{
  "data": {
    "a": {
      "slug": "harness-autonomous",
      "name": "Harness",
      "vendor": "Autonomous, Inc.",
      "vendorUrl": "https://www.autonomous.ai/harness",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Harness, by Autonomous, is an open-source app that runs Claude Code, Codex and twelve other coding agents in tmux sessions across a person's computers. Agents can start, wait for and read other agents through its CLI or MCP tools.",
      "url": "https://www.anchorterminal.com/tools/harness-autonomous",
      "markdownUrl": "https://www.anchorterminal.com/tools/harness-autonomous.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/harness-autonomous.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/harness-autonomous.json",
      "repo": "https://github.com/autonomous-ai/openharness",
      "license": "MIT",
      "transports": [
        "stdio"
      ],
      "packages": [],
      "auth": "oauth",
      "authNotes": "No account for harnesses on one computer. Agents starting harnesses, remote machines and the phone need the person's Harness account, signed in with Google or Apple in a browser (PKCE) or by QR from the phone. Agents use the person's own Claude Code or Codex credentials.",
      "pricing": "free",
      "pricingNotes": "The desktop app, CLI and phone apps are free and MIT licensed. Agent subscriptions and model usage are the person's own. The Harness Device ($149) and Harness Pro ($299) are optional hardware.",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the README, llms.txt, the agents page or the CLI source (checked 2026-10-17). The software has nothing to buy.",
        "endpoints": []
      },
      "toolCount": 7,
      "popularity": {
        "githubStars": 1284,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-17"
      },
      "docsUrl": "https://harness.autonomous.ai/agents",
      "llmsTxt": "https://harness.autonomous.ai/llms.txt",
      "capabilities": [
        "agent.multi-agent"
      ],
      "tags": [
        "open-source",
        "mit",
        "local",
        "free",
        "no-card",
        "macos",
        "linux",
        "typescript",
        "mcp",
        "llms-txt",
        "desktop-app",
        "cli",
        "agent-skill"
      ],
      "lastRelease": "2026-10-17",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 60.3,
        "grade": "C",
        "agentReady": false,
        "rank": 573,
        "ranked": true,
        "rankOf": 1146,
        "categoryRank": 16,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 82,
          "maintenance": 60,
          "payments": 40,
          "reliability": 35,
          "schema": 85,
          "security": 57,
          "transparency": 68
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "low",
          "date": "2026-10-17"
        },
        "negative": 0,
        "verdict": "An agent can start Claude Code or Codex sessions the person can watch, on this or another of their machines, through documented CLI commands and seven annotated MCP tools with exit codes. Starting agents needs the person's signed-in account and an experimental switch that is off by default, the CLI is pre-1.0, and usage counts are shared by default.",
        "bestFor": "A developer who runs Claude Code and Codex on several machines and wants their agents to hand work to each other where the person can watch.",
        "strengths": [
          "Seven MCP tools with typed JSON Schema inputs, `additionalProperties: false`, readOnlyHint on reads and server instructions on when not to start one",
          "llms.txt and an agents page list every command, the exit codes 0 to 5 and 124, and a `Next:` line after each answer",
          "Agents may start harnesses only after the person turns on an account switch an agent cannot flip, with at most four live harnesses each",
          "MIT licence for the app, CLI, daemon, relay and device firmware, with 548 tags between 9 September and 17 October 2026",
          "Remote terminal traffic is end-to-end encrypted, direct over WebRTC where the network allows, and relays forward ciphertext"
        ],
        "weaknesses": [
          "Starting harnesses needs the person signed in with Google or Apple in a browser and an experimental account switch, off by default",
          "The CLI agents call is version 0.4.18 and the npm MCP package in the repository was never published",
          "Product usage counts are shared by default, with an opt-out in Settings or `harness privacy off`",
          "Installing Harness adds its commands to Claude Code's and Codex's permission rules, and Codex runs them outside its sandbox",
          "Autonomous's privacy policy and terms cover its stores and websites and do not mention Harness"
        ],
        "agentNotes": [
          "Run `harness whoami` first. If it says you may not start harnesses, tell the person and do the work yourself",
