# Harness² vs Traycer

> Traycer scores 57 (C) 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-traycer
- Markdown: https://www.anchorterminal.com/compare/harness2-vs-traycer.md (~5,600 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

Traycer scores 57 (C) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on payments & pricing. 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
- Traycer: grade C, 57/100, rank #811 of 1486. Markdown https://www.anchorterminal.com/tools/traycer.md · JSON https://www.anchorterminal.com/api/v1/tools/traycer.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:
- Payments & pricing, 40 against 30

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

### Traycer (C)

Good for: Teams who want several coding agents working together with shared context and boards.

Ahead on:
- Reliability, 65 against 20
- Schema & documentation, 65 against 51
- Agent ergonomics, 65 against 59
- Maintenance & community, 75 against 36
- Transparency & trust, 60 against 49

Watch for: Privacy Mode is opt-in for individuals; with it off, prompts may be logged


## Why the edge

### Reliability: Traycer +45

- 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.
- Traycer (65): Local software. Builds for macOS, Linux and Windows, and package-manager publishing workflows (20). test.yml, CodeQL, OpenSSF Scorecard and secret scanning 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). CHANGELOG.md (15). Host 1.5.3 (15). 20 + 15 + 0 + 15 + 15 = 65.

### Maintenance & community: Traycer +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.
- Traycer (75): Commits on 6 November 2026 and host 1.5.3 (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 apps and CLI packages (15). CI with tests (10). 30 + 20 + 0 + 15 + 10 = 75.

### Schema & documentation: Traycer +14

- Harness² (51): Framework reading. Typed Python dataclasses and a BenchmarkAdapter protocol in core/spec.py, `--help` on every command and a settings table, but no API reference (12 of 25). Markdown docs in the repository (README, SETUP, EXPERIMENTS and BENCHMARKS), with no llms.txt (5 of 10). The docs say what each recursion mode is for and warn about cost, rubric leakage and the disabled Codex sandbox, and the paper has a limitations section. Nothing says how to use it outside the three benchmarks (13 of 20). `--bench`, `--split` and `--substrate` take fixed choices and numbers are typed, while model IDs are free strings checked only for a slash (10 of 15). Every command has a worked example and ConfigError messages name the fix, but the quick start's `cp .env.example .env` fails because the file isn't shipped (8 of 15). Version 0.1.0 with no changelog (3 of 15). 51 in all.
- Traycer (65): Harness reading. Mintlify docs, a protocol package and a CLI (65).

### Transparency & trust: Traycer +11

- Harness² (49): Apache-2.0 under Google LLC, with each bundled runner's licence and provenance file and a hash list. The WorkBuddy runners carry Tencent's custom licence, which has an EU territorial limitation (26 of 30). The docs list every host setup contacts and say credentials, generated configuration and run artefacts are not release assets. No privacy statement covers the package, and task data goes to the configured model provider (12 of 30). No deprecation policy or notices for the 0.1.0 research release (0). No telemetry found in the source, and the docs don't say either way. OpenCode's telemetry is turned off only in the WorkBuddy configs (10 of 20). 48 in all.
- Traycer (60): MIT (30). README privacy section and a linked privacy policy (not read) (18 of 30). CHANGELOG.md, no deprecation policy (10). Analytics described as 'may be enabled', with no opt-out given in the README (8 of 20). 30 + 18 + 10 + 8 = 66.

### Payments & pricing: Harness² +10

- 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.
- Traycer (30): Scored on the paid option, Traycer's own inference subscription, whose price wasn't read (0 of 20). No protocol (0). Bring-your-own-agent use is free (20). Accounts for sync and teams weren't checked, half (10). 0 + 0 + 20 + 10 = 30.

### Agent ergonomics: Traycer +6

- Harness² (59): Framework reading, adapted to a harness that a pipeline drives. Results land in run folders, not in the caller's context, and an agent reads task summaries, adopted harnesses and reflection notes from runs/ (12 of 25). `--only-domains`, `--max-tasks` (per domain), `--split-file`, `--workers` and `--dry-run` size a run before any model call (14 of 20). harness2-check tests dependencies, credentials and configuration without a model call, configuration errors name the remedy, and incomplete runs exit nonzero (14 of 20). Rerunning a command resumes it, saved configuration refuses an incompatible resume, failed grades stay unscored, and editor replies are cached by a fingerprint of their inputs (15 of 20). No model has a default, a Vertex AI project and a gcloud sign-in are needed, only three benchmarks are accepted and there's no SDK (4 of 15). 59 in all.
- Traycer (65): Harness reading. Model switching within an agent, agent-to-agent loops, a CLI and cross-device sync (65).

## Score by category

| Category | Weight | Harness² | Traycer | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 20 | 65 | Traycer +45 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 51 | 65 | Traycer +14 |
| Agent ergonomics | 13% (16.2 this run) | 59 | 65 | Traycer +6 |
| Security & auth | 14% (17.5 this run) | 44 | 42 | Harness² +2 |
| Payments & pricing | 10% (12.5 this run) | 40 | 30 | Harness² +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 36 | 75 | Traycer +39 |
| Transparency & trust | 7% (8.8 this run) | 49 | 60 | Traycer +11 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **42 · E** | **57 · C** | |

## Facts side by side

| Fact | Harness² | Traycer |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Google (Google Research) | Traycer AI |
| 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

### Traycer

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.

**Traycer.** An open-source app for running several coding agents together with shared context, agent-to-agent messaging and team boards, on every desktop OS. Privacy Mode is opt-in for individuals, and the README says Sentry and PostHog may be on in release builds.

## 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

### Traycer

1. Turn on Privacy Mode if you're an individual user and don't want prompts logged
2. CLI agents you configure send requests straight to their provider; Traycer's own inference goes through Traycer

## Questions

### Which is better for AI agents, Harness² or Traycer?

Traycer scores 57 (C) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on payments & pricing.

### Are Harness² and Traycer 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).). Traycer is open source (MIT).


## For agents

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

## Other comparisons with Harness² or Traycer

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

---

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