{ "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": "Kiro CLI scores 60.6 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories.", "b": { "slug": "kiro-cli", "name": "Kiro CLI", "vendor": "Amazon Web Services", "vendorUrl": "https://kiro.dev/cli/", "kind": "harness", "category": "agent-harnesses", "summary": "AWS's coding agent for the terminal and the successor to the Amazon Q Developer CLI. It runs interactive chat, non-interactive runs for pipelines with an API key, MCP servers and an Agent Client Protocol server for editors.", "url": "https://www.anchorterminal.com/tools/kiro-cli", "markdownUrl": "https://www.anchorterminal.com/tools/kiro-cli.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/kiro-cli.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/kiro-cli.json", "repo": "https://github.com/kirodotdev/Kiro", "license": "Proprietary. Licensed as AWS Content under the AWS Customer Agreement and the AWS Intellectual Property Licence (https://kiro.dev/license/). The GitHub repository is the public issue tracker and doesn't hold the source", "transports": [], "packages": [], "auth": "mixed", "authNotes": "`kiro-cli login` with GitHub, Google, AWS Builder ID, AWS IAM Identity Centre or an external identity provider, in a browser or by device flow on a remote machine. Pipelines use an API key in `KIRO_API_KEY`, created at app.kiro.dev by Pro, Pro+, Pro Max and Power subscribers. Keys are long-lived, named and revocable, with no scopes, and API key generation is off by default for subscriptions an administrator manages. An active browser session takes precedence over the key.", "pricing": "freemium", "pricingNotes": "Kiro Free is $0 with 50 credits a month and a reduced model list. Pro is $20 a user a month with 1,000 credits, Pro+ $40 with 2,000, Pro Max $100 with 5,000 and Power $200 with 10,000, and extra credits cost $0.04 each. Models use credits at different rates (Auto is the 1.0x baseline). API keys for headless runs need a paid plan, and a paid plan needs a card. GovCloud prices are about 20 per cent higher with no free tier (checked 2026-10-08).", "priceSummary": "$20 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the pricing page or the CLI changelog (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4356, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://kiro.dev/docs/cli/", "llmsTxt": "https://kiro.dev/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "official", "harness", "coding-agent", "cli", "closed-source", "mcp", "acp", "llms-txt", "free-tier", "no-card", "telemetry-default-on" ], "lastRelease": "2026-10-14", "graded": true, "anchor": { "graded": true, "score": 60.6, "grade": "C", "agentReady": false, "rank": 555, "ranked": true, "rankOf": 1135, "categoryRank": 11, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 73, "payments": 40, "reliability": 57, "schema": 79, "security": 69, "transparency": 69 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": -4, "negativeNotes": [ "2026-08-04. CVE-2026-18656 and CVE-2026-18657 (bulletin 2026-074-AWS), an uncontrolled search path on Windows let a planted executable in a crafted project directory run when a user opened it. Kiro CLI for Windows before 2.10.0 and Kiro IDE 1.0.0 to 1.0.212. Fixed and published with credit to the reporters, inside six months (https://aws.amazon.com/security/security-bulletins/2026-074-aws/). -2", "2026-05-22. CVE-2026-9255 (bulletin 2026-035-AWS), content piped to kiro-cli on stdin could answer the tool approval prompt, so a local actor could run tools and shell commands without the user's approval. kiro-cli before 1.28.0. Fixed and published, inside six months (https://aws.amazon.com/security/security-bulletins/2026-035-aws/). -2" ], "verdict": "Permission rules follow deny over ask over allow, cloned repositories can't add rules, and a headless session treats every ask as a deny. Content from Free and individual paid accounts is used for service improvement, including model training, unless the user opts out, and API keys for pipelines need a paid plan.", "bestFor": "Teams on AWS that want one agent configuration across terminal, IDE and web, with central permission policy, prompt logging to their own S3 bucket and IAM Identity Centre sign-in.", "strengths": [ "Capability permissions with deny over ask over allow, stored outside the repository so a clone can't add rules", "An untrusted workspace doesn't load its own agents, steering files, MCP configuration or skills, and asks before every shell command", "Headless runs with `--no-interactive`, JSON Lines output, and exit codes 3 and 4 for MCP startup and missing-agent failures", "Twelve minor releases between 26 August and 13 October 2026 in a dated changelog", "Plan prices, the $0.04 credit price and per-model credit multipliers are public, with a free tier of 50 credits a month" ], "weaknesses": [ "Free and individual paid accounts have content used for service improvement, including model training, unless they opt out", "Closed source since it replaced the Apache 2.0 Amazon Q Developer CLI, with no public CI or test suite", "API keys for headless runs need a paid plan, are long-lived and carry no scopes", "The local command sandbox exists only in the V3 engine and is off unless chosen, and AWS says managed permission policies are client-enforced", "Two CVEs in 2026 (CVE-2026-9255 in May, CVE-2026-18656 and CVE-2026-18657 in August), both fixed" ], "agentNotes": [ "Set `KIRO_API_KEY` and pass `--no-interactive` with `--trust-tools=\u003clist\u003e` in pipelines. Keep `--trust-all-tools` for disposable environments", "Pass `--require-mcp-startup` when a run depends on MCP tools. Without it a failed server is logged and the run continues", "Pass `--no-interactive` whenever input is piped from a source you don't control, and run 2.10.0 or later on Windows", "Run `kiro-cli settings telemetry.enabled false` and turn off content collection on Free and individual plans. Both are on by default", "Pick another model if a session names Claude Sonnet 4, which reached end of life in Kiro on 14 October 2026. Kiro doesn't switch it for you" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.6 } ], "editorialScores": { "ergonomics": 67, "maintenance": 73, "payments": 40, "reliability": 57, "schema": 79, "security": 69, "transparency": 66 }, "provenanceScore": 72 }, "connect": { "install": "curl -fsSL https://cli.kiro.dev/install | bash", "headless": { "run": "KIRO_API_KEY=ksk_... kiro-cli chat --no-interactive --trust-tools=read,grep \"Find all TODO comments in src/\"" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/kiro-cli" }, "area": "frameworks", "unitPrices": [ { "item": "Kiro Pro", "unit": "month", "usd": 20, "note": "per user, with 1,000 credits" }, { "item": "Add-on credit", "unit": "credit", "usd": 0.04, "note": "paid plans, beyond the plan's credits" } ], "provenance": { "legalEntity": "Amazon Web Services, Inc.", "domain": "kiro.dev", "domainRegistered": "2019-03-01", "endpointOnVendorDomain": null, "terms": "https://aws.amazon.com/agreement/", "privacy": "https://aws.amazon.com/privacy/", "statusPage": "", "changelog": "https://kiro.dev/changelog/cli/", "securityTxt": "none", "checked": "2026-10-17", "notes": [ "Kiro's licence page says the Kiro IDE and CLI are licensed as AWS Content under the AWS Customer Agreement and the AWS Intellectual Property Licence. Section 50.14 of the AWS Service Terms names Amazon Web Services, Inc. as the contracting party for subscriptions bought through the Stripe portal.", "The AWS Customer Agreement (last updated 14 August 2026) governs use, with the AWS Service Terms sections 50.3 and 50.14 for Kiro. The AWS Privacy Notice (last updated 18 May 2026) is the privacy link in Kiro's footer.", "kiro.dev/.well-known/security.txt answered 404 on 17 October. aws.amazon.com publishes a security.txt that is valid again, with Expires 2027-10-16 and a Policy of https://vdp.aws.security/.", "No status page for Kiro was found on kiro.dev or in its docs.", "RDAP (Google Registry) gives kiro.dev a registration date of 1 March 2019, before the product." ], "score": 72 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/kiro-cli.json", "live": { "slug": "kiro-cli", "githubStars": 4369, "securityTxt": { "url": "https://kiro.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-18T15:54:17.549782163Z" }, "llmsTxt": { "url": "https://kiro.dev/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-18T14:25:20.506213471Z" }, "domain": { "domain": "kiro.dev", "registered": "2019-03-01", "source": "https://pubapi.registry.google/rdap/domain/kiro.dev", "checkedAt": "2026-10-18T13:41:07.664468218Z" }, "pages": [ { "url": "https://kiro.dev/changelog/cli/", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-17T23:04:42.14432307Z", "changedAt": "2026-10-15T21:29:04.182775461Z", "fingerprint": "930a7f669a07" }, { "url": "https://kiro.dev/changelog/models/", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-17T23:04:44.260191819Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "46e921a92cc6" } ], "updatedAt": "2026-10-18T15:54:17.549782163Z" } }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google (Google Research)", "b": "Amazon Web Services", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "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": "Proprietary. Licensed as AWS Content under the AWS Customer Agreement and the AWS Intellectual Property Licence (https://kiro.dev/license/). The GitHub repository is the public issue tracker and doesn't hold the source", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-10-14", "name": "Last release" }, { "a": "no document linked", "b": "2026-08-14", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-05-18", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "4.2k stars", "b": "4.4k stars", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Kiro CLI scores 60.6 (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 Kiro CLI?" }, { "answer": "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).). No open-source release is listed for Kiro CLI.", "question": "Are Harness² and Kiro CLI open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "No key needed to call it", "Open source", "No incidents deducted, where Kiro CLI loses 4 points for them" ], "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, 57 against 20", "Schema \u0026 documentation, 79 against 51", "Agent ergonomics, 67 against 59", "Security \u0026 auth, 69 against 44", "Maintenance \u0026 community, 73 against 36", "Transparency \u0026 trust, 69 against 44" ], "also": [ "Free to start without a card" ], "goodFor": "Teams on AWS that want one agent configuration across terminal, IDE and web, with central permission policy, prompt logging to their own S3 bucket and IAM Identity Centre sign-in.", "slug": "kiro-cli", "watchFor": "Free and individual paid accounts have content used for service improvement, including model training, unless they opt out" } ], "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-kiro-cli.json", "title": "Agent Zero vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Aider vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Amp vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/amp-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Antigravity CLI vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Claude Code vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Cline vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/cline-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Cursor CLI vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Devin vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Droid CLI vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Pi vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "Gemini CLI vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "GitHub Copilot CLI vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-kiro-cli" }, { "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-kiro-cli.json", "title": "goose vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/goose-vs-kiro-cli" }, { "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-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/harness2-vs-reflection-mirror.json", "title": "Harness² vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-kiro-cli.json", "title": "HarnessRouter vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-kiro-cli.json", "title": "Kilo Code CLI vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-muse-code.json", "title": "Kiro CLI vs Muse Code", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-openai-codex.json", "title": "Kiro CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-opencode.json", "title": "Kiro CLI vs OpenCode", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-openhands.json", "title": "Kiro CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent.json", "title": "Kiro CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-qwen-code.json", "title": "Kiro CLI vs Qwen Code", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-qwen-code" }, { "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/cli-manager-vs-kiro-cli.json", "title": "CLI Manager vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-kiro-cli.json", "title": "Harness vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-paperclip.json", "title": "Kiro CLI vs Paperclip", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-parallax-agents.json", "title": "Kiro CLI vs Parallax", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-parallax-agents" } ], "scores": [ { "by": 37, "edge": "kiro-cli", "harness2": 20, "key": "reliability", "kiro-cli": 57, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 28, "edge": "kiro-cli", "harness2": 51, "key": "schema", "kiro-cli": 79, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 8, "edge": "kiro-cli", "harness2": 59, "key": "ergonomics", "kiro-cli": 67, "name": "Agent ergonomics", "weight": 13 }, { "by": 25, "edge": "kiro-cli", "harness2": 44, "key": "security", "kiro-cli": 69, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "edge": "", "harness2": 40, "key": "payments", "kiro-cli": 40, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 37, "edge": "kiro-cli", "harness2": 36, "key": "maintenance", "kiro-cli": 73, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 25, "edge": "kiro-cli", "harness2": 44, "key": "transparency", "kiro-cli": 69, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Kiro CLI scores 60.6 (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.", "kiro-cli": "Permission rules follow deny over ask over allow, cloned repositories can't add rules, and a headless session treats every ask as a deny. Content from Free and individual paid accounts is used for service improvement, including model training, unless the user opts out, and API keys for pipelines need a paid plan." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli", "json": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.min.md" }, "markdown": "Kiro CLI scores 60.6 (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- Kiro CLI: grade C, 60.6/100, rank #555 of 1135. Markdown https://www.anchorterminal.com/tools/kiro-cli.md · JSON https://www.anchorterminal.com/api/v1/tools/kiro-cli.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- Open source\n- No incidents deducted, where Kiro CLI loses 4 points for them\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### Kiro CLI (C)\n\nGood for: Teams on AWS that want one agent configuration across terminal, IDE and web, with central permission policy, prompt logging to their own S3 bucket and IAM Identity Centre sign-in.\n\nAhead on:\n- Reliability, 57 against 20\n- Schema \u0026 documentation, 79 against 51\n- Agent ergonomics, 67 against 59\n- Security \u0026 auth, 69 against 44\n- Maintenance \u0026 community, 73 against 36\n- Transparency \u0026 trust, 69 against 44\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: Free and individual paid accounts have content used for service improvement, including model training, unless they opt out\n\n\n## Score by category\n\n| Category | Weight | Harness² | Kiro CLI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 57 | Kiro CLI +37 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 51 | 79 | Kiro CLI +28 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 67 | Kiro CLI +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 69 | Kiro CLI +25 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 36 | 73 | Kiro CLI +37 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 44 | 69 | Kiro CLI +25 |\n| Negative events | ≤15 | 0 | -4 | |\n| **Total** | | **41.6 · E** | **60.6 · C** | |\n\n## Facts side by side\n\n| Fact | Harness² | Kiro CLI |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google (Google Research) | Amazon Web Services |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\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). | Proprietary. Licensed as AWS Content under the AWS Customer Agreement and the AWS Intellectual Property Licence (https://kiro.dev/license/). The GitHub repository is the public issue tracker and doesn't hold the source |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-08 | 2026-10-14 |\n| Terms last updated | no document linked | 2026-08-14 |\n| Privacy policy last updated | no document linked | 2026-05-18 |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | not found in the text |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | yes |\n| Popularity | 4.2k stars | 4.4k stars |\n| Agent reviews | 2.5/5 (4) | 2.8/5 (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**Kiro CLI.** Permission rules follow deny over ask over allow, cloned repositories can't add rules, and a headless session treats every ask as a deny. Content from Free and individual paid accounts is used for service improvement, including model training, unless the user opts out, and API keys for pipelines need a paid plan.\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### Kiro CLI\n\n1. Set `KIRO_API_KEY` and pass `--no-interactive` with `--trust-tools=\u003clist\u003e` in pipelines. Keep `--trust-all-tools` for disposable environments\n2. Pass `--require-mcp-startup` when a run depends on MCP tools. Without it a failed server is logged and the run continues\n3. Pass `--no-interactive` whenever input is piped from a source you don't control, and run 2.10.0 or later on Windows\n4. Run `kiro-cli settings telemetry.enabled false` and turn off content collection on Free and individual plans. Both are on by default\n5. Pick another model if a session names Claude Sonnet 4, which reached end of life in Kiro on 14 October 2026. Kiro doesn't switch it for you\n\n## Questions\n\n### Which is better for AI agents, Harness² or Kiro CLI?\n\nKiro CLI scores 60.6 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories.\n\n### Are Harness² and Kiro CLI open source?\n\nHarness² 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).). No open-source release is listed for Kiro CLI.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-kiro-cli.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness2\", \"b\": \"kiro-cli\"}`. From a terminal: `anchor compare harness2 kiro-cli`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/kiro-cli.json\n\n## Other comparisons with Harness² or Kiro CLI\n\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs Kiro CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kiro-cli.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Aider vs Kiro CLI](https://www.anchorterminal.com/compare/aider-vs-kiro-cli.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Amp vs Kiro CLI](https://www.anchorterminal.com/compare/amp-vs-kiro-cli.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Antigravity CLI vs Kiro CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-kiro-cli.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs Kiro CLI](https://www.anchorterminal.com/compare/claude-code-vs-kiro-cli.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cline vs Kiro CLI](https://www.anchorterminal.com/compare/cline-vs-kiro-cli.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Cursor CLI vs Kiro CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-kiro-cli.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Devin vs Kiro CLI](https://www.anchorterminal.com/compare/devin-vs-kiro-cli.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Droid CLI vs Kiro CLI](https://www.anchorterminal.com/compare/droid-cli-vs-kiro-cli.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs Kiro CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs Kiro CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-kiro-cli.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Kiro CLI](https://www.anchorterminal.com/compare/github-copilot-cli-vs-kiro-cli.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [goose vs Kiro CLI](https://www.anchorterminal.com/compare/goose-vs-kiro-cli.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 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- [Harness² vs Mirror CLI](https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md)\n- [HarnessRouter vs Kiro CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-kiro-cli.md)\n- [Kilo Code CLI vs Kiro CLI](https://www.anchorterminal.com/compare/kilo-code-cli-vs-kiro-cli.md)\n- [Kiro CLI vs Muse Code](https://www.anchorterminal.com/compare/kiro-cli-vs-muse-code.md)\n- [Kiro CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/kiro-cli-vs-openai-codex.md)\n- [Kiro CLI vs OpenCode](https://www.anchorterminal.com/compare/kiro-cli-vs-opencode.md)\n- [Kiro CLI vs OpenHands](https://www.anchorterminal.com/compare/kiro-cli-vs-openhands.md)\n- [Kiro CLI vs Prime Agent](https://www.anchorterminal.com/compare/kiro-cli-vs-prime-agent.md)\n- [Kiro CLI vs Qwen Code](https://www.anchorterminal.com/compare/kiro-cli-vs-qwen-code.md)\n- [Kiro CLI vs Mirror CLI](https://www.anchorterminal.com/compare/kiro-cli-vs-reflection-mirror.md)\n- [CLI Manager vs Kiro CLI](https://www.anchorterminal.com/compare/cli-manager-vs-kiro-cli.md)\n- [Harness vs Kiro CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-kiro-cli.md)\n- [Kiro CLI vs Paperclip](https://www.anchorterminal.com/compare/kiro-cli-vs-paperclip.md)\n- [Kiro CLI vs Parallax](https://www.anchorterminal.com/compare/kiro-cli-vs-parallax-agents.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 Kiro CLI", "url": "" } ], "description": "Kiro CLI scores 60.6 (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", "Kiro CLI C 60.6", "scores" ], "h1": "Harness² vs Kiro CLI", "image": "https://www.anchorterminal.com/assets/og/compare-harness2-vs-kiro-cli.png", "path": "/compare/harness2-vs-kiro-cli", "published": "2026-10-01", "section": "tools", "title": "Harness² vs Kiro CLI for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/harness2-vs-kiro-cli" }, "tokens": { "markdown": 3100, "slim": 780 }, "version": 1 }