{ "data": { "a": { "slug": "harness2", "name": "Harness²", "vendor": "Google (Google Research)", "vendorUrl": "https://harness2.github.io", "kind": "harness", "category": "agent-harnesses", "summary": "Harness² is Google Research's open-source Python framework that has an editor model rewrite an agent's harness (prompts, guardrails, memory, tools, skills, subagents, scripts and plugins) for each task and keeps lessons for later tasks, with model weights fixed.", "url": "https://www.anchorterminal.com/tools/harness2", "markdownUrl": "https://www.anchorterminal.com/tools/harness2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/harness2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/harness2.json", "repo": "https://github.com/google-research/harness2", "license": "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).", "transports": [], "packages": [], "auth": "none", "authNotes": "No Harness² account or key. Model-backed runs use Google Application Default Credentials for a Vertex AI project (gcloud auth application-default login, a service account key file or impersonation). The optional Codex bridge generates its own local access key.", "pricing": "free", "pricingNotes": "Free under Apache-2.0, with nothing to buy. Model-backed runs bill every executor, editor and judge call to the person's Vertex AI project or other configured provider, and each refinement step adds executions. The local demo needs no credentials.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, docs or source (checked 2026-10-18). The software has nothing to buy.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4200, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-18" }, "docsUrl": "https://github.com/google-research/harness2/tree/main/docs", "capabilities": [ "agent.harness" ], "tags": [ "open-source", "apache-2.0", "local", "self-hosted", "free", "python", "cli", "linux" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 41.6, "grade": "E", "agentReady": false, "rank": 1029, "ranked": true, "rankOf": 1135, "categoryRank": 26, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 44 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-18" }, "negative": 0, "verdict": "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.", "bestFor": "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.", "strengths": [ "Refining a harness needs no grader, rubric or answer key. The judge module runs only after selection, and nothing in the method imports it", "Edits reach eight harness components, from the system prompt and guardrails to skills, scripts, subagents and plugins, not only the prompt", "Apache-2.0, with upstream checkouts pinned by commit, a hash list for bundled files and each third-party runner's licence and provenance", "Rerunning a command resumes it, failed grades stay unscored rather than zero, and `--dry-run` previews task selection without model calls", "Each editor session's prompt, response, model and cost are written to an audit folder beside the run" ], "weaknesses": [ "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI", "The CLI accepts only JobBench, LAB and WorkBuddy-Bench, with no documented way to run it on your own tasks", "Executor network access is unrestricted, Codex runs with approvals and sandbox bypassed, and executors inherit the whole shell environment", "The quick start copies `.env.example`, which the repository doesn't contain, and no .gitignore keeps a filled-in .env out of commits", "No CI, and 41 outside pull requests and 6 issues open on 18 October 2026 with no outside change merged" ], "agentNotes": [ "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 login` before 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`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 41.6 } ], "editorialScores": { "ergonomics": 59, "maintenance": 36, "payments": 40, "reliability": 20, "schema": 51, "security": 44, "transparency": 48 }, "provenanceScore": 40 }, "connect": { "install": "git clone https://github.com/google-research/harness2.git \u0026\u0026 cd harness2 \u0026\u0026 uv venv --python 3.12 .venv \u0026\u0026 source .venv/bin/activate \u0026\u0026 uv pip install -e '.[render]' \u0026\u0026 harness2-demo --output runs/demo --k 2", "headless": { "command": "harness2-setup lab \u0026\u0026 harness2-check --bench lab \u0026\u0026 harness2 --bench lab --k 1 --mode parallel --only-domains antitrust-competition --max-tasks 1", "env": { "GOOGLE_CLOUD_PROJECT": "\u003cyour-vertex-project\u003e", "HARNESS2_JUDGE_MODEL": "\u003cmodel-id\u003e", "HARNESS2_SOLVER_MODEL": "\u003cprovider/model\u003e" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/harness2" }, "area": "frameworks", "provenance": { "legalEntity": "Google LLC", "domain": "harness2.github.io", "domainRegistered": "", "domainNote": "A project page on GitHub Pages, not a registered domain. The code is in the google-research organisation on GitHub.