# Harness² vs T3 Code

> T3 Code scores 51.9 (D) to Harness²'s 42 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/harness2-vs-t3-code
- Markdown: https://www.anchorterminal.com/compare/harness2-vs-t3-code.md (~5,400 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

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: grade E, 42/100, rank #1272 of 1486. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json
- T3 Code: grade D, 51.9/100, rank #1002 of 1486. Markdown https://www.anchorterminal.com/tools/t3-code.md · JSON https://www.anchorterminal.com/api/v1/tools/t3-code.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 1500 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### Harness² (E)

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

Watch for: No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI

### T3 Code (D)

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

Watch for: Usage data on by default, with hashed OpenAI and Claude account identifiers, and relay traces to Axiom


## 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.

## Score by category

| Category | Weight | Harness² | T3 Code | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 20 | 43 | T3 Code +23 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 51 | 55 | T3 Code +4 |
| Agent ergonomics | 13% (16.2 this run) | 59 | 60 | T3 Code +1 |
| Security & auth | 14% (17.5 this run) | 44 | 35 | Harness² +9 |
| Payments & pricing | 10% (12.5 this run) | 40 | 60 | T3 Code +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 36 | 75 | T3 Code +39 |
| Transparency & trust | 7% (8.8 this run) | 49 | 51 | T3 Code +2 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **42 · E** | **51.9 · D** | |

## Facts side by side

| Fact | Harness² | T3 Code |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Google (Google Research) | T3 Tools Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| 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 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-08 | 2026-11-06 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | 4.2k stars | none |
| Agent reviews | 2.5/5 (4) | none |

## How the scores have moved

### Harness²

- +0.4 on 27 October 2026: checklist

### T3 Code

No score change since it was listed.

## Verdicts

**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.

**T3 Code.** A fast-moving open-source way to run and steer several coding agents from desktop, browser or phone, using the subscriptions you already have. It's pre-1.0, and it sends usage data by default, including hashed identifiers for your OpenAI and Claude accounts, with the opt-out documented outside the README.

## Before you call either

### Harness²

1. 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
2. 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`
3. 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
4. Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it
5. Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up

### T3 Code

1. Set T3CODE_TELEMETRY_ENABLED=false before starting the server if you don't want usage events sent
2. Install and log in to at least one provider CLI first, such as codex login or claude auth login
3. Use a managed policy to fix settings across a team

## Questions

### Which is better for AI agents, Harness² or T3 Code?

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.

### Are Harness² and T3 Code open source?

Yes. 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).). T3 Code is open source (MIT).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-t3-code.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-t3-code.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "harness2", "b": "t3-code"}`. From a terminal: `anchor compare harness2 t3-code`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/t3-code.json

