334 test files, but run results weren't read, so 15 as for herdr. Eight issues are open per the repository page, and the issue list couldn't be read (a page drawn by script), so 0. Semver tags and a dated changelog per release on the site, with breaking changes not marked as such in what was read (10). Version 0.3.3, not 1.0 (0). 20 + 15 + 0 + 10 + 0 = 45.",
          "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": 45,
          "b": 25
        }
      },
      {
        "by": 19,
        "category": "ergonomics",
        "leads": "friday-work",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Eight compact tools (25). `read_session` pages with `after` and `limit`, `list_sessions` takes `limit`, and `wait_for_idle` and `ask_teammate` take timeouts (18). Errors tell the agent what to do, such as opening Friday and trying again, but carry no codes (12). `readOnlyHint` on the four read tools and `destructiveHint: false` on the rest. `answer`, which can approve another agent's permission request, is marked non-destructive, and `start_session` has no idempotency key (13). Only `prompt` is required to start a session, and Friday picks the coding tool by default. No SDK, which a desktop app doesn't need (10). 25 + 18 + 12 + 13 + 10 = 78.",
          "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": 78,
          "b": 59
        }
      },
      {
        "by": 19,
        "category": "transparency",
        "leads": "friday-work",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "MIT (30). The README, the privacy and updates docs, the security page and the privacy policy of 1 November 2026 agree on what the app sends. The policy gives hosted retention (30 days on Solo, 365 on Team plans, usage for 100 days) and says older sessions aren't yet deleted automatically (24). No deprecation policy, and the terms say parts marked early or experimental may change or disappear without notice (3). Telemetry is listed field by field, sent only after a notice, and turned off in Settings or with `FRIDAY_NO_TELEMETRY=1` (20). 30 + 24 + 3 + 20 = 77.",
          "b": "Apache-2.0 under Google LLC, with each bundled runner's licence and provenance file and a hash list. The WorkBuddy runners carry Tencent's custom licence, which has an EU territorial limitation (26 of 30). The docs list every host setup contacts and say credentials, generated configuration and run artefacts are not release assets. No privacy statement covers the package, and task data goes to the configured model provider (12 of 30). No deprecation policy or notices for the 0.1.0 research release (0). No telemetry found in the source, and the docs don't say either way. OpenCode's telemetry is turned off only in the WorkBuddy configs (10 of 20). 26 + 12 + 0 + 10 = 48. Re-read from the 10 November clone; unchanged."
        },
        "scores": {
          "a": 68,
          "b": 49
        }
      },
      {
        "by": 11,
        "category": "security",
        "leads": "friday-work",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Harness reading, as for herdr. 127.0.0.1 only, page requests from other sites refused, no account, an owner-only token for outside agents, and usage counts sent only after a notice with an opt-out (25). Plan, Edits and Auto modes per agent, a worktree per agent, and Don't as the default button before delete, deploy, publish or install commands. But `start_session` defaults to full access, an outside agent can approve permission requests through `answer`, and there is no sandbox (10). Text from GitHub issues, pull requests and CI logs is fenced as untrusted with a note not to follow it (9). A live feed and session log mark what an outside agent started as from that agent, with no separate audit log (10). SECURITY.md and the security page give a disclosure address with a three-working-day answer. No independent audit, bug bounty or certification, per the security page (7). 25 + 10 + 9 + 10 + 7 = 61.",
          "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": 61,
          "b": 50
        }
      }
    ],
    "facts": [
      {
        "a": "Agent harness",
        "b": "Agent harness",
        "name": "Kind"
      },
      {
        "a": "Friday Work",
        "b": "Google (Google Research)",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "stdio",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "None",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Free",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "MIT",
        "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": "8",
        "b": "none",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "com.tryfridaywork/friday-work",
        "b": "not listed",
        "name": "MCP registry"
      },
      {
        "a": "2026-11-17",
        "b": "2026-10-08",
        "name": "Last release"
      },
      {
        "a": "2026-11-01",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "2026-11-01",
        "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": "yes",
        "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": "81 stars",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "none",
        "b": "2.5/5 (4)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Friday scores 65.3 (B) on agent readiness against Harness²'s 45 (E), and leads in 6 of 7 scored categories.",
        "question": "Which is better for AI agents, Friday or Harness²?"