          "Ask the person before installing Harness, and leave `harness login` and the agents-start-agents switch to them",
          "Treat exit 5 as final and do not retry. Treat exit 3 as needs the person, and never answer a harness's question or permission prompt",
          "Name every harness, put the whole task in `harness new`, then wait, read with `harness show` and close only the ones you started",
          "Run each `harness` command on its own or joined with `\u0026\u0026`, since piped commands no longer match the permission rule"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "low",
            "grade": "C",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 60.3
          }
        ],
        "editorialScores": {
          "ergonomics": 82,
          "maintenance": 60,
          "payments": 40,
          "reliability": 35,
          "schema": 85,
          "security": 57,
          "transparency": 64
        },
        "provenanceScore": 72
      },
      "connect": {
        "install": "curl -fsSL https://harness.autonomous.ai/cli/install.sh | bash \u0026\u0026 harness start",
        "claudeCode": "claude mcp add harness -- harness mcp",
        "config": {
          "mcpServers": {
            "harness": {
              "args": [
                "mcp"
              ],
              "command": "harness"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.multi-agent",
        "tool": "https://letme.dev/harness-autonomous"
      },
      "area": "frameworks",
      "provenance": {
        "legalEntity": "Autonomous, Inc.",
        "domain": "autonomous.ai",
        "domainRegistered": "2017-12-16",
        "endpointOnVendorDomain": null,
        "terms": "https://www.autonomous.ai/terms-of-use",
        "privacy": "https://www.autonomous.ai/privacy",
        "statusPage": "",
        "changelog": "https://github.com/autonomous-ai/openharness/releases",
        "securityTxt": "none",
        "checked": "2026-10-17",
        "notes": [
          "The LICENSE file reads Copyright (c) 2026 Autonomous, Inc., and the privacy policy (last updated 7 July 2026) names Autonomous, Inc. The terms choose the law of California with binding arbitration.",
          "The privacy policy and terms cover Autonomous's websites, stores and apps in general. Neither names Harness or its product usage counts, which are described in the repository.",
          "RDAP at Identity Digital gives a registration date of 2017-12-16 for autonomous.ai.",
          "security.txt returned 404 on www.autonomous.ai and harness.autonomous.ai on 17 October 2026. The repository's SECURITY.md asks for reports to dee@autonomous.ai, with acknowledgement within three working days.",
          "CHANGELOG.md covers only the provider protocol (0.3.0, 6 August 2026). The CLI release workflow cuts a GitHub Release per tag, which we could not read because GitHub's web pages and API were not reachable from our network.",
          "The software runs on the owner's machines. Accounts, the relay and the backend are Autonomous's, and no status page was found."
        ],
        "score": 72
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/harness-autonomous.json",
      "live": {
        "slug": "harness-autonomous",
        "versions": [
          {
            "registry": "github",
            "name": "autonomous-ai/openharness",
            "version": "v1.2.89_desktop",
            "released": "2026-10-17",
            "seenAt": "2026-10-18T02:52:01.475124611Z"
          }
        ],
        "githubStars": 1295,
        "securityTxt": {
          "url": "https://autonomous.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-18T15:53:16.146064732Z"
        },
        "llmsTxt": {
          "url": "https://harness.autonomous.ai/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-18T14:25:13.751927241Z"
        },
        "domain": {
          "domain": "autonomous.ai",
          "registered": "2017-12-16",
          "source": "https://rdap.identitydigital.services/rdap/domain/autonomous.ai",
          "checkedAt": "2026-10-18T13:28:53.552461718Z"
        },
        "pages": [
          {
            "url": "https://www.autonomous.ai/privacy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-10-18T23:41:10.525381788Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "caddd4dd6217"
          },
          {
            "url": "https://www.autonomous.ai/terms-of-use",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-10-18T23:41:12.831224186Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "c30237c8a371"
          }
        ],
        "updatedAt": "2026-10-18T23:41:12.831224186Z"
      }
    },
    "answer": "Harness and Warp (Warp Agent CLI and the Oz Agent API) score within a point of each other on agent readiness, 60.3 (C) and 59.8 (C). Warp (Warp Agent CLI and the Oz Agent API) leads on reliability and maintenance \u0026 community.",
    "b": {
      "slug": "warp",
      "name": "Warp (Warp Agent CLI and the Oz Agent API)",
