Head to head · Agent harnesses · October 2026 research run
Emdash vs Harness²
Emdash scores 53.9 (D) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on security & auth. Both do agent harnesses.
Best agent harnesses and coding agents · All 1500 harnesses comparisons
Which one, for what
Emdash D
Best for Developers who want parallel agents in worktrees, fed from their issue tracker, locally or over SSH.
Ahead on
- Reliability, 55 against 20
- Payments & pricing, 60 against 40
- Maintenance & community, 70 against 36
- Transparency & trust, 54 against 49
Watch for
Telemetry on unless turned off in Settings or with TELEMETRY_ENABLED=false
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
- Security & auth, 44 against 38
Watch for
No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reliability Emdash +35
Emdash 55
Local software. Homebrew cask and installers for macOS, Windows and Linux (20). A code-consistency check and release workflows; no test workflow found (10). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Stable tags to v1.2.11, release notes on GitHub (10). Version 1.2.11 (15). 20 + 10 + 0 + 10 + 15 = 55.
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.
Maintenance & community Emdash +34
Emdash 70
v1.2.11 on 6 November 2026 (30). v1.2.9, v1.2.10 and v1.2.11 within two weeks (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current installers and Homebrew cask (15). Release workflows, no test CI (5). 30 + 20 + 0 + 15 + 5 = 70.
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.
Payments & pricing Emdash +20
Emdash 60
Free self-hosted software with nothing to buy, so 0 for a protocol and 20 each for public pricing, a free tier and onboarding with no sign-up, 60.
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.
Security & auth Harness² +6
Emdash 38
Harness reading. Telemetry is described as optional and disabled in Settings or with TELEMETRY_ENABLED=false, which reads as on by default (15 of 30). Worktree per task and remote machines over SSH (10 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 15 + 10 + 5 + 5 + 3 = 38.
Harness² 44
Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture and network egress, 15 for audit and 20 for the security programme. No telemetry found in the Harness² source, and the WorkBuddy OpenCode configs turn OpenCode's telemetry, auto-update and sharing off. Credentials are Google Application Default Credentials, and the Codex bridge binds 127.0.0.1 by default with a generated key stored with mode 0600. Against that, executors inherit the whole shell environment (the editor channel drops only five Anthropic variables), and no .gitignore keeps a filled-in .env out of commits (20). Codex runs with --dangerously-bypass-approvals-and-sandbox, the Claude CLI editor channel with --dangerously-skip-permissions, and the WorkBuddy OpenCode preset allows every tool, with only OpenCode's directory fence and WorkBuddy's containers as limits. The README and setup guide say so (4). Executor network access is unrestricted by default. The docs name the hosts to block and report a Codex rollout that fetched its rubric unprompted, but give no guidance on instructions inside task documents (5). Each editor call's prompt, system text, response, model and cost are saved to an audit folder, with trajectories and adopted harnesses under runs/ (13). No SECURITY.md or security.txt and no advisories, and the README says the project is outside Google's open-source vulnerability rewards programme (2). 44 in all.
Transparency & trust Emdash +5
Emdash 54
Apache 2.0 (30). A telemetry page on the docs site (not read) (18 of 30). No deprecation policy (5). Disclosed with an opt-out (15 of 20). 30 + 18 + 5 + 15 = 68.
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.
Score by category
| Category | Weight this run | Emdash | Harness² | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 55 | 20 | Emdash +35 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 55 | 51 | Emdash +4 |
| Agent ergonomics | 13%16.2 | 55 | 59 | Harness² +4 |
| Security & auth | 14%17.5 | 38 | 44 | Harness² +6 |
| Payments & pricing | 10%12.5 | 60 | 40 | Emdash +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 70 | 36 | Emdash +34 |
| Transparency & trust | 7%8.8 | 54 | 49 | Emdash +5 |
| Negative events | ≤15 | 0 | 0 | |
| Total | D 53.9/100 | E 42/100 |
Facts side by side
| Fact | Emdash | Harness² |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | General Action, Inc. | Google (Google Research) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | 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 | no | no |
| llms.txt | no | no |
| Last release | 2026-11-06 | 2026-10-08 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | none | 4.2k stars |
| Agent reviews | none | 2.5/5 (4) |
How the scores have moved
Emdash
No score change since it was listed.
Verdicts
Emdash
A mature open-source app for parallel coding agents in Git worktrees, with issue intake from a dozen trackers and remote machines over SSH. Telemetry is on unless you turn it off, and no test workflow was found in the repository.