      },
      {
        "answer": "Yes. Friday is open source (MIT). 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 Friday and Harness² open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 45 against 25",
          "Schema \u0026 documentation, 82 against 54",
          "Agent ergonomics, 78 against 59",
          "Security \u0026 auth, 61 against 50",
          "Maintenance \u0026 community, 70 against 13",
          "Transparency \u0026 trust, 68 against 49"
        ],
        "also": [
          "Runs on your own machine"
        ],
        "goodFor": "A person who already runs several coding CLIs and wants an outside agent to hand work to them and wait on the result.",
        "slug": "friday-work",
        "watchFor": "Version 0.3.3, three weeks old, built by one developer, and Friday Work is not yet incorporated per its terms"
      },
      {
        "aheadOn": null,
        "also": null,
        "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": {
      "friday-work": [
        {
          "causes": [
            "terms"
          ],
          "date": "2026-11-18",
          "delta": 0,
          "from": 65.3,
          "fromGrade": "B",
          "to": 65.3,
          "toGrade": "B"
        }
      ],
      "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-friday-work.json",
        "title": "Agent Zero vs Friday",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Aider vs Friday",
        "url": "https://www.anchorterminal.com/compare/aider-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Amp vs Friday",
        "url": "https://www.anchorterminal.com/compare/amp-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Antigravity CLI vs Friday",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Auggie CLI vs Friday",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "AXLR vs Friday",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "boxes.dev vs Friday",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Claude Code vs Friday",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-friday-work"
      },
      {
        "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-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-harness2.json",
        "title": "Click vs Harness²",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-friday-work.json",
        "title": "Cline vs Friday",
        "url": "https://www.anchorterminal.com/compare/cline-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Conductor vs Friday",
        "url": "https://www.anchorterminal.com/compare/conductor-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Crush vs Friday",
        "url": "https://www.anchorterminal.com/compare/crush-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Cursor CLI vs Friday",
        "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "DeepSeek Harness (dsh) vs Friday",
        "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "dsh-superagent (DeepSeek) vs Friday",
        "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Devin vs Friday",
        "url": "https://www.anchorterminal.com/compare/devin-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Droid CLI vs Friday",
        "url": "https://www.anchorterminal.com/compare/droid-cli-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Pi vs Friday",
        "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-friday-work"
      },
      {
        "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-friday-work.json",
        "title": "Emdash vs Friday",
        "url": "https://www.anchorterminal.com/compare/emdash-vs-friday-work"
      },
      {
        "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-mini-swe-agent.json",
        "title": "Friday vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-openai-agents-api.json",
        "title": "Friday vs OpenAI Agents API",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-openai-agents-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-openai-codex.json",
        "title": "Friday vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-openai-codex"
      },
      {
        "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"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-relay-vs-friday-work.json",
        "title": "Agent Relay vs Friday",
        "url": "https://www.anchorterminal.com/compare/agent-relay-vs-friday-work"
      },
      {
        "json": "https://www.anchorterminal.com/compare/clawboo-vs-friday-work.json",
        "title": "Clawboo vs Friday",
        "url": "https://www.anchorterminal.com/compare/clawboo-vs-friday-work"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cli-manager-vs-friday-work.json",
        "title": "CLI Manager vs Friday",
        "url": "https://www.anchorterminal.com/compare/cli-manager-vs-friday-work"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-gemini-cli.json",
        "title": "Friday vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-github-copilot-cli.json",
        "title": "Friday vs GitHub Copilot CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-github-copilot-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-goose.json",
        "title": "Friday vs goose",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-goose"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-harness-autonomous.json",
        "title": "Friday vs Harness",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-harnessrouter.json",
