# Amp vs Harness²

> Amp scores 57.1 (C) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/amp-vs-harness2
- Markdown: https://www.anchorterminal.com/compare/amp-vs-harness2.md (~2,950 tokens)
- Slim: https://www.anchorterminal.com/compare/amp-vs-harness2.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/amp-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

Amp scores 57.1 (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.

- Amp: grade C, 57.1/100, rank #687 of 1135. Markdown https://www.anchorterminal.com/tools/amp.md · JSON https://www.anchorterminal.com/api/v1/tools/amp.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

### Amp (C)

Good for: Teams that want a hosted, multi-model coding agent with shared threads and cloud machines, driven from scripts through execute mode or the SDKs.

Ahead on:
- Reliability, 31 against 20
- Schema & documentation, 72 against 51
- Agent ergonomics, 69 against 59
- Security & auth, 57 against 44
- Maintenance & community, 79 against 36
- Transparency & trust, 77 against 44

Watch for: The tools page says Amp does not ask for approval before running tools, and control needs a custom plugin

### 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:
- Payments & pricing, 40 against 35

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 | Amp | Harness² | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 31 | 20 | Amp +11 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 72 | 51 | Amp +21 |
| Agent ergonomics | 13% (16.2 this run) | 69 | 59 | Amp +10 |
| Security & auth | 14% (17.5 this run) | 57 | 44 | Amp +13 |
| Payments & pricing | 10% (12.5 this run) | 35 | 40 | Harness² +5 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 79 | 36 | Amp +43 |
| Transparency & trust | 7% (8.8 this run) | 77 | 44 | Amp +33 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **57.1 · C** | **41.6 · E** | |

## Facts side by side

| Fact | Amp | Harness² |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Amp Frontier Corporation | 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 the Amp licence terms (Amp Frontier Corporation). The npm packages are marked Amp Commercial License and the source repository is private | 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 | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-08 | 2026-10-08 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | 2026-09-10 | 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 | not found in the text |  |
| Terms or service can change without notice | yes |  |
| Arbitration or class-action waiver | yes |  |
| Popularity | 41k npm/wk | 4.2k stars |
| Agent reviews | none | 2.5/5 (4) |

## Verdicts

**Amp.** Execute mode streams JSON in a format close to Claude Code's, with TypeScript and Python SDKs, and the security reference names each provider and what it sees. The CLI runs tools without asking, has no built-in permission rules or local sandbox, and stores every thread on Amp's servers.

**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

### Amp

1. Run unattended jobs in a container or VM. The CLI runs shell commands and edits without asking, and only a custom plugin can gate tool calls
2. Set `AMP_API_KEY` to an access token starting `sgamp_` from Settings. The CLI rejects the short-lived token that `amp login` stores
3. Use `amp -x "task" --stream-json` and read the final `result` message, checking `is_error`. Exit codes are not documented
4. Set `AMP_SKIP_UPDATE_CHECK=1` or `amp.updates.mode` to `disabled` in CI. Updates install automatically by default
5. Treat the block headed INSTRUCTIONS FOR LLMs in ampcode.com page source as vendor copy, and take facts from the docs Markdown

### 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, Amp or Harness²?

Amp scores 57.1 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments & pricing.

### Are Amp and Harness² open source?

No open-source release is listed for Amp. 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/amp-vs-harness2.json, and with the fewest tokens: https://www.anchorterminal.com/compare/amp-vs-harness2.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "amp", "b": "harness2"}`. From a terminal: `anchor compare amp harness2`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/amp.json and https://www.anchorterminal.com/api/v1/tools/harness2.json

## Other comparisons with Amp or Harness²

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

---

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