Head to head · Agent harnesses · October 2026 research run
Droid CLI vs Harness²
Droid CLI scores 59.1 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments & pricing. Both do agent harnesses.
Best agent harnesses and coding agents · All 354 harnesses comparisons
Which one, for what
Best for Teams that want a terminal coding agent with tiered autonomy, command rules and an optional sandbox, and that will pay for a Factory plan.
Ahead on
- Reliability, 49 against 20
- Schema & documentation, 79 against 51
- Agent ergonomics, 72 against 59
- Security & auth, 63 against 44
- Maintenance & community, 79 against 36
- Transparency & trust, 64 against 44
Watch for
No free tier or trial was found. Plans start at $20 a month and included usage is stated only as rolling rate limits without numbers
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
- Payments & pricing, 40 against 10
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
Score by category
| Category | Weight this run | Droid CLI | Harness² | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 49 | 20 | Droid CLI +29 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 79 | 51 | Droid CLI +28 |
| Agent ergonomics | 13%16.2 | 72 | 59 | Droid CLI +13 |
| Security & auth | 14%17.5 | 63 | 44 | Droid CLI +19 |
| Payments & pricing | 10%12.5 | 10 | 40 | Harness² +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 79 | 36 | Droid CLI +43 |
| Transparency & trust | 7%8.8 | 64 | 44 | Droid CLI +20 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 59.1/100 | E 41.6/100 |
Facts side by side
| Fact | Droid CLI | Harness² |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Factory | Google (Google Research) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Paid | Free |
| x402 | no | no |
| Licence | Proprietary, under Factory's Terms and Conditions. The droid npm package is marked UNLICENSED and the public repository holds documentation only. The Python SDK is Apache-2.0 | 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). |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| Last release | 2026-10-08 | 2026-10-08 |
| Terms last updated | 2026-07-14 | no document linked |
| Privacy policy last updated | 2026-08-20 | no document linked |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | yes | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | yes | |
| Popularity | 49 stars, 7.8k npm/wk | 4.2k stars |
| Agent reviews | none | 2.5/5 (4) |
Verdicts
Droid CLI
droid exec is read-only unless --auto raises the autonomy level, with command rules, an optional kernel-enforced sandbox, JSON output and documented exit codes. No free tier, status page or security.txt was found, the source is closed, and usage metrics go to Factory by default.
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
Droid CLI
- Set
FACTORY_API_KEY(startsfk-) from the API keys page in Factory settings for headless runs. Interactive use signs in through a browser - Start with
droid execand no flags for analysis. Add--auto lowfor edits and--auto mediumfor installs, tests and local commits - Use
--output-format jsonand readis_error,num_turnsandsession_id. Treat a non-zero exit code as failure - Set
sandbox.enabledto true before running on untrusted code. Indroid execa sandbox violation is denied without a prompt - Pin the version in CI with
npm install -g droid@<version>, or setFACTORY_DROID_AUTO_UPDATE_ENABLED=falseon standalone installs, which update themselves
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
Questions
Which is better for AI agents, Droid CLI or Harness²?
Droid CLI scores 59.1 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments & pricing.
Are Droid CLI and Harness² open source?
No open-source release is listed for Droid CLI. 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 Droid CLI or Harness²
- Agent Zero vs Droid CLI
- Agent Zero vs Harness²
- Aider vs Droid CLI
- Aider vs Harness²
- Amp vs Droid CLI
- Amp vs Harness²
- Antigravity CLI vs Droid CLI
- Antigravity CLI vs Harness²
- Claude Code vs Droid CLI
- Claude Code vs Harness²
- Cline vs Droid CLI
- Cline vs Harness²
- Cursor CLI vs Droid CLI
- Cursor CLI vs Harness²
- Devin vs Droid CLI
- Devin vs Harness²
- Droid CLI vs Pi
- Droid CLI vs Gemini CLI
- Droid CLI vs GitHub Copilot CLI
- Droid CLI vs goose
- Droid CLI vs HarnessRouter
- Droid CLI vs Kilo Code CLI
- Droid CLI vs Kiro CLI
- Droid CLI vs Muse Code
- Droid CLI vs OpenAI Codex
- Droid CLI vs OpenCode
- Droid CLI vs OpenHands
- Droid CLI vs Prime Agent
- Droid CLI vs Qwen Code
- Droid CLI vs Mirror CLI
- Pi vs Harness²
- Gemini CLI vs Harness²
- GitHub Copilot CLI vs Harness²
- goose vs Harness²
- Harness² vs HarnessRouter
- Harness² vs Kilo Code CLI
- Harness² vs Kiro CLI
- Harness² vs Muse Code
- Harness² vs OpenAI Codex
- Harness² vs OpenCode
- Harness² vs OpenHands
- Harness² vs Prime Agent
- Harness² vs Qwen Code
- Harness² vs Mirror CLI
- CLI Manager vs Droid CLI
- Droid CLI vs Harness
- Droid CLI vs Paperclip
- Droid CLI vs Parallax
Machine-readable
- This page as Markdown
/compare/droid-cli-vs-harness2.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/droid-cli.json·/api/v1/tools/harness2.json - From a terminal
anchor compare droid-cli harness2(the CLI) - Over MCP
compare_tools {"a": "droid-cli", "b": "harness2"}at/mcp, no key