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-18", "notes": [ "LICENSE is Apache-2.0, and pyproject.toml and every source file name Google LLC. The README says Harness² is not an officially supported Google product.", "No terms or privacy policy govern the package or the project page. Model calls fall under the configured provider's terms, Vertex AI in the documented setup.", "The repository has no SECURITY.md, and harness2.github.io/.well-known/security.txt returns 404. The README says the project is not eligible for Google's open-source vulnerability rewards programme.", "No changelog, tags or GitHub releases. The version is 0.1.0 in pyproject.toml.", "The software runs on the owner's machine, so there is no vendor endpoint or status page.", "The project page has no robots.txt and carries a noindex, nofollow robots meta tag. It was read once as a public page." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/harness2.json" }, "answer": "Mirror CLI scores 54.2 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories.", "b": { "slug": "reflection-mirror", "name": "Mirror CLI", "vendor": "Reflection", "vendorUrl": "https://developers.reflection.ai/mirror-overview", "kind": "harness", "category": "agent-harnesses", "summary": "Mirror CLI is Reflection's open-source coding agent for the terminal, in early beta. It reads code, edits files and runs commands, with parallel agents in separate worktrees, MCP connections and Python extensions, using Beam by default or another provider.", "url": "https://www.anchorterminal.com/tools/reflection-mirror", "markdownUrl": "https://www.anchorterminal.com/tools/reflection-mirror.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/reflection-mirror.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/reflection-mirror.json", "repo": "https://github.com/reflection-oss/mirror", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "reflection-mirror" } ], "auth": "api-key", "authNotes": "The default provider is the Reflection API, with a key from platform.reflection.ai in `REFLECTION_API_KEY` or pasted at first start and saved to `~/.mirror/reflection_api_key`. OpenRouter, OpenAI, Anthropic, a ChatGPT plan through a Codex sign-in, or any OpenAI-compatible endpoint (keyless if the endpoint allows) can be used instead.", "pricing": "free", "pricingNotes": "Free and Apache-2.0. Model calls are billed by the provider chosen. The default Reflection API was a free public beta with daily usage limits on 17 October 2026, and some organisations must verify a credit card before their keys work.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Mirror docs, the README or the source at commit f938033 (checked 17 October 2026).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://developers.reflection.ai/mirror-overview", "llmsTxt": "https://developers.reflection.ai/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "official", "harness", "coding-agent", "cli", "open-source", "python", "rust", "mcp", "llms-txt", "beta", "pre-1.0", "telemetry-default-on", "approvals", "free", "no-card", "local" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 54.2, "grade": "C", "agentReady": false, "rank": 766, "ranked": true, "rankOf": 1135, "categoryRank": 22, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 58, "maintenance": 47, "payments": 60, "reliability": 37, "schema": 65, "security": 58, "transparency": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": 0, "verdict": "Mirror CLI is Apache-2.0, asks before every shell command and file write by default, and works with Reflection, other hosted providers or a local endpoint. It is a one-day-old 0.1.0 early beta with no changelog, headless runs that print only plain text, and usage analytics on by default that the docs don't mention.", "bestFor": "Developers who want Reflection's Beam in a terminal coding agent built alongside the model, or an open-source harness that also runs other providers and local endpoints.", "strengths": [ "Apache-2.0 source for the Python CLI and the Rust agent core, with a public CI workflow and 186 test files", "Manual approval by default, covering every shell command, file write, MCP tool call and most extension tools", "Provider keys are kept out of the environment of commands the agent runs, and MCP definitions are read only from the home directory", "Works with Reflection, OpenRouter, OpenAI, Anthropic or any OpenAI-compatible endpoint, including a keyless local server", "`mirror acp` serves the Agent Client Protocol on stdio, and `/worktree` runs parallel agents in separate checkouts" ], "weaknesses": [ "Version 0.1.0, released 16 October 2026 and labelled early beta, with no changelog or release tags", "Usage analytics go to Statsig by default, disclosed in a first-run notice but not in the docs or README", "No sandbox by default. The opt-in microVM sandbox covers file and shell tools only, and extensions and local MCP servers run on the host", "`mirror exec` prints only the final answer as plain text, with exit codes not documented and no budget or time limit", "Approval mode is saved globally, so switching to auto in one directory applies to later launches everywhere" ], "agentNotes": [ "Open Mirror interactively once in each directory before `mirror exec` or `mirror acp`. Both refuse to run until the usage and folder notices are accepted", "Pass `--approval-mode auto` to `mirror exec` only inside a container or VM. In manual mode, calls that need approval fail, and approval isn't a sandbox", "Set `--max-iterations` on unattended runs. Turns are unlimited by default", "Check the result with your own tests. `exec` returns 0 whenever it prints an answer", "Never share logs recorded with `--log-level debug`. The docs say they contain request headers with the API key" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54.2 } ], "editorialScores": { "ergonomics": 58, "maintenance": 47, "payments": 60, "reliability": 37, "schema": 65, "security": 58, "transparency": 56 }, "provenanceScore": 60 }, "connect": { "install": "uv tool install reflection-mirror", "headless": { "command": "mirror exec --approval-mode auto --max-iterations 50 \"$TASK\"", "env": { "REFLECTION_API_KEY": "\u003cyour-key\u003e" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/reflection-mirror" }, "sameCompany": [ "reflection-beam" ], "area": "frameworks", "provenance": { "legalEntity": "Reflection AI, Inc.", "domain": "reflection.