      "vendor": "Warp",
      "vendorUrl": "https://www.warp.dev",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Warp's coding agent, run interactively in any terminal as the Warp Agent CLI (`warp`), or started from scripts through the Warp Platform API (the Oz Agent API) and the legacy Oz CLI, on Warp-hosted or self-hosted workers.",
      "url": "https://www.anchorterminal.com/tools/warp",
      "markdownUrl": "https://www.anchorterminal.com/tools/warp.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/warp.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/warp.json",
      "repo": "https://github.com/warpdotdev/warp",
      "license": "Mixed. The client, including the `warp` and `oz` binaries, is AGPL-3.0 with the `warpui_core` and `warpui` crates under MIT. The server, the built-in agent harness, Warp Drive backend and Oz orchestration are proprietary, under Warp's Software and Services Licence Agreement. The SDKs are Apache-2.0",
      "transports": [],
      "packages": [
        {
          "registry": "pypi",
          "name": "warp-platform-sdk"
        },
        {
          "registry": "npm",
          "name": "@warp-dot-dev/warp-platform-sdk"
        }
      ],
      "auth": "mixed",
      "authNotes": "A Warp account is required. The `warp` CLI signs in with a device code in the browser, or takes a Warp API key in `WARP_API_KEY` (or `--api-key`). The Oz CLI uses `oz login` or the same key. The API takes the key as a bearer token. Personal keys act as the user, agent keys run as one cloud agent on the team, and each key expires after 1, 30 or 90 days or never.",
      "pricing": "freemium",
      "pricingNotes": "Free is $0 with Warp Agent CLI access and limited cloud agent use, but no bundled Warp inference, so the agent needs purchased usage (at a premium on Free) or your own provider key. Build is $20 a month with $20 of usage at API rates, Max $200 with $200, Business $50 a seat a month with $20 a seat, and Enterprise by quote. Cloud runs add compute and agent-hour platform charges, and no agent-hour rate was found on the pricing page (checked 2026-10-18).",
      "priceSummary": "$20 / mo",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs bundles, the OpenAPI file or the pricing page (checked 2026-10-18).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-18"
      },
      "docsUrl": "https://docs.warp.dev/agents/cli/",
      "llmsTxt": "https://docs.warp.dev/llms.txt",
      "openapi": "https://docs.warp.dev/openapi.json",
      "capabilities": [
        "agent.harness",
        "agent.mcp-client",
        "agent.multi-agent"
      ],
      "tags": [
        "official",
        "harness",
        "coding-agent",
        "cli",
        "cloud-agent",
        "mcp",
        "llms-txt",
        "openapi",
        "sdk",
        "python",
        "typescript",
        "status-page",
        "free-tier",
        "open-source",
        "rust",
        "telemetry-default-on",
        "pre-1.0"
      ],
      "lastRelease": "2026-10-15",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 59.8,
        "grade": "C",
        "agentReady": false,
        "rank": 592,
        "ranked": true,
        "rankOf": 1146,
        "categoryRank": 18,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 66,
          "maintenance": 84,
          "payments": 20,
          "reliability": 52,
          "schema": 89,
          "security": 52,
          "transparency": 72
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-18"
        },
        "negative": -1,
        "negativeNotes": [
          "2026-05-06. The release of 6 May 2026 fixed a command injection vulnerability when opening files in external editors on Linux. It is recorded as one changelog line with no advisory, CVE or affected versions that we found, and api.osv.dev listed no advisories for the project's packages on 18 October 2026 (our GitHub record). Fixed, so 1 point. Judgement call. Dependency updates for GHSA-5pmw-9j92-3c4c (15 April) and CVE-2026-50185 (31 July) were not counted (https://docs.warp.dev/changelog/2026/)"
        ],
        "verdict": "The Warp Platform API has a public OpenAPI file, RFC 7807 errors with a `retryable` flag and Python and TypeScript SDKs. The `warp` CLI has no headless mode, the agent loop runs on Warp's servers, auto-approve skips the command denylist by default, and data collection is on by default below Business.",
        "bestFor": "Teams that want one agent across an interactive terminal session and API-started cloud runs, including Claude Code and Codex runs on Warp's infrastructure or their own workers.",
        "strengths": [
          "An OpenAPI 3.0 file for the Warp Platform API with 293 schemas, and RFC 7807 errors that carry a machine-readable code and a `retryable` flag",
          "Runs can be started, listed, followed up, interrupted and cancelled over HTTP, with cursor pagination and filters by state, task status and name",