## Other comparisons with Harness² or T3 Code

- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)
- [Agent Zero vs T3 Code](https://www.anchorterminal.com/compare/agent-zero-vs-t3-code.md)
- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)
- [Aider vs T3 Code](https://www.anchorterminal.com/compare/aider-vs-t3-code.md)
- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)
- [Amp vs T3 Code](https://www.anchorterminal.com/compare/amp-vs-t3-code.md)
- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)
- [Antigravity CLI vs T3 Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-t3-code.md)
- [Auggie CLI vs Harness²](https://www.anchorterminal.com/compare/auggie-vs-harness2.md)
- [Auggie CLI vs T3 Code](https://www.anchorterminal.com/compare/auggie-vs-t3-code.md)
- [AXLR vs Harness²](https://www.anchorterminal.com/compare/axlr-vs-harness2.md)
- [AXLR vs T3 Code](https://www.anchorterminal.com/compare/axlr-vs-t3-code.md)
- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)
- [Claude Code vs T3 Code](https://www.anchorterminal.com/compare/claude-code-vs-t3-code.md)
- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)
- [Cline vs T3 Code](https://www.anchorterminal.com/compare/cline-vs-t3-code.md)
- [Conductor vs Harness²](https://www.anchorterminal.com/compare/conductor-vs-harness2.md)
- [Conductor vs T3 Code](https://www.anchorterminal.com/compare/conductor-vs-t3-code.md)
- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)
- [Crush vs T3 Code](https://www.anchorterminal.com/compare/crush-vs-t3-code.md)
- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)
- [Cursor CLI vs T3 Code](https://www.anchorterminal.com/compare/cursor-cli-vs-t3-code.md)
- [DeepSeek Harness (dsh) vs Harness²](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.md)
- [DeepSeek Harness (dsh) vs T3 Code](https://www.anchorterminal.com/compare/deepseek-harness-vs-t3-code.md)
- [dsh-superagent (DeepSeek) vs Harness²](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harness2.md)
- [dsh-superagent (DeepSeek) vs T3 Code](https://www.anchorterminal.com/compare/deepseek-superagent-vs-t3-code.md)
- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)
- [Devin vs T3 Code](https://www.anchorterminal.com/compare/devin-vs-t3-code.md)
- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)
- [Droid CLI vs T3 Code](https://www.anchorterminal.com/compare/droid-cli-vs-t3-code.md)
- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)
- [Pi vs T3 Code](https://www.anchorterminal.com/compare/earendil-pi-vs-t3-code.md)
- [Emdash vs Harness²](https://www.anchorterminal.com/compare/emdash-vs-harness2.md)
- [Emdash vs T3 Code](https://www.anchorterminal.com/compare/emdash-vs-t3-code.md)
- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)
- [Gemini CLI vs T3 Code](https://www.anchorterminal.com/compare/gemini-cli-vs-t3-code.md)
- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)
- [GitHub Copilot CLI vs T3 Code](https://www.anchorterminal.com/compare/github-copilot-cli-vs-t3-code.md)
- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)
- [goose vs T3 Code](https://www.anchorterminal.com/compare/goose-vs-t3-code.md)
- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)
- [Harness² vs Jules](https://www.anchorterminal.com/compare/harness2-vs-jules.md)
- [Harness² vs Junie CLI](https://www.anchorterminal.com/compare/harness2-vs-junie.md)
- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)
- [Harness² vs Kimi Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kimi-code-cli.md)
- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)
- [Harness² vs Letta](https://www.anchorterminal.com/compare/harness2-vs-letta.md)
- [Harness² vs mini-swe-agent](https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.md)
- [Harness² vs MiniMax Code](https://www.anchorterminal.com/compare/harness2-vs-minimax-code.md)
- [Harness² vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harness2-vs-mistral-vibe-cli.md)
- [Harness² vs Muse Code](https://www.anchorterminal.com/compare/harness2-vs-muse-code.md)
- [Harness² vs OpenAI Agents API](https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api.md)
- [Harness² vs OpenAI Codex](https://www.anchorterminal.com/compare/harness2-vs-openai-codex.md)
- [Harness² vs OpenCode](https://www.anchorterminal.com/compare/harness2-vs-opencode.md)
- [Harness² vs OpenHands](https://www.anchorterminal.com/compare/harness2-vs-openhands.md)