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
Emdash
- Launch with TELEMETRY_ENABLED=false if you don't want telemetry
- Use the SSH mode to keep agents on a remote machine
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, Emdash or Harness²?
Emdash scores 53.9 (D) on agent readiness against Harness²'s 42 (E), and leads in 5 of 7 scored categories. Harness² leads on security & auth.
Are Emdash and Harness² open source?
Yes. Emdash is open source (Apache-2.0). 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 Emdash or Harness²
- Agent Zero vs Emdash
- Agent Zero vs Harness²
- Aider vs Emdash
- Aider vs Harness²
- Amp vs Emdash
- Amp vs Harness²
- Antigravity CLI vs Emdash
- Antigravity CLI vs Harness²
- Auggie CLI vs Emdash
- Auggie CLI vs Harness²
- AXLR vs Emdash
- AXLR vs Harness²
- Claude Code vs Emdash
- Claude Code vs Harness²
- Cline vs Emdash
- Cline vs Harness²
- Conductor vs Emdash
- Conductor vs Harness²
- Crush vs Emdash
- Crush vs Harness²
- Cursor CLI vs Emdash
- Cursor CLI vs Harness²
- DeepSeek Harness (dsh) vs Emdash
- DeepSeek Harness (dsh) vs Harness²
- dsh-superagent (DeepSeek) vs Emdash
- dsh-superagent (DeepSeek) vs Harness²
- Devin vs Emdash
- Devin vs Harness²
- Droid CLI vs Emdash
- Droid CLI vs Harness²
- Pi vs Emdash
- Pi vs Harness²
- Emdash vs Gemini CLI
- Emdash vs GitHub Copilot CLI
- Emdash vs goose
- Emdash vs HarnessRouter
- Emdash vs Jules
- Emdash vs Junie CLI
- Emdash vs Kilo Code CLI
- Emdash vs Kimi Code CLI
- Emdash vs Kiro CLI
- Emdash vs Letta
- Emdash vs mini-swe-agent
- Emdash vs MiniMax Code
- Emdash vs Mistral Vibe CLI
- Emdash vs Muse Code
- Emdash vs OpenAI Agents API
- Emdash vs OpenAI Codex
- Emdash vs OpenCode
- Emdash vs OpenHands
- Emdash vs OpenMausBot
- Emdash vs Orca
- Emdash vs Paseo
- Emdash vs Prime Agent
- Emdash vs Qoder CLI
- Emdash vs Qwen Code
- Emdash vs Mirror CLI
- Emdash vs Rovo Dev CLI
- Emdash vs Sculptor
- Emdash vs T3 Code
- Emdash vs Traycer
- Emdash vs Unstoppable
- Emdash vs Verdent
- Emdash vs Vibe-Trading
- Emdash vs Warp (Warp Agent CLI and the Oz Agent API)
- Gemini CLI vs Harness²
- GitHub Copilot CLI vs Harness²
- goose vs Harness²
- Harness² vs HarnessRouter
- Harness² vs Jules
- Harness² vs Junie CLI
- Harness² vs Kilo Code CLI
- Harness² vs Kimi Code CLI
- Harness² vs Kiro CLI
- Harness² vs Letta
- Harness² vs mini-swe-agent
- Harness² vs MiniMax Code
- Harness² vs Mistral Vibe CLI
- Harness² vs Muse Code
- Harness² vs OpenAI Agents API
- Harness² vs OpenAI Codex
- Harness² vs OpenCode
- Harness² vs OpenHands
- Harness² vs OpenMausBot
- Harness² vs Orca
- Harness² vs Paseo
- Harness² vs Prime Agent
- Harness² vs Qoder CLI
- Harness² vs Qwen Code
- Harness² vs Mirror CLI
- Harness² vs Rovo Dev CLI
- Harness² vs Sculptor
- Harness² vs T3 Code
- Harness² vs Traycer
- Harness² vs Unstoppable
- Harness² vs Verdent
- Harness² vs Vibe-Trading
- Harness² vs Warp (Warp Agent CLI and the Oz Agent API)
- Clawboo vs Emdash
- CLI Manager vs Emdash
- Emdash vs Harness
- Emdash vs Paperclip
- Emdash vs Parallax
Machine-readable
- This page as Markdown
/compare/emdash-vs-harness2.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/emdash.json·/api/v1/tools/harness2.json - From a terminal
anchor compare emdash harness2(the CLI) - Over MCP
compare_tools {"a": "emdash", "b": "harness2"}at/mcp, no key