# Harness² vs T3 Code (slim)

> T3 Code scores 51.9 (D) 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-t3-code.md (~5,400 tokens) · this version ~1,830 tokens · JSON https://www.anchorterminal.com/compare/harness2-vs-t3-code.json · canonical https://www.anchorterminal.com/compare/harness2-vs-t3-code
- 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)

T3 Code scores 51.9 (D) on agent readiness against Harness²'s 42 (E), and leads in 6 of 7 scored categories. Harness² leads on security & auth. Both do agent harnesses.

- Harness²: E 42, rank #1272 of 1486 · https://www.anchorterminal.com/tools/harness2.min.md
- T3 Code: D 51.9, rank #1002 of 1486 · https://www.anchorterminal.com/tools/t3-code.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. Ahead on Security & auth, 44 against 35.
- T3 Code, good for Developers who want one app, including on their phone, to drive several coding agents they already pay for. Ahead on Reliability, 43 against 20; Payments & pricing, 60 against 40; Maintenance & community, 75 against 36.

| Category | Harness² | T3 Code |
| --- | --- | --- |
| Reliability (16%) | 20 | 43 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 51 | 55 |
| Agent ergonomics (13%) | 59 | 60 |
| Security & auth (14%) | 44 | 35 |
| Payments & pricing (10%) | 40 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 36 | 75 |
| Transparency & trust (7%) | 49 | 51 |

| Fact (where they differ) | Harness² | T3 Code |
| --- | --- | --- |
| Vendor | Google (Google Research) | T3 Tools Inc. |
| 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). | MIT |
| Last release | 2026-10-08 | 2026-11-06 |
| Popularity | 4.2k stars | none |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Maintenance & community, T3 Code +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.); T3 Code 75 (Commits and nightly tags on 6 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 official apps and install script (15). CI on push (10). 30 + 20 + 0 + 15 + 10 = 75.)
- Reliability, T3 Code +23: 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.); T3 Code 43 (Local software. An install script and desktop and mobile apps from the vendor (20). ci.yml and windows-tests.yml run 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). Stable tags v0.1.5 to v0.1.7 with many nightlies, no changelog file (8). Version 0.1.7 (0). 20 + 15 + 0 + 8 + 0 = 43.)
- Payments & pricing, T3 Code +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.); T3 Code 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.)
- Security & auth, Harness² +9: 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.); T3 Code 35 (Harness reading. Product usage events go by default to ingest.t3.codes and PostHog, with hashed identifiers for your T3 Connect, OpenAI and Claude accounts, and relay traces to Axiom, which can include machine names and error text. Off with T3CODE_TELEMETRY_ENABLED=false or a managed policy. Disclosed in docs/user/telemetry.md, not the README (10 of 30). Permission modes and managed policies (12 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 10 + 12 + 5 + 5 + 3 = 35.)