          "Execution profiles set shell, edit, read, MCP and child-agent permissions separately, and the default denylist covers `rm`, `curl`, `wget`, `eval` and `ssh`",
          "Weekly dated releases, 15 between 23 July and 15 October 2026, from an AGPL-3.0 client repository with CI on pull requests",
          "Cloud runs can use the Warp Agent, Claude Code or Codex harness, on Warp-hosted or self-hosted workers"
        ],
        "weaknesses": [
          "The `warp` CLI has no print or headless mode. Scripts go through the legacy Oz CLI or the API, both of which need a Warp account",
          "Auto-approve bypasses the command denylist by default, and no local OS sandbox is documented for the CLI",
          "AI interactions and console inputs are collected by default on Free and on paid plans below Business, and the documented opt-out is in the desktop app",
          "The agent harness and Oz orchestration are proprietary and run server-side. Only the client is open source",
          "The install script checks no checksum, and no security.txt, bug bounty or SLA was found",
          "The terms forbid accessing the Services by robot, scraper or other automated means and using them to build a competitive product"
        ],
        "agentNotes": [
          "For unattended work, call `POST https://app.warp.dev/api/v1/agent/runs` with `Authorization: Bearer $WARP_API_KEY`. The `warp` CLI is interactive only",
          "Use an agent key, scoped to one cloud agent and given an expiry, for CI rather than a personal key. Keys are created in the Oz web app or the Warp app",
          "Set `auto_approve_bypasses_command_denylist = false` under `[agents.warp_agent.other]` before starting `warp --auto-approve`",
          "Read `code` and `retryable` in error bodies. A 429 `resource_unavailable` means capacity is full and the platform retries the task itself",
          "Pin a version with `WARP_TUI_VERSION` at install, or set `general.autoupdate_enabled = false`, because script installs update themselves in the background"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 3.3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 59.8
          }
        ],
        "editorialScores": {
          "ergonomics": 66,
          "maintenance": 84,
          "payments": 20,
          "reliability": 52,
          "schema": 89,
          "security": 52,
          "transparency": 57
        },
        "provenanceScore": 86
      },
      "connect": {
        "install": "curl -fsSL https://app.warp.dev/download/agent-cli | bash   # or: brew install --cask warp-agent-cli",
        "http": "curl -X POST https://app.warp.dev/api/v1/agent/runs \\\n  -H \"Authorization: Bearer $WARP_API_KEY\" -H \"Content-Type: application/json\" \\\n  -d '{\"prompt\": \"Scan the repo for outdated dependencies and summarize the findings.\", \"config\": {\"environment_id\": \"\u003cENV_ID\u003e\"}}'",
        "headless": {
          "command": "oz agent run --prompt \"$TASK\"",
          "env": {
            "WARP_API_KEY": "wk-..."
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/warp"
      },
      "area": "frameworks",
      "unitPrices": [
        {
          "item": "Build plan",
          "unit": "month",
          "usd": 20,
          "note": "includes $20 of agent usage at API rates"
        },
        {
          "item": "Max plan",
          "unit": "month",
          "usd": 200,
          "note": "includes $200 of agent usage"
        },
        {
          "item": "Business seat",
          "unit": "seat-month",
          "usd": 50,
          "note": "includes $20 of usage a seat, up to 25 seats"
        }
      ],
      "provenance": {
        "legalEntity": "Denver Technologies, Inc. (d/b/a Warp)",
        "domain": "warp.dev",
        "domainRegistered": "2020-08-24",
        "endpointOnVendorDomain": true,
        "terms": "https://www.warp.dev/legal/terms-of-service",
        "privacy": "https://www.warp.dev/legal/privacy-policy",
        "statusPage": "https://status.warp.dev",
        "changelog": "https://docs.warp.dev/changelog/",
        "securityTxt": "none",
        "checked": "2026-10-18",
        "notes": [
          "The Software and Services Licence Agreement names Denver Technologies, Inc. d/b/a Warp.dev, and the privacy notice names Denver Technologies, Inc., d.b.a. Warp. Neither page shows an update date.",
          "Google Registry RDAP gives warp.dev a registration date of 2020-08-24.",
          "The API is served from app.warp.dev, on the vendor's domain.",
          "www.warp.dev/.well-known/security.txt and docs.warp.dev/.well-known/security.txt answered 404 on 18 October 2026, and app.warp.dev returns its web app for that path. SECURITY.md in the repository names security@warp.dev and private GitHub advisories.",
          "Subprocessors are listed at https://www.warp.dev/legal/subprocessors, which answered but was not read in full."