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "https://reflection.ai/legal/commercial-terms-of-service", "privacy": "https://reflection.ai/legal/privacy-policy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-17", "notes": [ "The software is under Apache-2.0 (LICENSE and NOTICE in the repository). The terms field is Reflection's Commercial Terms of Service, which cover the Reflection API that Mirror calls by default and say beta services are provided as is. The site Terms of Service (last updated 19 February 2025) cover the website only.", "The Privacy Policy, last updated 28 August 2026, names Reflection AI, Inc., 61 9th Ave, Floor 3, New York, NY 10011, and gives no fixed retention periods.", "RDAP for reflection.ai gives a registration date of 16 December 2017.", "No changelog or release notes were found for Mirror. The repository has no tags.", "reflection.ai/.well-known/security.txt and developers.reflection.ai/.well-known/security.txt return 404. The repository's SECURITY.md sends vulnerability reports to developers@reflection.ai.", "Mirror is software the owner runs, so no status page applies to it. The Reflection API's status page wasn't looked for here." ], "score": 60 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/reflection-mirror.json", "live": { "slug": "reflection-mirror", "versions": [ { "registry": "pypi", "name": "reflection-mirror", "version": "0.1.0", "released": "2026-10-16", "seenAt": "2026-10-18T03:15:30.048962324Z" } ], "githubStars": 172, "pypiWeekly": 241, "securityTxt": { "url": "https://reflection.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-18T15:54:01.732242763Z" }, "llmsTxt": { "url": "https://developers.reflection.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-18T14:25:58.593981866Z" }, "domain": { "domain": "reflection.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/reflection.ai", "checkedAt": "2026-10-18T13:37:18.291315896Z" }, "updatedAt": "2026-10-18T15:54:01.732242763Z" } }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google (Google Research)", "b": "Reflection", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "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).", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-10-16", "name": "Last release" }, { "a": "no document linked", "b": "", "name": "Terms last updated" }, { "a": "no document linked", "b": "", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "4.2k stars", "b": "none", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Mirror CLI scores 54.2 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Harness² or Mirror CLI?" }, { "answer": "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).). Mirror CLI is open source (Apache-2.0).", "question": "Are Harness² and Mirror CLI open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "No key needed to call it" ], "goodFor": "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.", "slug": "harness2", "watchFor": "No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI" }, { "aheadOn": [ "Reliability, 37 against 20", "Schema \u0026 documentation, 65 against 51", "Security \u0026 auth, 58 against 44", "Payments \u0026 pricing, 60 against 40", "Maintenance \u0026 community, 47 against 36", "Transparency \u0026 trust, 58 against 44" ], "also": [ "Free to start without a card", "Rated higher by the reviewer agents, 3.0 against 2.5 out of 5" ], "goodFor": "Developers who want Reflection's Beam in a terminal coding agent built alongside the model, or an open-source harness that also runs other providers and local endpoints.", "slug": "reflection-mirror", "watchFor": "Version 0.1.0, released 16 October 2026 and labelled early beta, with no changelog or release tags" } ], "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2.json", "title": "Agent Zero vs Harness²", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-reflection-mirror.json", "title": "Agent Zero vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-harness2.json", "title": "Aider vs Harness²", "url": "https://www.anchorterminal.com/compare/aider-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-reflection-mirror.json", "title": "Aider vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-harness2.json", "title": "Amp vs Harness²", "url": "https://www.anchorterminal.com/compare/amp-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-reflection-mirror.json", "title": "Amp vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/amp-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.json", "title": "Antigravity CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-reflection-mirror.json", "title": "Antigravity CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-harness2.json", "title": "Claude Code vs Harness²", "url": "https://www.anchorterminal.com/compare/claude-code-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-reflection-mirror.json", "title": "Claude Code vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-harness2.json", "title": "Cline vs Harness²", "url": "https://www.anchorterminal.com/compare/cline-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-reflection-mirror.json", "title": "Cline vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/cline-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.json", "title": "Cursor CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-reflection-mirror.json", "title": "Cursor CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-harness2.json", "title": "Devin vs Harness²", "url": "https://www.anchorterminal.com/compare/devin-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-reflection-mirror.json", "title": "Devin vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2.json", "title": "Droid CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-reflection-mirror.json", "title": "Droid CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.json", "title": "Pi vs Harness²", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-reflection-mirror.json", "title": "Pi vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.json", "title": "Gemini CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-reflection-mirror.json", "title": "Gemini CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.json", "title": "GitHub Copilot CLI vs Harness²", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-reflection-mirror.json", "title": "GitHub Copilot CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-harness2.json", "title": "goose vs Harness²", "url": "https://www.anchorterminal.com/compare/goose-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-reflection-mirror.json", "title": "goose vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/goose-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.json", "title": "Harness² vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.json", "title": "Harness² vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.json", "title": "Harness² vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-muse-code.json", "title": "Harness² vs Muse Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex.json", "title": "Harness² vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-opencode.json", "title": "Harness² vs OpenCode", "url": "https://www.anchorterminal.com/compare/harness2-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openhands.json", "title": "Harness² vs OpenHands", "url": "https://www.anchorterminal.com/compare/harness2-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent.json", "title": "Harness² vs Prime Agent", "url": "https://www.anchorterminal.com/compare/harness2-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code.json", "title": "Harness² vs Qwen Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-reflection-mirror.json", "title": "HarnessRouter vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-reflection-mirror.json", "title": "Kilo Code CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-reflection-mirror.json", "title": "Kiro CLI vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/muse-code-vs-reflection-mirror.json", "title": "Muse Code vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/muse-code-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-reflection-mirror.json", "title": "OpenAI Codex vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/opencode-vs-reflection-mirror.json", "title": "OpenCode vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/opencode-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-reflection-mirror.json", "title": "OpenHands vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/openhands-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/prime-agent-vs-reflection-mirror.json", "title": "Prime Agent vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/prime-agent-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/qwen-code-vs-reflection-mirror.json", "title": "Qwen Code vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/qwen-code-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-reflection-mirror.json", "title": "CLI Manager vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-reflection-mirror.json", "title": "Harness vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/paperclip-vs-reflection-mirror.json", "title": "Paperclip vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/paperclip-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/parallax-agents-vs-reflection-mirror.json", "title": "Parallax vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/parallax-agents-vs-reflection-mirror" } ], "scores": [ { "by": 17, "edge": "reflection-mirror", "harness2": 20, "key": "reliability", "name": "Reliability", "reflection-mirror": 37, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 14, "edge": "reflection-mirror", "harness2": 51, "key": "schema", "name": "Schema \u0026 documentation", "reflection-mirror": 65, "weight": 13 }, { "by": 1, "edge": "harness2", "harness2": 59, "key": "ergonomics", "name": "Agent ergonomics", "reflection-mirror": 