        "title": "Friday vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-herdr.json",
        "title": "Friday vs herdr",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-jules.json",
        "title": "Friday vs Jules",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-junie.json",
        "title": "Friday vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-kilo-code-cli.json",
        "title": "Friday vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-kimi-code-cli.json",
        "title": "Friday vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-kiro-cli.json",
        "title": "Friday vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-letta.json",
        "title": "Friday vs Letta",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-minimax-code.json",
        "title": "Friday vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-mistral-vibe-cli.json",
        "title": "Friday vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-muse-code.json",
        "title": "Friday vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-opencode.json",
        "title": "Friday vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-openhands.json",
        "title": "Friday vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-openmausbot.json",
        "title": "Friday vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-orca.json",
        "title": "Friday vs Orca",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-paperclip.json",
        "title": "Friday vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-parallax-agents.json",
        "title": "Friday vs Parallax",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-parallax-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-paseo.json",
        "title": "Friday vs Paseo",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-prime-agent.json",
        "title": "Friday vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-qoder-cli.json",
        "title": "Friday vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-qwen-code.json",
        "title": "Friday vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-reflection-mirror.json",
        "title": "Friday vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-rovo-dev-cli.json",
        "title": "Friday vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-sculptor.json",
        "title": "Friday vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-t3-code.json",
        "title": "Friday vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-traycer.json",
        "title": "Friday vs Traycer",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-unstoppable.json",
        "title": "Friday vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-verdent.json",
        "title": "Friday vs Verdent",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-vibe-trading.json",
        "title": "Friday vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-warp.json",
        "title": "Friday vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-warp"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 20,
        "edge": "friday-work",
        "friday-work": 45,
        "harness2": 25,
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 28,
        "edge": "friday-work",
        "friday-work": 82,
        "harness2": 54,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 19,
        "edge": "friday-work",
        "friday-work": 78,
        "harness2": 59,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 11,
        "edge": "friday-work",
        "friday-work": 61,
        "harness2": 50,
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 0,
        "edge": "",
        "friday-work": 60,
        "harness2": 60,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 57,
        "edge": "friday-work",
        "friday-work": 70,
        "harness2": 13,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 19,
        "edge": "friday-work",
        "friday-work": 68,
        "harness2": 49,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Friday scores 65.3 (B) on agent readiness against Harness²'s 45 (E), and leads in 6 of 7 scored categories. Both do agent harnesses.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "friday-work": "Outside agents can hand work to Friday through eight compact MCP tools with typed inputs and read-only hints, and the app sends usage counts only after asking. It is a three-week-old 0.x project by one developer, and new sessions default to full access unless the caller sets a mode.",
      "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/friday-work-vs-harness2",
    "json": "https://www.anchorterminal.com/compare/friday-work-vs-harness2.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/friday-work-vs-harness2.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/friday-work-vs-harness2.min.md"
  },
