# Harness² vs Paseo (slim)

> Paseo scores 62.1 (B) to Harness²'s 42 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/harness2-vs-paseo.md (~5,650 tokens) · this version ~2,230 tokens · JSON https://www.anchorterminal.com/compare/harness2-vs-paseo.json · canonical https://www.anchorterminal.com/compare/harness2-vs-paseo
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Paseo scores 62.1 (B) on agent readiness against Harness²'s 42 (E), and leads in every scored category. Both do agent harnesses.

- Harness²: E 42, rank #1290 of 1510 · https://www.anchorterminal.com/tools/harness2.min.md
- Paseo: B 62.1, rank #577 of 1510 · https://www.anchorterminal.com/tools/paseo.min.md
- Harness², good 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.
- Paseo, good for Developers who want parallel coding agents on their own machines with no telemetry, reachable from anywhere. Ahead on Reliability, 50 against 20; Schema & documentation, 65 against 51; Agent ergonomics, 70 against 59; Security & auth, 58 against 44; Payments & pricing, 60 against 40; Maintenance & community, 75 against 36; Transparency & trust, 68 against 49.

| Category | Harness² | Paseo |
| --- | --- | --- |
| Reliability (16%) | 20 | 50 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 51 | 65 |
| Agent ergonomics (13%) | 59 | 70 |
| Security & auth (14%) | 44 | 58 |
| Payments & pricing (10%) | 40 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 36 | 75 |
| Transparency & trust (7%) | 49 | 68 |

| Fact (where they differ) | Harness² | Paseo |
| --- | --- | --- |
| Vendor | Google (Google Research) | Mohamed Boudra |
| Licence | 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). | Apache-2.0 |
| Last release | 2026-10-08 | 2026-11-07 |
| Popularity | 4.2k stars | none |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Maintenance & community, Paseo +39: Harness² 36 (0.1.0, first committed on 8 October 2026, with a README fix on 13 October (30). No tags, releases or dated changelog entries (0). 42 pull requests (41 from outside contributors, one from Dependabot) and 6 issues open on 18 October, against one pull request and no issues closed. No outside change is on main, which has three commits by the authors, and reply times couldn't be read (3 of 25). Not on PyPI and no SDK (0). No CI. Dependencies are pinned by version and upstream checkouts by commit, a ruff configuration is in pyproject.toml, and Dependabot's litellm bump of 8 October is still open (3 of 10). 36 in all.); Paseo 75 (v0.15.3 and commits on 7 November 2026 (30). More than three releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current builds (15). CI on push (10). 30 + 20 + 0 + 15 + 10 = 75.)
- Reliability, Paseo +30: Harness² 20 (Local-package reading. Not on PyPI (the release feed for harness2 answers 404). 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). No CI workflow in the repository. tests/test_workflow.py holds five unit tests over the deterministic demo, which needs no credentials (5 of 25). Six issues and 42 pull requests were open on 18 October, the pull requests mostly fixes by their titles, such as the missing .env.example, report failures, seeds lost between refinement and grading, and resume. None is merged and no issue is closed. Issue text and replies couldn't be read (5 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). 20 in all.); Paseo 50 (Local software. Desktop builds, an Android APK, a Docker image and a Nix package (20). ci.yml on the repository; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). CHANGELOG.md (15). Version 0.15.3 (0). 20 + 15 + 0 + 15 + 0 = 50.)
- Payments & pricing, Paseo +20: Harness² 40 (No payment protocol (0). Read with the self-hosted rule, as for the other harnesses. Free under Apache-2.0 with nothing to buy (20). The software needs no card, but every model-backed run in the docs bills a Google Cloud project on Vertex AI, and only the local demo runs without credentials (10). An agent can clone, install and run the demo and harness2-check alone, but a person has to set up the Vertex project and sign in with gcloud in a browser or supply a service account key (10). 40 in all.); Paseo 60 (Free self-hosted software with nothing to buy, so 0 for a protocol and 20 each for public pricing, a free tier and onboarding with no sign-up, 60.)
- Transparency & trust, Paseo +19: 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). 48 in all.); Paseo 68 (Apache 2.0 for everything but third-party components (30). No telemetry and agents run on your machine (22 of 30). CHANGELOG.md, no deprecation policy (10). States no telemetry (20). 30 + 22 + 10 + 20 = 82.)
- Schema & documentation, Paseo +14: Harness² 51 (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, but the quick start's `cp .env.example .env` fails because the file isn't shipped (8 of 15). Version 0.1.0 with no changelog (3 of 15). 51 in all.); Paseo 65 (Harness reading. Public docs, a CLI and plugin examples in the repository (65).)
- Security & auth, Paseo +14: Harness² 44 (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. Against that, executors inherit the whole shell environment (the editor channel drops only five Anthropic variables), and no .gitignore keeps a filled-in .env out of commits (20). 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). 44 in all.); Paseo 58 (Harness reading. The README says no telemetry, tracking or forced log-ins (30 of 30). Worktree per agent, on your own machine (10 of 20). No prompt-injection guidance (5). No audit log (5). SECURITY.md (8). 30 + 10 + 5 + 5 + 8 = 58.)