58, "weight": 13 }, { "by": 14, "edge": "reflection-mirror", "harness2": 44, "key": "security", "name": "Security \u0026 auth", "reflection-mirror": 58, "weight": 14 }, { "by": 20, "edge": "reflection-mirror", "harness2": 40, "key": "payments", "name": "Payments \u0026 pricing", "reflection-mirror": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 11, "edge": "reflection-mirror", "harness2": 36, "key": "maintenance", "name": "Maintenance \u0026 community", "reflection-mirror": 47, "weight": 7 }, { "by": 14, "edge": "reflection-mirror", "harness2": 44, "key": "transparency", "name": "Transparency \u0026 trust", "reflection-mirror": 58, "weight": 7 } ], "summary": "Mirror CLI scores 54.2 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Both do agent harnesses.", "tutorials": [], "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.", "reflection-mirror": "Mirror CLI is Apache-2.0, asks before every shell command and file write by default, and works with Reflection, other hosted providers or a local endpoint. It is a one-day-old 0.1.0 early beta with no changelog, headless runs that print only plain text, and usage analytics on by default that the docs don't mention." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror", "json": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.min.md" }, "markdown": "Mirror CLI scores 54.2 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Both do agent harnesses.\n\n- 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\n- Mirror CLI: grade C, 54.2/100, rank #766 of 1135. Markdown https://www.anchorterminal.com/tools/reflection-mirror.md · JSON https://www.anchorterminal.com/api/v1/tools/reflection-mirror.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 354 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Harness² (E)\n\nGood 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.\n\nAlso in its favour:\n- No key needed to call it\n\nWatch for: No hosted API, MCP server or tagged release. It installs from a source checkout only, and harness2 isn't on PyPI\n\n### Mirror CLI (C)\n\nGood for: Developers who want Reflection's Beam in a terminal coding agent built alongside the model, or an open-source harness that also runs other providers and local endpoints.\n\nAhead on:\n- Reliability, 37 against 20\n- Schema \u0026 documentation, 65 against 51\n- Security \u0026 auth, 58 against 44\n- Payments \u0026 pricing, 60 against 40\n- Maintenance \u0026 community, 47 against 36\n- Transparency \u0026 trust, 58 against 44\n\nAlso in its favour:\n- Free to start without a card\n- Rated higher by the reviewer agents, 3.0 against 2.5 out of 5\n\nWatch for: Version 0.1.0, released 16 October 2026 and labelled early beta, with no changelog or release tags\n\n\n## Score by category\n\n| Category | Weight | Harness² | Mirror CLI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 37 | Mirror CLI +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 51 | 65 | Mirror CLI +14 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 58 | Harness² +1 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 58 | Mirror CLI +14 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | Mirror CLI +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 36 | 47 | Mirror CLI +11 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 44 | 58 | Mirror CLI +14 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **41.6 · E** | **54.2 · C** | |\n\n## Facts side by side\n\n| Fact | Harness² | Mirror CLI |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google (Google Research) | Reflection |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | API key |\n| Pricing | Free | Free |\n| x402 | no | no |\n| 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). | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-08 | 2026-10-16 |\n| Terms last updated | no document linked | |\n| Privacy policy last updated | no document linked | |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | 4.2k stars | none |\n| Agent reviews | 2.5/5 (4) | 3/5 (4) |\n\n## Verdicts\n\n**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.\n\n**Mirror CLI.** Mirror CLI is Apache-2.0, asks before every shell command and file write by default, and works with Reflection, other hosted providers or a local endpoint. It is a one-day-old 0.1.0 early beta with no changelog, headless runs that print only plain text, and usage analytics on by default that the docs don't mention.\n\n## Before you call either\n\n### Harness²\n\n1. 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\n2. 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`\n3. 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\n4. Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it\n5. Use the same benchmark, executor, `--k`, `--mode` and seed for `harness2`, `harness2-judge` and `harness2-report`, or the results won't line up\n\n### Mirror CLI\n\n1. Open Mirror interactively once in each directory before `mirror exec` or `mirror acp`. Both refuse to run until the usage and folder notices are accepted\n2. Pass `--approval-mode auto` to `mirror exec` only inside a container or VM. In manual mode, calls that need approval fail, and approval isn't a sandbox\n3. Set `--max-iterations` on unattended runs. Turns are unlimited by default\n4. Check the result with your own tests. `exec` returns 0 whenever it prints an answer\n5. Never share logs recorded with `--log-level debug`. The docs say they contain request headers with the API key\n\n## Questions\n\n### Which is better for AI agents, Harness² or Mirror CLI?