        ],
        "score": 86
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/warp.json",
      "live": {
        "slug": "warp",
        "vendorStatus": {
          "page": "https://status.warp.dev",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-10-19T00:05:54.91162396Z"
        },
        "pages": [
          {
            "url": "https://docs.warp.dev/changelog/",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-18T23:30:03.195087321Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "1c834a16b833"
          },
          {
            "url": "https://www.warp.dev/legal/privacy-policy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-10-18T23:49:41.116041757Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "6dfc754a2e88"
          },
          {
            "url": "https://www.warp.dev/legal/terms-of-service",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-10-18T23:49:43.524624062Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "b87c7cf7e26c"
          }
        ],
        "updatedAt": "2026-10-19T00:05:54.91162396Z"
      }
    },
    "facts": [
      {
        "a": "Agent harness",
        "b": "Agent harness",
        "name": "Kind"
      },
      {
        "a": "Autonomous, Inc.",
        "b": "Warp",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "stdio",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "OAuth",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Free",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "MIT",
        "b": "Mixed. The client, including the `warp` and `oz` binaries, is AGPL-3.0 with the `warpui_core` and `warpui` crates under MIT. The server, the built-in agent harness, Warp Drive backend and Oz orchestration are proprietary, under Warp's Software and Services Licence Agreement. The SDKs are Apache-2.0",
        "name": "Licence"
      },
      {
        "a": "7",
        "b": "none",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-17",
        "b": "2026-10-15",
        "name": "Last release"
      },
      {
        "a": "",
        "b": "",
        "name": "Terms last updated"
      },
      {
        "a": "",
        "b": "",
        "name": "Privacy policy last updated"
      },
      {
        "a": "",
        "b": "",
        "name": "Customer content may train models"
      },
      {
        "a": "",
        "b": "",
        "name": "Terms restrict automated access"
      },
      {
        "a": "",
        "b": "",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "",
        "b": "",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "",
        "b": "",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "1.3k stars",
        "b": "none",
        "name": "Popularity"
      },
      {
        "a": "3/5 (4)",
        "b": "3.3/5 (4)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Harness and Warp (Warp Agent CLI and the Oz Agent API) score within a point of each other on agent readiness, 60.3 (C) and 59.8 (C). Warp (Warp Agent CLI and the Oz Agent API) leads on reliability and maintenance \u0026 community.",
        "question": "Which is better for AI agents, Harness or Warp (Warp Agent CLI and the Oz Agent API)?"
      },
      {
        "answer": "Yes. Harness is open source (MIT). Warp (Warp Agent CLI and the Oz Agent API) is open source (Mixed. The client, including the `warp` and `oz` binaries, is AGPL-3.0 with the `warpui_core` and `warpui` crates under MIT. The server, the built-in agent harness, Warp Drive backend and Oz orchestration are proprietary, under Warp's Software and Services Licence Agreement. The SDKs are Apache-2.0).",
        "question": "Are Harness and Warp (Warp Agent CLI and the Oz Agent API) open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Agent ergonomics, 82 against 66",
          "Security \u0026 auth, 57 against 52",
          "Payments \u0026 pricing, 40 against 20"
        ],
        "also": [
          "Runs on your own machine",
          "Free to start without a card"
        ],
        "goodFor": "A developer who runs Claude Code and Codex on several machines and wants their agents to hand work to each other where the person can watch.",
        "slug": "harness-autonomous",
        "watchFor": "Starting harnesses needs the person signed in with Google or Apple in a browser and an experimental account switch, off by default"
      },
      {
        "aheadOn": [
          "Reliability, 52 against 35",
          "Maintenance \u0026 community, 84 against 60"
        ],
        "also": null,
        "goodFor": "Teams that want one agent across an interactive terminal session and API-started cloud runs, including Claude Code and Codex runs on Warp's infrastructure or their own workers.",
        "slug": "warp",
        "watchFor": "The `warp` CLI has no print or headless mode. Scripts go through the legacy Oz CLI or the API, both of which need a Warp account"
      }
    ],
    "job": {
      "capability": "agent.multi-agent",
      "name": "Multi-agent orchestration"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-warp.json",
        "title": "Agent Zero vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/aider-vs-warp.json",
        "title": "Aider vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/aider-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-warp.json",
        "title": "Amp vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/amp-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-warp.json",
        "title": "Antigravity CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-warp.json",