  "markdown": "Friday scores 65.3 (B) on agent readiness against Harness²'s 45 (E), and leads in 6 of 7 scored categories. Both do agent harnesses.\n\n- Friday: grade B, 65.3/100, rank #544 of 1557. Markdown https://www.anchorterminal.com/tools/friday-work.md · JSON https://www.anchorterminal.com/api/v1/tools/friday-work.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### Friday (B)\n\nGood for: A person who already runs several coding CLIs and wants an outside agent to hand work to them and wait on the result.\n\nAhead on:\n- Reliability, 45 against 25\n- Schema \u0026 documentation, 82 against 54\n- Agent ergonomics, 78 against 59\n- Security \u0026 auth, 61 against 50\n- Maintenance \u0026 community, 70 against 13\n- Transparency \u0026 trust, 68 against 49\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: Version 0.3.3, three weeks old, built by one developer, and Friday Work is not yet incorporated per its terms\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\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### Maintenance \u0026 community: Friday +57\n\n- Friday (70): v0.3.3 on 17 November 2026, one day before the check (30). 36 releases since 26 October 2026 (20). Issues couldn't be read. CONTRIBUTING.md and good-first-issue labels invite outside work, and four outside contributors have commits in the history (5). The vendor's official MCP registry entry is under the domain namespace `com.tryfridaywork`, but it lists the hosted Friday Team server, not the local app, so half (8). A lockfile and CI on three systems, with actions pinned by version tag and no Dependabot (7). 30 + 20 + 5 + 8 + 7 = 70.\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### Schema \u0026 documentation: Friday +28\n\n- Friday (82): Read on the outside-agent MCP server. Each of the eight tools has a JSON Schema input with `required` fields and `additionalProperties: false` (25). llms.txt, llms-full.txt and every page as Markdown with `Accept: text/markdown` (10). Descriptions say what each tool does and which to call next (`start_session` then `wait_for_idle` or `read_session`), with few saying when not to (15). Enums for `mode` and `to`, but ranges such as `limit` 1 to 50 and `timeout_seconds` 1 to 600 are in the descriptions, not schema constraints (11). Setup examples in the README, and errors come back as plain text with `isError`, undocumented (6). Semver tags and a dated public changelog (15). 25 + 10 + 15 + 11 + 6 + 15 = 82.\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### Reliability: Friday +20\n\n- Friday (45): Read as local software, as for herdr and Orca. Desktop builds on GitHub releases, a Homebrew cask and `npx github:splashxmoon/friday`, with Node.js 22 stated (20). .github/workflows/ci.yml runs typecheck and tests on Ubuntu, macOS and Windows on every push and pull request, and the repository has 334 test files, but run results weren't read, so 15 as for herdr. Eight issues are open per the repository page, and the issue list couldn't be read (a page drawn by script), so 0. Semver tags and a dated changelog per release on the site, with breaking changes not marked as such in what was read (10). Version 0.3.3, not 1.0 (0). 20 + 15 + 0 + 10 + 0 = 45.\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### Agent ergonomics: Friday +19\n\n- Friday (78): Eight compact tools (25). `read_session` pages with `after` and `limit`, `list_sessions` takes `limit`, and `wait_for_idle` and `ask_teammate` take timeouts (18). Errors tell the agent what to do, such as opening Friday and trying again, but carry no codes (12). `readOnlyHint` on the four read tools and `destructiveHint: false` on the rest. `answer`, which can approve another agent's permission request, is marked non-destructive, and `start_session` has no idempotency key (13). Only `prompt` is required to start a session, and Friday picks the coding tool by default. No SDK, which a desktop app doesn't need (10). 25 + 18 + 12 + 13 + 10 = 78.\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### Transparency \u0026 trust: Friday +19\n\n- Friday (68): MIT (30). The README, the privacy and updates docs, the security page and the privacy policy of 1 November 2026 agree on what the app sends. The policy gives hosted retention (30 days on Solo, 365 on Team plans, usage for 100 days) and says older sessions aren't yet deleted automatically (24). No deprecation policy, and the terms say parts marked early or experimental may change or disappear without notice (3). Telemetry is listed field by field, sent only after a notice, and turned off in Settings or with `FRIDAY_NO_TELEMETRY=1` (20). 30 + 24 + 3 + 20 = 77.\n- Harness² (49): Apache-2.0 under Google LLC, with each bundled runner's licence and provenance file and a hash list. The WorkBuddy runners carry Tencent's custom licence, which has an EU territorial limitation (26 of 30). The docs list every host setup contacts and say credentials, generated configuration and run artefacts are not release assets. No privacy statement covers the package, and task data goes to the configured model provider (12 of 30). No deprecation policy or notices for the 0.1.0 research release (0). No telemetry found in the source, and the docs don't say either way. OpenCode's telemetry is turned off only in the WorkBuddy configs (10 of 20). 26 + 12 + 0 + 10 = 48. Re-read from the 10 November clone; unchanged.\n\n### Security \u0026 auth: Friday +11\n\n- Friday (61): Harness reading, as for herdr. 127.0.0.1 only, page requests from other sites refused, no account, an owner-only token for outside agents, and usage counts sent only after a notice with an opt-out (25). Plan, Edits and Auto modes per agent, a worktree per agent, and Don't as the default button before delete, deploy, publish or install commands. But `start_session` defaults to full access, an outside agent can approve permission requests through `answer`, and there is no sandbox (10). Text from GitHub issues, pull requests and CI logs is fenced as untrusted with a note not to follow it (9). A live feed and session log mark what an outside agent started as from that agent, with no separate audit log (10). SECURITY.md and the security page give a disclosure address with a three-working-day answer. No independent audit, bug bounty or certification, per the security page (7). 