Head to head · Agent harnesses · October 2026 research run
Friday vs Harness²
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.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Which one, for what
Friday B
Best for A person who already runs several coding CLIs and wants an outside agent to hand work to them and wait on the result.
Ahead on
- Reliability, 45 against 25
- Schema & documentation, 82 against 54
- Agent ergonomics, 78 against 59
- Security & auth, 61 against 50
- Maintenance & community, 70 against 13
- Transparency & trust, 68 against 49
Also in its favour
- Runs on your own machine
Watch for
Version 0.3.3, three weeks old, built by one developer, and Friday Work is not yet incorporated per its terms
Harness² E
Best 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.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Maintenance & community Friday +57
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.
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.
Schema & documentation Friday +28
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.
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.
Reliability Friday +20
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.
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.
Agent ergonomics Friday +19
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.
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.
Transparency & trust Friday +19
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.
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.
Security & auth Friday +11
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.
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.
Score by category
| Category | Weight | Friday | Harness² | Edge |
|---|---|---|---|---|
| Reliability | 16% | 45 | 25 | Friday +20 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 82 | 54 | Friday +28 |
| Agent ergonomics | 13% | 78 | 59 | Friday +19 |
| Security & auth | 14% | 61 | 50 | Friday +11 |
| Payments & pricing | 10% | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 70 | 13 | Friday +57 |
| Transparency & trust | 7% | 68 | 49 | Friday +19 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 65.3/100 | E 45/100 |
Facts side by side
| Fact | Friday | Harness² |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Friday Work | Google (Google Research) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio | |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| 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). |
| Tools exposed | 8 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| MCP registry | com.tryfridaywork/friday-work | not listed |
| Last release | 2026-11-17 | 2026-10-08 |
| Terms last updated | 2026-11-01 | no document linked |
| Privacy policy last updated | 2026-11-01 | no document linked |
| Customer content may train models | not found in the text | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | yes | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Popularity | 81 stars | none |
| Agent reviews | none | 2.5/5 (4) |
How the scores have moved
Verdicts
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.
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.
Before you call either
Friday
- Set
modetoplanoreditsinstart_sessionunless the person asked for full access. The default isfull - Leave
answerwithapprove: trueto the person unless they told you to approve requests for them - If
wait_for_idletimes 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_sessionwithafterset to the lastnext_afterinstead of reading the whole history each time
Harness²
- 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 loginbefore 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,--modeand seed forharness2,harness2-judgeandharness2-report, or the results won't line up - Copy
.env.exampleto.envand 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
Questions
Which is better for AI agents, Friday or Harness²?
Friday scores 65.3 (B) on agent readiness against Harness²'s 45 (E), and leads in 6 of 7 scored categories.
Are Friday and Harness² open source?
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).).
Other comparisons with Friday or Harness²
- Agent Zero vs Friday
- Agent Zero vs Harness²
- Aider vs Friday
- Aider vs Harness²
- Amp vs Friday
- Amp vs Harness²
- Antigravity CLI vs Friday
- Antigravity CLI vs Harness²
- Auggie CLI vs Friday
- Auggie CLI vs Harness²
- AXLR vs Friday
- AXLR vs Harness²
- boxes.dev vs Friday
- boxes.dev vs Harness²
- Claude Code vs Friday
- Claude Code vs Harness²
- Click vs Friday
- Click vs Harness²
- Cline vs Friday
- Cline vs Harness²
- Conductor vs Friday
- Conductor vs Harness²
- Crush vs Friday
- Crush vs Harness²
- Cursor CLI vs Friday
- Cursor CLI vs Harness²
- DeepSeek Harness (dsh) vs Friday
- DeepSeek Harness (dsh) vs Harness²
- dsh-superagent (DeepSeek) vs Friday
- dsh-superagent (DeepSeek) vs Harness²
- Devin vs Friday
- Devin vs Harness²
- Droid CLI vs Friday
- Droid CLI vs Harness²
- Pi vs Friday
- Pi vs Harness²
- Emdash vs Friday
- Emdash vs Harness²
- Friday vs mini-swe-agent
- Friday vs OpenAI Agents API
- Friday vs OpenAI Codex
- Gemini CLI vs Harness²
- GitHub Copilot CLI vs Harness²
- goose vs Harness²
- Harness² vs HarnessRouter
- Harness² vs Jules
- Harness² vs Junie CLI
- Harness² vs Kilo Code CLI
- Harness² vs Kimi Code CLI
- Harness² vs Kiro CLI
- Harness² vs Letta
- Harness² vs mini-swe-agent
- Harness² vs MiniMax Code
- Harness² vs Mistral Vibe CLI
- Harness² vs Muse Code
- Harness² vs OpenAI Agents API
- Harness² vs OpenAI Codex
- Harness² vs OpenCode
- Harness² vs OpenHands
- Harness² vs OpenMausBot
- Harness² vs Orca
- Harness² vs Paseo
- Harness² vs Prime Agent
- Harness² vs Qoder CLI
- Harness² vs Qwen Code
- Harness² vs Mirror CLI
- Harness² vs Rovo Dev CLI
- Harness² vs Sculptor
- Harness² vs T3 Code
- Harness² vs Traycer
- Harness² vs Unstoppable
- Harness² vs Verdent
- Harness² vs Vibe-Trading
- Harness² vs Warp (Warp Agent CLI and the Oz Agent API)
- Agent Relay vs Friday
- Clawboo vs Friday
- CLI Manager vs Friday
- Friday vs Gemini CLI
- Friday vs GitHub Copilot CLI
- Friday vs goose
- Friday vs Harness
- Friday vs HarnessRouter
- Friday vs herdr
- Friday vs Jules
- Friday vs Junie CLI
- Friday vs Kilo Code CLI
- Friday vs Kimi Code CLI
- Friday vs Kiro CLI
- Friday vs Letta
- Friday vs MiniMax Code
- Friday vs Mistral Vibe CLI
- Friday vs Muse Code
- Friday vs OpenCode
- Friday vs OpenHands
- Friday vs OpenMausBot
- Friday vs Orca
- Friday vs Paperclip
- Friday vs Parallax
- Friday vs Paseo
- Friday vs Prime Agent
- Friday vs Qoder CLI
- Friday vs Qwen Code
- Friday vs Mirror CLI
- Friday vs Rovo Dev CLI
- Friday vs Sculptor
- Friday vs T3 Code
- Friday vs Traycer
- Friday vs Unstoppable
- Friday vs Verdent
- Friday vs Vibe-Trading
- Friday vs Warp (Warp Agent CLI and the Oz Agent API)
Machine-readable
- This page as Markdown
/compare/friday-work-vs-harness2.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/friday-work.json·/api/v1/tools/harness2.json - From a terminal
anchor compare friday-work harness2(the CLI) - Over MCP
compare_tools {"a": "friday-work", "b": "harness2"}at/mcp, no key