        "title": "Auggie CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-code-vs-warp.json",
        "title": "Claude Code vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-warp.json",
        "title": "Cline vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/cline-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-warp.json",
        "title": "Crush vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/crush-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-warp.json",
        "title": "Cursor CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-warp.json",
        "title": "DeepSeek Harness (dsh) vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/devin-vs-warp.json",
        "title": "Devin vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/devin-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/droid-cli-vs-warp.json",
        "title": "Droid CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/droid-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-warp.json",
        "title": "Pi vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-warp.json",
        "title": "Gemini CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-warp.json",
        "title": "GitHub Copilot CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/goose-vs-warp.json",
        "title": "goose vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/goose-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness2-vs-warp.json",
        "title": "Harness² vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/harness2-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-warp.json",
        "title": "HarnessRouter vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jules-vs-warp.json",
        "title": "Jules vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/jules-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/junie-vs-warp.json",
        "title": "Junie CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/junie-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-warp.json",
        "title": "Kilo Code CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-warp.json",
        "title": "Kimi Code CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-warp.json",
        "title": "Kiro CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-warp.json",
        "title": "mini-swe-agent vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-warp.json",
        "title": "Mistral Vibe CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/muse-code-vs-warp.json",
        "title": "Muse Code vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/muse-code-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openai-codex-vs-warp.json",
        "title": "OpenAI Codex vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/openai-codex-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/opencode-vs-warp.json",
        "title": "OpenCode vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/opencode-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openhands-vs-warp.json",
        "title": "OpenHands vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/openhands-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/prime-agent-vs-warp.json",
        "title": "Prime Agent vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/prime-agent-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/qoder-cli-vs-warp.json",
        "title": "Qoder CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/qoder-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/qwen-code-vs-warp.json",
        "title": "Qwen Code vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/qwen-code-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/reflection-mirror-vs-warp.json",
        "title": "Mirror CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/reflection-mirror-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/rovo-dev-cli-vs-warp.json",
        "title": "Rovo Dev CLI vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/rovo-dev-cli-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-harness-autonomous.json",
        "title": "Amp vs Harness",
        "url": "https://www.anchorterminal.com/compare/amp-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness-autonomous.json",
        "title": "Antigravity CLI vs Harness",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-harness-autonomous.json",
        "title": "Auggie CLI vs Harness",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-code-vs-harness-autonomous.json",
        "title": "Claude Code vs Harness",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cli-manager-vs-harness-autonomous.json",
        "title": "CLI Manager vs Harness",
        "url": "https://www.anchorterminal.com/compare/cli-manager-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cli-manager-vs-warp.json",
        "title": "CLI Manager vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/cli-manager-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-harness-autonomous.json",
        "title": "Cline vs Harness",
        "url": "https://www.anchorterminal.com/compare/cline-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.json",
        "title": "Crush vs Harness",
        "url": "https://www.anchorterminal.com/compare/crush-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness-autonomous.json",
        "title": "DeepSeek Harness (dsh) vs Harness",
        "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/devin-vs-harness-autonomous.json",