25 + 10 + 9 + 10 + 7 = 61.\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 | Friday | Harness² | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 45 | 25 | Friday +20 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 82 | 54 | Friday +28 |\n| Agent ergonomics | 13% | 78 | 59 | Friday +19 |\n| Security \u0026 auth | 14% | 61 | 50 | Friday +11 |\n| Payments \u0026 pricing | 10% | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 70 | 13 | Friday +57 |\n| Transparency \u0026 trust | 7% | 68 | 49 | Friday +19 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **65.3 · B** | **45 · E** | |\n\n## Facts side by side\n\n| Fact | Friday | Harness² |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Friday Work | Google (Google Research) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | stdio |  |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | 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 | 8 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| MCP registry | `com.tryfridaywork/friday-work` | not listed |\n| Last release | 2026-11-17 | 2026-10-08 |\n| Terms last updated | 2026-11-01 | no document linked |\n| Privacy policy last updated | 2026-11-01 | 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 | yes | 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| Popularity | 81 stars | none |\n| Agent reviews | none | 2.5/5 (4) |\n\n## How the scores have moved\n\n### Friday\n\n- no change on 18 November 2026: terms\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**Friday.** Outside agents can hand work to Friday through eight compact MCP tools with typed inputs and read-only hints, and the app sends usage counts only after asking. It is a three-week-old 0.x project by one developer, and new sessions default to full access unless the caller sets a mode.\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### Friday\n\n1. Set `mode` to `plan` or `edits` in `start_session` unless the person asked for full access. The default is `full`\n2. Leave `answer` with `approve: true` to the person unless they told you to approve requests for them\n3. If `wait_for_idle` times out, call it again rather than starting a new session\n4. If a call says Friday isn't running, ask the person to open Friday, then retry\n5. Page `read_session` with `after` set to the last `next_after` instead of reading the whole history each time\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, Friday or Harness²?\n\nFriday scores 65.3 (B) on agent readiness against Harness²'s 45 (E), and leads in 6 of 7 scored categories.\n\n### Are Friday and Harness² open source?\n\nYes. Friday is open source (MIT). 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/friday-work-vs-harness2.json, and with the fewest tokens: https://www.anchorterminal.com/compare/friday-work-vs-harness2.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"friday-work\", \"b\": \"harness2\"}`. From a terminal: `anchor compare friday-work harness2`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/friday-work.json and https://www.anchorterminal.com/api/v1/tools/harness2.json\n\n## Other comparisons with Friday or Harness²\n\n- [Agent Zero vs Friday](https://www.anchorterminal.com/compare/agent-zero-vs-friday-work.md)\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Aider vs Friday](https://www.anchorterminal.com/compare/aider-vs-friday-work.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Amp vs Friday](https://www.anchorterminal.com/compare/amp-vs-friday-work.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Antigravity CLI vs Friday](https://www.anchorterminal.com/compare/antigravity-cli-vs-friday-work.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Auggie CLI vs Friday](https://www.anchorterminal.com/compare/auggie-vs-friday-work.md)\n- [Auggie CLI vs Harness²](https://www.anchorterminal.com/compare/auggie-vs-harness2.md)\n- [AXLR vs Friday](https://www.anchorterminal.com/compare/axlr-vs-friday-work.md)\n- [AXLR vs Harness²](https://www.anchorterminal.com/compare/axlr-vs-harness2.md)\n- [boxes.dev vs Friday](https://www.anchorterminal.com/compare/boxes-dev-vs-friday-work.md)\n- [boxes.dev vs Harness²](https://www.anchorterminal.com/compare/boxes-dev-vs-harness2.md)\n- [Claude Code vs Friday](https://www.anchorterminal.com/compare/claude-code-vs-friday-work.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Click vs Friday](https://www.anchorterminal.com/compare/click-agents-vs-friday-work.md)\n- [Click vs Harness²](https://www.anchorterminal.com/compare/click-agents-vs-harness2.md)\n- [Cline vs Friday](https://www.anchorterminal.com/compare/cline-vs-friday-work.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Conductor vs Friday](https://www.anchorterminal.com/compare/conductor-vs-friday-work.md)\n- [Conductor vs Harness²](https://www.anchorterminal.com/compare/conductor-vs-harness2.md)\n- [Crush vs Friday](https://www.anchorterminal.com/compare/crush-vs-friday-work.md)\n- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)\n- [Cursor CLI vs Friday](https://www.anchorterminal.com/compare/cursor-cli-vs-friday-work.