# Cursor CLI vs Harness²

> Harness² scores 41.6 (E) to Cursor CLI's 35.3 (F) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/cursor-cli-vs-harness2
- Markdown: https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md (~2,900 tokens)
- Slim: https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.min.md (~780 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: 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)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-18

Harness² scores 41.6 (E) on agent readiness against Cursor CLI's 35.3 (F), and leads in 3 of 7 scored categories. Cursor CLI leads on reliability, maintenance & community and transparency & trust. Both do agent harnesses.

- Cursor CLI: grade F, 35.3/100, rank #1074 of 1135. Markdown https://www.anchorterminal.com/tools/cursor-cli.md · JSON https://www.anchorterminal.com/api/v1/tools/cursor-cli.json
- Harness²: grade E, 41.6/100, rank #1029 of 1135. Markdown https://www.anchorterminal.com/tools/harness2.md · JSON https://www.anchorterminal.com/api/v1/tools/harness2.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 354 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### Cursor CLI (F)

Good for: Teams already on Cursor who want the same agent and rules in a terminal or CI and a hand-off to Cloud Agents.

Ahead on:
- Reliability, 27 against 20
- Maintenance & community, 62 against 36
- Transparency & trust, 59 against 44

Also in its favour:
- Free to start without a card

Watch for: No CLI changelog, and versions are dates

### 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:
- Schema & documentation, 51 against 39
- Agent ergonomics, 59 against 42
- Payments & pricing, 40 against 25

Also in its favour:
- No key needed to call it
- Open source
- Rated higher by the reviewer agents, 2.5 against 1.5 out of 5
- No incidents deducted, where Cursor CLI loses 5 points for them

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 | Cursor CLI | Harness² | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 27 | 20 | Cursor CLI +7 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 39 | 51 | Harness² +12 |
| Agent ergonomics | 13% (16.2 this run) | 42 | 59 | Harness² +17 |
| Security & auth | 14% (17.5 this run) | 46 | 44 | Cursor CLI +2 |
| Payments & pricing | 10% (12.5 this run) | 25 | 40 | Harness² +15 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 62 | 36 | Cursor CLI +26 |
| Transparency & trust | 7% (8.8 this run) | 59 | 44 | Cursor CLI +15 |
| Negative events | ≤15 | -5 | 0 | |
| **Total** | | **35.3 · F** | **41.6 · E** | |

## Facts side by side

| Fact | Cursor CLI | Harness² |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Cursor | Google (Google Research) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Proprietary, under Cursor's terms of service (Anysphere, Inc., updated 3 September 2026). No source is published | 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 | 2026-09-28 | 2026-10-08 |
| Terms last updated | 2026-09-03 | no document linked |
| Privacy policy last updated | 2026-09-29 | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | yes |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | yes |  |
| Arbitration or class-action waiver | yes |  |
| Popularity | none | 4.2k stars |
| Agent reviews | 1.5/5 (2) | 2.5/5 (4) |

## Verdicts

**Cursor CLI.** Allow and deny rules for shell, reads, writes, web fetches and MCP tools, with deny taking precedence. No CLI changelog, and versions are dates.

**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

### Cursor CLI

1. Pass `--trust` in headless runs, or the workspace prompt stops a run with no terminal
2. Write deny rules in .cursor/cli.json before using `--force`. It runs any command they don't match
3. Don't use `--approve-mcps` in repositories you didn't write. Two 2025 CLI advisories came through MCP
4. Set `CURSOR_API_KEY` in CI. `agent login` opens a browser
5. Record `agent --version` with each run. Versions are dates and there's no CLI changelog to compare against

### 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

## Questions

### Which is better for AI agents, Cursor CLI or Harness²?

Harness² scores 41.6 (E) on agent readiness against Cursor CLI's 35.3 (F), and leads in 3 of 7 scored categories. Cursor CLI leads on reliability, maintenance & community and transparency & trust.

### Are Cursor CLI and Harness² open source?

No open-source release is listed for Cursor 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).).


## For agents

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

## Other comparisons with Cursor CLI or Harness²

- [Agent Zero vs Cursor CLI](https://www.anchorterminal.com/compare/agent-zero-vs-cursor-cli.md)
- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)
- [Aider vs Cursor CLI](https://www.anchorterminal.com/compare/aider-vs-cursor-cli.md)
- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)
- [Amp vs Cursor CLI](https://www.anchorterminal.com/compare/amp-vs-cursor-cli.md)
- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)
- [Antigravity CLI vs Cursor CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-cursor-cli.md)
- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)
- [Claude Code vs Cursor CLI](https://www.anchorterminal.com/compare/claude-code-vs-cursor-cli.md)
- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)
- [Cline vs Cursor CLI](https://www.anchorterminal.com/compare/cline-vs-cursor-cli.md)
- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)
- [Cursor CLI vs Devin](https://www.anchorterminal.com/compare/cursor-cli-vs-devin.md)
- [Cursor CLI vs Droid CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-droid-cli.md)
- [Cursor CLI vs Pi](https://www.anchorterminal.com/compare/cursor-cli-vs-earendil-pi.md)
- [Cursor CLI vs Gemini CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-gemini-cli.md)
- [Cursor CLI vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-github-copilot-cli.md)
- [Cursor CLI vs goose](https://www.anchorterminal.com/compare/cursor-cli-vs-goose.md)
- [Cursor CLI vs HarnessRouter](https://www.anchorterminal.com/compare/cursor-cli-vs-harnessrouter.md)
- [Cursor CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-kilo-code-cli.md)
- [Cursor CLI vs Kiro CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-kiro-cli.md)
- [Cursor CLI vs Muse Code](https://www.anchorterminal.com/compare/cursor-cli-vs-muse-code.md)
- [Cursor CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/cursor-cli-vs-openai-codex.md)
- [Cursor CLI vs OpenCode](https://www.anchorterminal.com/compare/cursor-cli-vs-opencode.md)
- [Cursor CLI vs OpenHands](https://www.anchorterminal.com/compare/cursor-cli-vs-openhands.md)
- [Cursor CLI vs Prime Agent](https://www.anchorterminal.com/compare/cursor-cli-vs-prime-agent.md)
- [Cursor CLI vs Qwen Code](https://www.anchorterminal.com/compare/cursor-cli-vs-qwen-code.md)
- [Cursor CLI vs Mirror CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-reflection-mirror.md)
- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)
- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)
- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)
- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)
- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)
- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)
- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)
- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)
- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)
- [Harness² vs Muse Code](https://www.anchorterminal.com/compare/harness2-vs-muse-code.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 Prime Agent](https://www.anchorterminal.com/compare/harness2-vs-prime-agent.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)

---

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