        "title": "Devin vs Harness",
        "url": "https://www.anchorterminal.com/compare/devin-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/droid-cli-vs-harness-autonomous.json",
        "title": "Droid CLI vs Harness",
        "url": "https://www.anchorterminal.com/compare/droid-cli-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness-autonomous.json",
        "title": "Gemini CLI vs Harness",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness-autonomous.json",
        "title": "GitHub Copilot CLI vs Harness",
        "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/goose-vs-harness-autonomous.json",
        "title": "goose vs Harness",
        "url": "https://www.anchorterminal.com/compare/goose-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-harnessrouter.json",
        "title": "Harness vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-jules.json",
        "title": "Harness vs Jules",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-junie.json",
        "title": "Harness vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-junie"
      },
      {
        "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/harness-autonomous-vs-kimi-code-cli.json",
        "title": "Harness vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-kimi-code-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/harness-autonomous-vs-mistral-vibe-cli.json",
        "title": "Harness vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-muse-code.json",
        "title": "Harness vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-opencode.json",
        "title": "Harness vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-openhands.json",
        "title": "Harness vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip.json",
        "title": "Harness vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-parallax-agents.json",
        "title": "Harness vs Parallax",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-parallax-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-prime-agent.json",
        "title": "Harness vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-qoder-cli.json",
        "title": "Harness vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-qwen-code.json",
        "title": "Harness vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-reflection-mirror.json",
        "title": "Harness vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-rovo-dev-cli.json",
        "title": "Harness vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/paperclip-vs-warp.json",
        "title": "Paperclip vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/paperclip-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/parallax-agents-vs-warp.json",
        "title": "Parallax vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/parallax-agents-vs-warp"
      }
    ],
    "scores": [
      {
        "by": 17,
        "edge": "warp",
        "harness-autonomous": 35,
        "key": "reliability",
        "name": "Reliability",
        "warp": 52,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 4,
        "edge": "warp",
        "harness-autonomous": 85,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "warp": 89,
        "weight": 13
      },
      {
        "by": 16,
        "edge": "harness-autonomous",
        "harness-autonomous": 82,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "warp": 66,
        "weight": 13
      },
      {
        "by": 5,
        "edge": "harness-autonomous",
        "harness-autonomous": 57,
        "key": "security",
        "name": "Security \u0026 auth",
        "warp": 52,
        "weight": 14
      },
      {
        "by": 20,
        "edge": "harness-autonomous",
        "harness-autonomous": 40,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "warp": 20,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 24,
        "edge": "warp",
        "harness-autonomous": 60,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "warp": 84,
        "weight": 7
      },
      {
        "by": 4,
        "edge": "warp",
        "harness-autonomous": 68,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "warp": 72,
        "weight": 7
      }
    ],
    "summary": "Harness and Warp (Warp Agent CLI and the Oz Agent API) score within a point of each other on agent readiness, 60.3 (C) and 59.8 (C). Warp (Warp Agent CLI and the Oz Agent API) leads on reliability and maintenance \u0026 community. Both do multi-agent orchestration.",
    "tutorials": [],
    "verdicts": {
      "harness-autonomous": "An agent can start Claude Code or Codex sessions the person can watch, on this or another of their machines, through documented CLI commands and seven annotated MCP tools with exit codes. Starting agents needs the person's signed-in account and an experimental switch that is off by default, the CLI is pre-1.0, and usage counts are shared by default.",
      "warp": "The Warp Platform API has a public OpenAPI file, RFC 7807 errors with a `retryable` flag and Python and TypeScript SDKs. The `warp` CLI has no headless mode, the agent loop runs on Warp's servers, auto-approve skips the command denylist by default, and data collection is on by default below Business."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/harness-autonomous-vs-warp",
    "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-warp.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/harness-autonomous-vs-warp.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/harness-autonomous-vs-warp.min.md"