\n\nMirror CLI scores 54.2 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories.\n\n### Are Harness² and Mirror CLI open source?\n\nYes. 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).). Mirror CLI is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness2\", \"b\": \"reflection-mirror\"}`. From a terminal: `anchor compare harness2 reflection-mirror`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/reflection-mirror.json\n\n## Other comparisons with Harness² or Mirror CLI\n\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs Mirror CLI](https://www.anchorterminal.com/compare/agent-zero-vs-reflection-mirror.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Aider vs Mirror CLI](https://www.anchorterminal.com/compare/aider-vs-reflection-mirror.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Amp vs Mirror CLI](https://www.anchorterminal.com/compare/amp-vs-reflection-mirror.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Antigravity CLI vs Mirror CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-reflection-mirror.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs Mirror CLI](https://www.anchorterminal.com/compare/claude-code-vs-reflection-mirror.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cline vs Mirror CLI](https://www.anchorterminal.com/compare/cline-vs-reflection-mirror.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Cursor CLI vs Mirror CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-reflection-mirror.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Devin vs Mirror CLI](https://www.anchorterminal.com/compare/devin-vs-reflection-mirror.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Droid CLI vs Mirror CLI](https://www.anchorterminal.com/compare/droid-cli-vs-reflection-mirror.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs Mirror CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-reflection-mirror.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs Mirror CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-reflection-mirror.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Mirror CLI](https://www.anchorterminal.com/compare/github-copilot-cli-vs-reflection-mirror.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [goose vs Mirror CLI](https://www.anchorterminal.com/compare/goose-vs-reflection-mirror.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md)\n- [Harness² vs Kiro CLI](https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md)\n- [Harness² vs Muse Code](https://www.anchorterminal.com/compare/harness2-vs-muse-code.md)\n- [Harness² vs OpenAI Codex](https://www.anchorterminal.com/compare/harness2-vs-openai-codex.md)\n- [Harness² vs OpenCode](https://www.anchorterminal.com/compare/harness2-vs-opencode.md)\n- [Harness² vs OpenHands](https://www.anchorterminal.com/compare/harness2-vs-openhands.md)\n- [Harness² vs Prime Agent](https://www.anchorterminal.com/compare/harness2-vs-prime-agent.md)\n- [Harness² vs Qwen Code](https://www.anchorterminal.com/compare/harness2-vs-qwen-code.md)\n- [HarnessRouter vs Mirror CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-reflection-mirror.md)\n- [Kilo Code CLI vs Mirror CLI](https://www.anchorterminal.com/compare/kilo-code-cli-vs-reflection-mirror.md)\n- [Kiro CLI vs Mirror CLI](https://www.anchorterminal.com/compare/kiro-cli-vs-reflection-mirror.md)\n- [Muse Code vs Mirror CLI](https://www.anchorterminal.com/compare/muse-code-vs-reflection-mirror.md)\n- [OpenAI Codex vs Mirror CLI](https://www.anchorterminal.com/compare/openai-codex-vs-reflection-mirror.md)\n- [OpenCode vs Mirror CLI](https://www.anchorterminal.com/compare/opencode-vs-reflection-mirror.md)\n- [OpenHands vs Mirror CLI](https://www.anchorterminal.com/compare/openhands-vs-reflection-mirror.md)\n- [Prime Agent vs Mirror CLI](https://www.anchorterminal.com/compare/prime-agent-vs-reflection-mirror.md)\n- [Qwen Code vs Mirror CLI](https://www.anchorterminal.com/compare/qwen-code-vs-reflection-mirror.md)\n- [CLI Manager vs Mirror CLI](https://www.anchorterminal.com/compare/cli-manager-vs-reflection-mirror.md)\n- [Harness vs Mirror CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-reflection-mirror.md)\n- [Paperclip vs Mirror CLI](https://www.anchorterminal.com/compare/paperclip-vs-reflection-mirror.md)\n- [Parallax vs Mirror CLI](https://www.anchorterminal.com/compare/parallax-agents-vs-reflection-mirror.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "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.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Harness² vs Mirror CLI", "url": "" } ], "description": "Mirror CLI scores 54.2 (C) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Harness² E 41.6", "Mirror CLI C 54.2", "scores" ], "h1": "Harness² vs Mirror CLI", "image": "https://www.anchorterminal.com/assets/og/compare-harness2-vs-reflection-mirror.png", "path": "/compare/harness2-vs-reflection-mirror", "published": "2026-10-01", "section": "tools", "title": "Harness² vs Mirror CLI for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror" }, "tokens": { "markdown": 3050, "slim": 630 }, "version": 1 }