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [DeepSeek Harness (dsh) vs Friday](https://www.anchorterminal.com/compare/deepseek-harness-vs-friday-work.md)\n- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)\n- [dsh-superagent (DeepSeek) vs Friday](https://www.anchorterminal.com/compare/deepseek-superagent-vs-friday-work.md)\n- [dsh-superagent (DeepSeek) vs Harness²](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.md)\n- [Devin vs Friday](https://www.anchorterminal.com/compare/devin-vs-friday-work.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Droid CLI vs Friday](https://www.anchorterminal.com/compare/droid-cli-vs-friday-work.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Pi vs Friday](https://www.anchorterminal.com/compare/earendil-pi-vs-friday-work.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Emdash vs Friday](https://www.anchorterminal.com/compare/emdash-vs-friday-work.md)\n- [Emdash vs Harness²](https://www.anchorterminal.com/compare/emdash-vs-harness2.md)\n- [Friday vs mini-swe-agent](https://www.anchorterminal.com/compare/friday-work-vs-mini-swe-agent.md)\n- [Friday vs OpenAI Agents API](https://www.anchorterminal.com/compare/friday-work-vs-openai-agents-api.md)\n- [Friday vs OpenAI Codex](https://www.anchorterminal.com/compare/friday-work-vs-openai-codex.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- [Agent Relay vs Friday](https://www.anchorterminal.com/compare/agent-relay-vs-friday-work.md)\n- [Clawboo vs Friday](https://www.anchorterminal.com/compare/clawboo-vs-friday-work.md)\n- [CLI Manager vs Friday](https://www.anchorterminal.com/compare/cli-manager-vs-friday-work.md)\n- [Friday vs Gemini CLI](https://www.anchorterminal.com/compare/friday-work-vs-gemini-cli.md)\n- [Friday vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/friday-work-vs-github-copilot-cli.md)\n- [Friday vs goose](https://www.anchorterminal.com/compare/friday-work-vs-goose.md)\n- [Friday vs Harness](https://www.anchorterminal.com/compare/friday-work-vs-harness-autonomous.md)\n- [Friday vs HarnessRouter](https://www.anchorterminal.com/compare/friday-work-vs-harnessrouter.md)\n- [Friday vs herdr](https://www.anchorterminal.com/compare/friday-work-vs-herdr.md)\n- [Friday vs Jules](https://www.anchorterminal.com/compare/friday-work-vs-jules.md)\n- [Friday vs Junie CLI](https://www.anchorterminal.com/compare/friday-work-vs-junie.md)\n- [Friday vs Kilo Code CLI](https://www.anchorterminal.com/compare/friday-work-vs-kilo-code-cli.md)\n- [Friday vs Kimi Code CLI](https://www.anchorterminal.com/compare/friday-work-vs-kimi-code-cli.md)\n- [Friday vs Kiro CLI](https://www.anchorterminal.com/compare/friday-work-vs-kiro-cli.md)\n- [Friday vs Letta](https://www.anchorterminal.com/compare/friday-work-vs-letta.md)\n- [Friday vs MiniMax Code](https://www.anchorterminal.com/compare/friday-work-vs-minimax-code.md)\n- [Friday vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/friday-work-vs-mistral-vibe-cli.md)\n- [Friday vs Muse Code](https://www.anchorterminal.com/compare/friday-work-vs-muse-code.md)\n- [Friday vs OpenCode](https://www.anchorterminal.com/compare/friday-work-vs-opencode.md)\n- [Friday vs OpenHands](https://www.anchorterminal.com/compare/friday-work-vs-openhands.md)\n- [Friday vs OpenMausBot](https://www.anchorterminal.com/compare/friday-work-vs-openmausbot.md)\n- [Friday vs Orca](https://www.anchorterminal.com/compare/friday-work-vs-orca.md)\n- [Friday vs Paperclip](https://www.anchorterminal.com/compare/friday-work-vs-paperclip.md)\n- [Friday vs Parallax](https://www.anchorterminal.com/compare/friday-work-vs-parallax-agents.md)\n- [Friday vs Paseo](https://www.anchorterminal.com/compare/friday-work-vs-paseo.md)\n- [Friday vs Prime Agent](https://www.anchorterminal.com/compare/friday-work-vs-prime-agent.md)\n- [Friday vs Qoder CLI](https://www.anchorterminal.com/compare/friday-work-vs-qoder-cli.md)\n- [Friday vs Qwen Code](https://www.anchorterminal.com/compare/friday-work-vs-qwen-code.md)\n- [Friday vs Mirror CLI](https://www.anchorterminal.com/compare/friday-work-vs-reflection-mirror.md)\n- [Friday vs Rovo Dev CLI](https://www.anchorterminal.com/compare/friday-work-vs-rovo-dev-cli.md)\n- [Friday vs Sculptor](https://www.anchorterminal.com/compare/friday-work-vs-sculptor.md)\n- [Friday vs T3 Code](https://www.anchorterminal.com/compare/friday-work-vs-t3-code.md)\n- [Friday vs Traycer](https://www.anchorterminal.com/compare/friday-work-vs-traycer.md)\n- [Friday vs Unstoppable](https://www.anchorterminal.com/compare/friday-work-vs-unstoppable.md)\n- [Friday vs Verdent](https://www.anchorterminal.com/compare/friday-work-vs-verdent.md)\n- [Friday vs Vibe-Trading](https://www.anchorterminal.com/compare/friday-work-vs-vibe-trading.md)\n- [Friday vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/friday-work-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": "Friday vs Harness²",
        "url": ""
      }
    ],
    "description": "Friday scores 65.3 (B) to Harness²'s 45 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Friday B 65.3",
      "Harness² E 45",
      "scores"
    ],
    "h1": "Friday vs Harness²",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/friday-work-vs-harness2",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Friday vs Harness² for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/friday-work-vs-harness2"
  },
  "tokens": {
    "markdown": 7150,
    "slim": 980
  },
  "version": 1
}
