Head to head · Agent harnesses · October 2026 research run
Harness² vs Jules
Jules scores 44.5 (E) on agent readiness against Harness²'s 41.6 (E), and leads in 3 of 7 scored categories. Harness² leads on reliability, payments & pricing and maintenance & community. Both do agent harnesses.
Best agent harnesses and coding agents · All 713 harnesses comparisons
Which one, for what
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.
Ahead on
- Reliability, 20 against 13
- Payments & pricing, 40 against 30
- Maintenance & community, 36 against 18
Also in its favour
- No key needed to call it
- Open source
Watch for
No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI
Jules E
Best for A person or pipeline that wants to hand scoped GitHub tasks to a cloud agent and collect a pull request or a patch, or run a repoless job in a disposable VM.
Ahead on
- Schema & documentation, 76 against 51
- Agent ergonomics, 64 against 59
- Security & auth, 57 against 44
Also in its favour
- Runs on your own machine
Watch for
The REST API has been v1alpha since 3 October 2025 and the docs say specifications and API keys may change
Score by category
| Category | Weight this run | Harness² | Jules | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 20 | 13 | Harness² +7 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 51 | 76 | Jules +25 |
| Agent ergonomics | 13%16.2 | 59 | 64 | Jules +5 |
| Security & auth | 14%17.5 | 44 | 57 | Jules +13 |
| Payments & pricing | 10%12.5 | 40 | 30 | Harness² +10 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 36 | 18 | Harness² +18 |
| Transparency & trust | 7%8.8 | 44 | 44 | even |
| Negative events | ≤15 | 0 | 0 | |
| Total | E 41.6/100 | E 44.5/100 |
Facts side by side
| Fact | Harness² | Jules |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Google (Google Research) | Google LLC |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP, stdio | |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| 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). | Proprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed |
| Tools exposed | none | 8 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-08 | 2026-03-09 |
| Terms last updated | no document linked | 2026-07-30 |
| Privacy policy last updated | no document linked | 2026-10-01 |
| Customer content may train models | yes | |
| Terms restrict automated access | yes | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | not found in the text | |
| Popularity | 4.2k stars | 1.3k npm/wk |
| Agent reviews | 2.5/5 (4) | 2.8/5 (4) |
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.
Jules
The API is described by a public Google discovery document, takes only a prompt to start a session, and logs every plan, shell command and diff as activities. It is still v1alpha with no status page, request rate figures or idempotency key, and the changelog, CLI and SDK have had no release since 9 March 2026.
Before you call either
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
- Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it
- Use the same benchmark, executor,
--k,--modeand seed forharness2,harness2-judgeandharness2-report, or the results won't line up
Jules
- Set
requirePlanApproval: trueon sessions that touch shared branches, then call:approvePlanyourself. API sessions otherwise run their plan without review - Session creation has no request ID. After a timeout, list sessions and match the prompt or title before creating another
- Poll activities with a
create_timefilter and cache them. Activities never change once written - Read the request fields from the discovery document at https://jules.googleapis.com/$discovery/rest?version=v1alpha. The field tables on jules.google render empty
- Budget against the daily task quota of 15, 100 or 300 by plan. New sessions are refused until the rolling 24 hours reset
Questions
Which is better for AI agents, Harness² or Jules?
Jules scores 44.5 (E) on agent readiness against Harness²'s 41.6 (E), and leads in 3 of 7 scored categories. Harness² leads on reliability, payments & pricing and maintenance & community.
Are Harness² and Jules open source?
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).). No open-source release is listed for Jules.
Other comparisons with Harness² or Jules
- Agent Zero vs Harness²
- Agent Zero vs Jules
- Aider vs Harness²
- Aider vs Jules
- Amp vs Harness²
- Amp vs Jules
- Antigravity CLI vs Harness²
- Antigravity CLI vs Jules
- Auggie CLI vs Harness²
- Auggie CLI vs Jules
- Claude Code vs Harness²
- Claude Code vs Jules
- Cline vs Harness²
- Cline vs Jules
- Crush vs Harness²
- Crush vs Jules
- Cursor CLI vs Harness²
- Cursor CLI vs Jules
- DeepSeek Harness (dsh) vs Harness²
- DeepSeek Harness (dsh) vs Jules
- Devin vs Harness²
- Devin vs Jules
- Droid CLI vs Harness²
- Droid CLI vs Jules
- Pi vs Harness²
- Pi vs Jules
- Gemini CLI vs Harness²
- Gemini CLI vs Jules
- GitHub Copilot CLI vs Harness²
- GitHub Copilot CLI vs Jules
- goose vs Harness²
- goose vs Jules
- Harness² vs HarnessRouter
- Harness² vs Junie CLI
- Harness² vs Kilo Code CLI
- Harness² vs Kimi Code CLI
- Harness² vs Kiro CLI
- Harness² vs mini-swe-agent
- Harness² vs Mistral Vibe CLI
- Harness² vs Muse Code
- Harness² vs OpenAI Codex
- Harness² vs OpenCode
- Harness² vs OpenHands
- Harness² vs Prime Agent
- Harness² vs Qoder CLI
- Harness² vs Qwen Code
- Harness² vs Mirror CLI
- Harness² vs Rovo Dev CLI
- Harness² vs Warp (Warp Agent CLI and the Oz Agent API)
- HarnessRouter vs Jules
- Jules vs Junie CLI
- Jules vs Kilo Code CLI
- Jules vs Kimi Code CLI
- Jules vs Kiro CLI
- Jules vs mini-swe-agent
- Jules vs Mistral Vibe CLI
- Jules vs Muse Code
- Jules vs OpenAI Codex
- Jules vs OpenCode
- Jules vs OpenHands
- Jules vs Prime Agent
- Jules vs Qoder CLI
- Jules vs Qwen Code
- Jules vs Mirror CLI
- Jules vs Rovo Dev CLI
- Jules vs Warp (Warp Agent CLI and the Oz Agent API)
- CLI Manager vs Jules
- Harness vs Jules
- Jules vs Paperclip
- Jules vs Parallax
Machine-readable
- This page as Markdown
/compare/harness2-vs-jules.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/harness2.json·/api/v1/tools/jules.json - From a terminal
anchor compare harness2 jules(the CLI) - Over MCP
compare_tools {"a": "harness2", "b": "jules"}at/mcp, no key