- [Harness² vs OpenMausBot](https://www.anchorterminal.com/compare/harness2-vs-openmausbot.md)
- [Harness² vs Orca](https://www.anchorterminal.com/compare/harness2-vs-orca.md)
- [Harness² vs Paseo](https://www.anchorterminal.com/compare/harness2-vs-paseo.md)
- [Harness² vs Prime Agent](https://www.anchorterminal.com/compare/harness2-vs-prime-agent.md)
- [Harness² vs Qoder CLI](https://www.anchorterminal.com/compare/harness2-vs-qoder-cli.md)
- [Harness² vs Qwen Code](https://www.anchorterminal.com/compare/harness2-vs-qwen-code.md)
- [Harness² vs Mirror CLI](https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md)
- [Harness² vs Rovo Dev CLI](https://www.anchorterminal.com/compare/harness2-vs-rovo-dev-cli.md)
- [Harness² vs Sculptor](https://www.anchorterminal.com/compare/harness2-vs-sculptor.md)
- [Harness² vs Traycer](https://www.anchorterminal.com/compare/harness2-vs-traycer.md)
- [Harness² vs Unstoppable](https://www.anchorterminal.com/compare/harness2-vs-unstoppable.md)
- [Harness² vs Verdent](https://www.anchorterminal.com/compare/harness2-vs-verdent.md)
- [Harness² vs Vibe-Trading](https://www.anchorterminal.com/compare/harness2-vs-vibe-trading.md)
- [Harness² vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/harness2-vs-warp.md)
- [HarnessRouter vs T3 Code](https://www.anchorterminal.com/compare/harnessrouter-vs-t3-code.md)
- [Jules vs T3 Code](https://www.anchorterminal.com/compare/jules-vs-t3-code.md)
- [Junie CLI vs T3 Code](https://www.anchorterminal.com/compare/junie-vs-t3-code.md)
- [Kilo Code CLI vs T3 Code](https://www.anchorterminal.com/compare/kilo-code-cli-vs-t3-code.md)
- [Kimi Code CLI vs T3 Code](https://www.anchorterminal.com/compare/kimi-code-cli-vs-t3-code.md)
- [Kiro CLI vs T3 Code](https://www.anchorterminal.com/compare/kiro-cli-vs-t3-code.md)
- [Letta vs T3 Code](https://www.anchorterminal.com/compare/letta-vs-t3-code.md)
- [mini-swe-agent vs T3 Code](https://www.anchorterminal.com/compare/mini-swe-agent-vs-t3-code.md)
- [MiniMax Code vs T3 Code](https://www.anchorterminal.com/compare/minimax-code-vs-t3-code.md)
- [Mistral Vibe CLI vs T3 Code](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-t3-code.md)
- [Muse Code vs T3 Code](https://www.anchorterminal.com/compare/muse-code-vs-t3-code.md)
- [OpenAI Agents API vs T3 Code](https://www.anchorterminal.com/compare/openai-agents-api-vs-t3-code.md)
- [OpenAI Codex vs T3 Code](https://www.anchorterminal.com/compare/openai-codex-vs-t3-code.md)
- [OpenCode vs T3 Code](https://www.anchorterminal.com/compare/opencode-vs-t3-code.md)
- [OpenHands vs T3 Code](https://www.anchorterminal.com/compare/openhands-vs-t3-code.md)
- [Orca vs T3 Code](https://www.anchorterminal.com/compare/orca-vs-t3-code.md)
- [Paseo vs T3 Code](https://www.anchorterminal.com/compare/paseo-vs-t3-code.md)
- [Prime Agent vs T3 Code](https://www.anchorterminal.com/compare/prime-agent-vs-t3-code.md)
- [Qoder CLI vs T3 Code](https://www.anchorterminal.com/compare/qoder-cli-vs-t3-code.md)
- [Qwen Code vs T3 Code](https://www.anchorterminal.com/compare/qwen-code-vs-t3-code.md)
- [Mirror CLI vs T3 Code](https://www.anchorterminal.com/compare/reflection-mirror-vs-t3-code.md)
- [Rovo Dev CLI vs T3 Code](https://www.anchorterminal.com/compare/rovo-dev-cli-vs-t3-code.md)
- [Sculptor vs T3 Code](https://www.anchorterminal.com/compare/sculptor-vs-t3-code.md)
- [T3 Code vs Traycer](https://www.anchorterminal.com/compare/t3-code-vs-traycer.md)
- [T3 Code vs Unstoppable](https://www.anchorterminal.com/compare/t3-code-vs-unstoppable.md)
- [T3 Code vs Verdent](https://www.anchorterminal.com/compare/t3-code-vs-verdent.md)
- [T3 Code vs Vibe-Trading](https://www.anchorterminal.com/compare/t3-code-vs-vibe-trading.md)
- [T3 Code vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/t3-code-vs-warp.md)
- [Clawboo vs T3 Code](https://www.anchorterminal.com/compare/clawboo-vs-t3-code.md)
- [CLI Manager vs T3 Code](https://www.anchorterminal.com/compare/cli-manager-vs-t3-code.md)
- [Harness vs T3 Code](https://www.anchorterminal.com/compare/harness-autonomous-vs-t3-code.md)
- [OpenMausBot vs T3 Code](https://www.anchorterminal.com/compare/openmausbot-vs-t3-code.md)
- [Paperclip vs T3 Code](https://www.anchorterminal.com/compare/paperclip-vs-t3-code.md)
- [Parallax vs T3 Code](https://www.anchorterminal.com/compare/parallax-agents-vs-t3-code.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp