{ "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": "Kilo Code CLI scores 73 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category.", "b": { "slug": "kilo-code-cli", "name": "Kilo Code CLI", "vendor": "Kilo Code Inc.", "vendorUrl": "https://kilo.ai", "kind": "harness", "category": "agent-harnesses", "summary": "Open-source coding agent for the terminal, forked from opencode and built from the same repository as Kilo's VS Code and JetBrains extensions. It runs with your own provider key, a local model or the Kilo Gateway.", "url": "https://www.anchorterminal.com/tools/kilo-code-cli", "markdownUrl": "https://www.anchorterminal.com/tools/kilo-code-cli.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/kilo-code-cli.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/kilo-code-cli.json", "repo": "https://github.com/Kilo-Org/kilocode", "license": "MIT", "transports": [], "packages": [ { "registry": "npm", "name": "@kilocode/cli" }, { "registry": "npm", "name": "@kilocode/sdk" } ], "auth": "mixed", "authNotes": "Your own provider key in `~/.config/kilo/kilo.jsonc` or the environment, a local model, or a Kilo account through `kilo auth login` for the Kilo Gateway and its free models. `kilo serve` runs unauthenticated unless `KILO_SERVER_PASSWORD` is set.", "pricing": "freemium", "pricingNotes": "The CLI is free and MIT-licensed, and needs no Kilo account with your own key or a local model. Kilo Gateway credits are billed at provider rates with a 5 per cent fee on credit purchases. Kilo Pass starts at $19 a month, Teams is $15 a user a month and Enterprise is quoted. The pricing page says the free tier needs no card.", "priceSummary": "$19 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the pricing page or the README (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 27539, "npmWeekly": 32804, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://kilo.ai/docs/code-with-ai/platforms/cli", "llmsTxt": "https://kilo.ai/docs/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "harness", "coding-agent", "cli", "open-source", "typescript", "mcp", "llms-txt", "telemetry-default-on", "freemium", "no-card", "local" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 73, "grade": "BB", "agentReady": true, "rank": 98, "ranked": true, "rankOf": 1135, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 87, "payments": 50, "reliability": 85, "schema": 90, "security": 64, "transparency": 76 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": -2, "negativeNotes": [ "2026-10-14. 7.8.10 added the conda client ID to default-on telemetry. When `~/.conda/aau_token` exists the CLI runs `conda info --json --offline` and attaches the ID (`aauClientToken`) to every PostHog event, and a commit hashing it was reverted. Neither the changelog nor the docs mention it. It respects Kilo's opt-out and conda's `anaconda_anon_usage: false`. -2. https://github.com/Kilo-Org/kilocode/blob/main/packages/kilo-telemetry/src/conda.ts" ], "verdict": "Shell commands ask before running by default, and an optional operating-system sandbox blocks writes outside the workspace and outbound network. Telemetry to PostHog is on by default and the sandbox is off, so an unattended `kilo run --auto` approves everything not denied unless both are configured first.", "bestFor": "Developers who want an open-source terminal agent with per-tool permission rules, an optional sandbox and a choice of provider, and the same engine in VS Code and JetBrains.", "strengths": [ "Permission rules of `allow`, `ask` or `deny` per tool with glob patterns, and shell commands asking by default outside a built-in allow list", "A sandbox on macOS and Linux that limits writes, blocks network by default and refuses to run when it can't be enforced", "Project config can't weaken the sandbox or read environment variables through `{env:VAR}`", "Your own provider key or a local model works with no Kilo account", "Releases most weeks, with 7.8.9, 7.8.10 and 7.8.12 between 13 and 15 October 2026" ], "weaknesses": [ "Telemetry to PostHog is on by default, attaches the conda client ID since 7.8.10, and the privacy policy doesn't mention it", "The sandbox is off by default and unavailable on Windows", "`kilo run` lists no flag for a turn, time or cost limit", "The terms grant a perpetual licence to use uploaded Customer Data to improve Kilo's services", "SECURITY.md still says the CLI has no sandbox, and NVD records an unanswered low-severity CVE from May 2026" ], "agentNotes": [ "Set `sandbox.enabled` to true in the global `kilo.jsonc` before `kilo run --auto`. `--auto` approves every permission request not explicitly denied", "Set `experimental.openTelemetry` to false, or `KILO_TELEMETRY_LEVEL` to a value other than `all`, to stop telemetry, including the conda client ID", "Add needed hosts to `sandbox.allowed_hosts` in global config. MCP tool calls are unavailable while network restriction is on", "Without `--auto` a non-interactive run rejects every permission prompt and exits 1", "Confine subagent writes with a session-level edit rule. From 7.8.13 a custom agent's own `edit` denies no longer bind the subagents it starts" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 73 } ], "editorialScores": { "ergonomics": 72, "maintenance": 87, "payments": 50, "reliability": 85, "schema": 90, "security": 64, "transparency": 61 }, "provenanceScore": 90 }, "connect": { "install": "npm install -g @kilocode/cli # or: brew install Kilo-Org/tap/kilo", "headless": { "command": "kilo run --auto --format json \"$TASK\"" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/kilo-code-cli" }, "area": "frameworks", "unitPrices": [ { "item": "Kilo Pass, entry tier", "unit": "month", "usd": 19, "note": "monthly model credits with bonus credits, optional" }, { "item": "Teams plan", "unit": "seat-month", "usd": 15, "note": "model use billed separately at provider rates" } ], "provenance": { "legalEntity": "Kilo Code Inc. (the terms are a contract with Anaconda, Inc. on behalf of itself and its affiliates, including Kilo Code Inc.)", "domain": "kilo.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "https://kilo.ai/terms", "privacy": "https://kilo.ai/privacy", "statusPage": "https://status.kilo.ai", "changelog": "https://github.com/Kilo-Org/kilocode/blob/main/packages/opencode/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The terms (last updated 30 September 2026) name the CLI among the services they cover and are made with Anaconda, Inc. The privacy policy (29 May 2026) names Kilo Code Inc. as data controller.", "kilo.ai/.well-known/security.txt lists security@kilo.ai and the policy at kilo.ai/security, names the CLI in scope and expires on 2026-12-31.", "trust.kilo.ai redirects to trust.anaconda.com, which has a Kilo Code section.", "status.kilo.ai is a Statuspage site for the website, gateway and cloud platform. The CLI runs on the owner's machine.", "PRIVACY.md in the repository is a separate short policy for the CLI dated March 2025." ], "score": 90 }, "requirements": { "card": "no", "freeTier": true, "minutes": 3, "credential": "mixed", "hosting": [ "self-hosted" ], "euResidency": "unknown", "trainsOnData": "unknown", "zeroRetention": "unknown", "selfHost": "yes" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/kilo-code-cli.json", "live": { "slug": "kilo-code-cli", "vendorStatus": { "page": "https://status.kilo.ai", "indicator": "maintenance", "summary": "Service Under Maintenance", "checkedAt": "2026-10-18T19:17:38.448295891Z" }, "versions": [ { "registry": "github", "name": "Kilo-Org/kilocode", "version": "jetbrains/v7.1.11", "released": "2026-10-16", "seenAt": "2026-10-18T02:55:29.251341634Z" }, { "registry": "npm", "name": "@kilocode/cli", "version": "7.8.12", "seenAt": "2026-10-18T02:55:26.949905974Z" }, { "registry": "npm", "name": "@kilocode/sdk", "version": "7.8.12", "seenAt": "2026-10-18T02:55:27.804205643Z" } ], "githubStars": 27641, "npmWeekly": 16165, "securityTxt": { "url": "https://kilo.ai/.well-known/security.txt", "state": "valid", "expires": "2026-12-31T23:59:59.000Z", "checkedAt": "2026-10-18T15:54:21.604811161Z" }, "llmsTxt": { "url": "https://kilo.ai/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-18T14:25:20.846290567Z" }, "domain": { "domain": "kilo.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/kilo.ai", "checkedAt": "2026-10-18T13:31:01.933025219Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/Kilo-Org/kilocode/main/packages/opencode/CHANGELOG.md", "kind": "changelog", "status": 304, "checkedAt": "2026-10-17T23:08:54.813972948Z", "changedAt": "2026-10-16T22:29:57.710209449Z", "fingerprint": "54fc57f1fa71" }, { "url": "https://kilo.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-17T23:04:39.797446489Z", "changedAt": "2026-10-16T22:25:44.849295384Z", "fingerprint": "3530880fcddd" }, { "url": "https://kilo.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-17T23:04:41.977656113Z", "changedAt": "2026-10-16T22:25:47.165449472Z", "fingerprint": "5664f5d29427" } ], "updatedAt": "2026-10-18T19:17:38.448295891Z" } }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Google (Google Research)", "b": "Kilo Code Inc.", "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": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-08", "b": "2026-10-15", "name": "Last release" }, { "a": "no document linked", "b": "2026-09-30", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-05-29", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "yes", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "4.2k stars", "b": "28k stars, 33k npm/wk", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "2.3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Kilo Code CLI scores 73 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category.", "question": "Which is better for AI agents, Harness² or Kilo Code 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).). Kilo Code CLI is open source (MIT).", "question": "Are Harness² and Kilo Code 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, 85 against 20", "Schema \u0026 documentation, 90 against 51", "Agent ergonomics, 72 against 59", "Security \u0026 auth, 64 against 44", "Payments \u0026 pricing, 50 against 40", "Maintenance \u0026 community, 87 against 36", "Transparency \u0026 trust, 76 against 44" ], "also": [ "Agent-ready, a grade of BB or better", "Free to start without a card" ], "goodFor": "Developers who want an open-source terminal agent with per-tool permission rules, an optional sandbox and a choice of provider, and the same engine in VS Code and JetBrains.", "slug": "kilo-code-cli", "watchFor": "Telemetry to PostHog is on by default, attaches the conda client ID since 7.8.10, and the privacy policy doesn't mention it" } ], "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-kilo-code-cli.json", "title": "Agent Zero vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-kilo-code-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-kilo-code-cli.json", "title": "Aider vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/aider-vs-kilo-code-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-kilo-code-cli.json", "title": "Amp vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/amp-vs-kilo-code-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-kilo-code-cli.json", "title": "Antigravity CLI vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-kilo-code-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-kilo-code-cli.json", "title": "Claude Code vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/claude-code-vs-kilo-code-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-kilo-code-cli.json", "title": "Cline vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/cline-vs-kilo-code-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-kilo-code-cli.json", "title": "Cursor CLI vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-kilo-code-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-kilo-code-cli.json", "title": "Devin vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/devin-vs-kilo-code-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-kilo-code-cli.json", "title": "Droid CLI vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-kilo-code-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-kilo-code-cli.json", "title": "Pi vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-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-kilo-code-cli.json", "title": "Gemini CLI vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-kilo-code-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-kilo-code-cli.json", "title": "GitHub Copilot CLI vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-kilo-code-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-kilo-code-cli.json", "title": "goose vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/goose-vs-kilo-code-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-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/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-kilo-code-cli.json", "title": "HarnessRouter vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-kilo-code-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/kilo-code-cli-vs-muse-code.json", "title": "Kilo Code CLI vs Muse Code", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-codex.json", "title": "Kilo Code CLI vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-opencode.json", "title": "Kilo Code CLI vs OpenCode", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openhands.json", "title": "Kilo Code CLI vs OpenHands", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-prime-agent.json", "title": "Kilo Code CLI vs Prime Agent", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-qwen-code.json", "title": "Kilo Code CLI vs Qwen Code", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-qwen-code" }, { "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/cli-manager-vs-kilo-code-cli.json", "title": "CLI Manager vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-kilo-code-cli.json", "title": "Harness vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-paperclip.json", "title": "Kilo Code CLI vs Paperclip", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-parallax-agents.json", "title": "Kilo Code CLI vs Parallax", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-parallax-agents" } ], "scores": [ { "by": 65, "edge": "kilo-code-cli", "harness2": 20, "key": "reliability", "kilo-code-cli": 85, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 39, "edge": "kilo-code-cli", "harness2": 51, "key": "schema", "kilo-code-cli": 90, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 13, "edge": "kilo-code-cli", "harness2": 59, "key": "ergonomics", "kilo-code-cli": 72, "name": "Agent ergonomics", "weight": 13 }, { "by": 20, "edge": "kilo-code-cli", "harness2": 44, "key": "security", "kilo-code-cli": 64, "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "edge": "kilo-code-cli", "harness2": 40, "key": "payments", "kilo-code-cli": 50, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 51, "edge": "kilo-code-cli", "harness2": 36, "key": "maintenance", "kilo-code-cli": 87, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 32, "edge": "kilo-code-cli", "harness2": 44, "key": "transparency", "kilo-code-cli": 76, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Kilo Code CLI scores 73 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. 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.", "kilo-code-cli": "Shell commands ask before running by default, and an optional operating-system sandbox blocks writes outside the workspace and outbound network. Telemetry to PostHog is on by default and the sandbox is off, so an unattended `kilo run --auto` approves everything not denied unless both are configured first." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli", "json": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.min.md" }, "markdown": "Kilo Code CLI scores 73 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. 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- Kilo Code CLI: grade BB, 73/100, rank #98 of 1135. Markdown https://www.anchorterminal.com/tools/kilo-code-cli.md · JSON https://www.anchorterminal.com/api/v1/tools/kilo-code-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\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### Kilo Code CLI (BB)\n\nGood for: Developers who want an open-source terminal agent with per-tool permission rules, an optional sandbox and a choice of provider, and the same engine in VS Code and JetBrains.\n\nAhead on:\n- Reliability, 85 against 20\n- Schema \u0026 documentation, 90 against 51\n- Agent ergonomics, 72 against 59\n- Security \u0026 auth, 64 against 44\n- Payments \u0026 pricing, 50 against 40\n- Maintenance \u0026 community, 87 against 36\n- Transparency \u0026 trust, 76 against 44\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Free to start without a card\n\nWatch for: Telemetry to PostHog is on by default, attaches the conda client ID since 7.8.10, and the privacy policy doesn't mention it\n\n\n## Score by category\n\n| Category | Weight | Harness² | Kilo Code CLI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 20 | 85 | Kilo Code CLI +65 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 51 | 90 | Kilo Code CLI +39 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 72 | Kilo Code CLI +13 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 64 | Kilo Code CLI +20 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 50 | Kilo Code CLI +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 36 | 87 | Kilo Code CLI +51 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 44 | 76 | Kilo Code CLI +32 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **41.6 · E** | **73 · BB** | |\n\n## Facts side by side\n\n| Fact | Harness² | Kilo Code CLI |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google (Google Research) | Kilo Code Inc. |\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). | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-08 | 2026-10-15 |\n| Terms last updated | no document linked | 2026-09-30 |\n| Privacy policy last updated | no document linked | 2026-05-29 |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | yes |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | yes |\n| Arbitration or class-action waiver | | yes |\n| Popularity | 4.2k stars | 28k stars, 33k npm/wk |\n| Agent reviews | 2.5/5 (4) | 2.3/5 (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**Kilo Code CLI.** Shell commands ask before running by default, and an optional operating-system sandbox blocks writes outside the workspace and outbound network. Telemetry to PostHog is on by default and the sandbox is off, so an unattended `kilo run --auto` approves everything not denied unless both are configured first.\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### Kilo Code CLI\n\n1. Set `sandbox.enabled` to true in the global `kilo.jsonc` before `kilo run --auto`. `--auto` approves every permission request not explicitly denied\n2. Set `experimental.openTelemetry` to false, or `KILO_TELEMETRY_LEVEL` to a value other than `all`, to stop telemetry, including the conda client ID\n3. Add needed hosts to `sandbox.allowed_hosts` in global config. MCP tool calls are unavailable while network restriction is on\n4. Without `--auto` a non-interactive run rejects every permission prompt and exits 1\n5. Confine subagent writes with a session-level edit rule. From 7.8.13 a custom agent's own `edit` denies no longer bind the subagents it starts\n\n## Questions\n\n### Which is better for AI agents, Harness² or Kilo Code CLI?\n\nKilo Code CLI scores 73 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category.\n\n### Are Harness² and Kilo Code 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).). Kilo Code CLI is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness2\", \"b\": \"kilo-code-cli\"}`. From a terminal: `anchor compare harness2 kilo-code-cli`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness2.json and https://www.anchorterminal.com/api/v1/tools/kilo-code-cli.json\n\n## Other comparisons with Harness² or Kilo Code CLI\n\n- [Agent Zero vs Harness²](https://www.anchorterminal.com/compare/agent-zero-vs-harness2.md)\n- [Agent Zero vs Kilo Code CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kilo-code-cli.md)\n- [Aider vs Harness²](https://www.anchorterminal.com/compare/aider-vs-harness2.md)\n- [Aider vs Kilo Code CLI](https://www.anchorterminal.com/compare/aider-vs-kilo-code-cli.md)\n- [Amp vs Harness²](https://www.anchorterminal.com/compare/amp-vs-harness2.md)\n- [Amp vs Kilo Code CLI](https://www.anchorterminal.com/compare/amp-vs-kilo-code-cli.md)\n- [Antigravity CLI vs Harness²](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness2.md)\n- [Antigravity CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-kilo-code-cli.md)\n- [Claude Code vs Harness²](https://www.anchorterminal.com/compare/claude-code-vs-harness2.md)\n- [Claude Code vs Kilo Code CLI](https://www.anchorterminal.com/compare/claude-code-vs-kilo-code-cli.md)\n- [Cline vs Harness²](https://www.anchorterminal.com/compare/cline-vs-harness2.md)\n- [Cline vs Kilo Code CLI](https://www.anchorterminal.com/compare/cline-vs-kilo-code-cli.md)\n- [Cursor CLI vs Harness²](https://www.anchorterminal.com/compare/cursor-cli-vs-harness2.md)\n- [Cursor CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-kilo-code-cli.md)\n- [Devin vs Harness²](https://www.anchorterminal.com/compare/devin-vs-harness2.md)\n- [Devin vs Kilo Code CLI](https://www.anchorterminal.com/compare/devin-vs-kilo-code-cli.md)\n- [Droid CLI vs Harness²](https://www.anchorterminal.com/compare/droid-cli-vs-harness2.md)\n- [Droid CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/droid-cli-vs-kilo-code-cli.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs Kilo Code CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-cli.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-kilo-code-cli.md)\n- [GitHub Copilot CLI vs Harness²](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness2.md)\n- [GitHub Copilot CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/github-copilot-cli-vs-kilo-code-cli.md)\n- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)\n- [goose vs Kilo Code CLI](https://www.anchorterminal.com/compare/goose-vs-kilo-code-cli.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.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- [Harness² vs Mirror CLI](https://www.anchorterminal.com/compare/harness2-vs-reflection-mirror.md)\n- [HarnessRouter vs Kilo Code CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-kilo-code-cli.md)\n- [Kilo Code CLI vs Kiro CLI](https://www.anchorterminal.com/compare/kilo-code-cli-vs-kiro-cli.md)\n- [Kilo Code CLI vs Muse Code](https://www.anchorterminal.com/compare/kilo-code-cli-vs-muse-code.md)\n- [Kilo Code CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-codex.md)\n- [Kilo Code CLI vs OpenCode](https://www.anchorterminal.com/compare/kilo-code-cli-vs-opencode.md)\n- [Kilo Code CLI vs OpenHands](https://www.anchorterminal.com/compare/kilo-code-cli-vs-openhands.md)\n- [Kilo Code CLI vs Prime Agent](https://www.anchorterminal.com/compare/kilo-code-cli-vs-prime-agent.md)\n- [Kilo Code CLI vs Qwen Code](https://www.anchorterminal.com/compare/kilo-code-cli-vs-qwen-code.md)\n- [Kilo Code CLI vs Mirror CLI](https://www.anchorterminal.com/compare/kilo-code-cli-vs-reflection-mirror.md)\n- [CLI Manager vs Kilo Code CLI](https://www.anchorterminal.com/compare/cli-manager-vs-kilo-code-cli.md)\n- [Harness vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-kilo-code-cli.md)\n- [Kilo Code CLI vs Paperclip](https://www.anchorterminal.com/compare/kilo-code-cli-vs-paperclip.md)\n- [Kilo Code CLI vs Parallax](https://www.anchorterminal.com/compare/kilo-code-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 Kilo Code CLI", "url": "" } ], "description": "Kilo Code CLI scores 73 (BB) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Harness² E 41.6", "Kilo Code CLI BB 73", "scores" ], "h1": "Harness² vs Kilo Code CLI", "image": "https://www.anchorterminal.com/assets/og/compare-harness2-vs-kilo-code-cli.png", "path": "/compare/harness2-vs-kilo-code-cli", "published": "2026-10-01", "section": "tools", "title": "Harness² vs Kilo Code CLI for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-18", "url": "https://www.anchorterminal.com/compare/harness2-vs-kilo-code-cli" }, "tokens": { "markdown": 3100, "slim": 730 }, "version": 1 }