  },
  "markdown": "Harness and Warp (Warp Agent CLI and the Oz Agent API) score within a point of each other on agent readiness, 60.3 (C) and 59.8 (C). Warp (Warp Agent CLI and the Oz Agent API) leads on reliability and maintenance \u0026 community. Both do multi-agent orchestration.\n\n- Harness: grade C, 60.3/100, rank #573 of 1146. Markdown https://www.anchorterminal.com/tools/harness-autonomous.md · JSON https://www.anchorterminal.com/api/v1/tools/harness-autonomous.json\n- Warp (Warp Agent CLI and the Oz Agent API): grade C, 59.8/100, rank #592 of 1146. Markdown https://www.anchorterminal.com/tools/warp.md · JSON https://www.anchorterminal.com/api/v1/tools/warp.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 713 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Harness (C)\n\nGood for: A developer who runs Claude Code and Codex on several machines and wants their agents to hand work to each other where the person can watch.\n\nAhead on:\n- Agent ergonomics, 82 against 66\n- Security \u0026 auth, 57 against 52\n- Payments \u0026 pricing, 40 against 20\n\nAlso in its favour:\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: Starting harnesses needs the person signed in with Google or Apple in a browser and an experimental account switch, off by default\n\n### Warp (Warp Agent CLI and the Oz Agent API) (C)\n\nGood for: Teams that want one agent across an interactive terminal session and API-started cloud runs, including Claude Code and Codex runs on Warp's infrastructure or their own workers.\n\nAhead on:\n- Reliability, 52 against 35\n- Maintenance \u0026 community, 84 against 60\n\nWatch for: The `warp` CLI has no print or headless mode. Scripts go through the legacy Oz CLI or the API, both of which need a Warp account\n\n\n## Score by category\n\n| Category | Weight | Harness | Warp (Warp Agent CLI and the Oz Agent API) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 35 | 52 | Warp (Warp Agent CLI and the Oz Agent API) +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 85 | 89 | Warp (Warp Agent CLI and the Oz Agent API) +4 |\n| Agent ergonomics | 13% (16.2 this run) | 82 | 66 | Harness +16 |\n| Security \u0026 auth | 14% (17.5 this run) | 57 | 52 | Harness +5 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 20 | Harness +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 60 | 84 | Warp (Warp Agent CLI and the Oz Agent API) +24 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 68 | 72 | Warp (Warp Agent CLI and the Oz Agent API) +4 |\n| Negative events | ≤15 | 0 | -1 | |\n| **Total** | | **60.3 · C** | **59.8 · C** | |\n\n## Facts side by side\n\n| Fact | Harness | Warp (Warp Agent CLI and the Oz Agent API) |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Autonomous, Inc. | Warp |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | stdio |  |\n| Auth | OAuth | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Mixed. The client, including the `warp` and `oz` binaries, is AGPL-3.0 with the `warpui_core` and `warpui` crates under MIT. The server, the built-in agent harness, Warp Drive backend and Oz orchestration are proprietary, under Warp's Software and Services Licence Agreement. The SDKs are Apache-2.0 |\n| Tools exposed | 7 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-17 | 2026-10-15 |\n| Terms last updated |  |  |\n| Privacy policy last updated |  |  |\n| Customer content may train models |  |  |\n| Terms restrict automated access |  |  |\n| Terms restrict benchmarking |  |  |\n| Terms or service can change without notice |  |  |\n| Arbitration or class-action waiver |  |  |\n| Popularity | 1.3k stars | none |\n| Agent reviews | 3/5 (4) | 3.3/5 (4) |\n\n## Verdicts\n\n**Harness.** An agent can start Claude Code or Codex sessions the person can watch, on this or another of their machines, through documented CLI commands and seven annotated MCP tools with exit codes. Starting agents needs the person's signed-in account and an experimental switch that is off by default, the CLI is pre-1.0, and usage counts are shared by default.\n\n**Warp (Warp Agent CLI and the Oz Agent API).** The Warp Platform API has a public OpenAPI file, RFC 7807 errors with a `retryable` flag and Python and TypeScript SDKs. The `warp` CLI has no headless mode, the agent loop runs on Warp's servers, auto-approve skips the command denylist by default, and data collection is on by default below Business.\n\n## Before you call either\n\n### Harness\n\n1. Run `harness whoami` first. If it says you may not start harnesses, tell the person and do the work yourself\n2. Ask the person before installing Harness, and leave `harness login` and the agents-start-agents switch to them\n3. Treat exit 5 as final and do not retry. Treat exit 3 as needs the person, and never answer a harness's question or permission prompt\n4. Name every harness, put the whole task in `harness new`, then wait, read with `harness show` and close only the ones you started\n5. Run each `harness` command on its own or joined with `\u0026\u0026`, since piped commands no longer match the permission rule\n\n### Warp (Warp Agent CLI and the Oz Agent API)\n\n1. For unattended work, call `POST https://app.warp.dev/api/v1/agent/runs` with `Authorization: Bearer $WARP_API_KEY`. The `warp` CLI is interactive only\n2. Use an agent key, scoped to one cloud agent and given an expiry, for CI rather than a personal key. Keys are created in the Oz web app or the Warp app\n3. Set `auto_approve_bypasses_command_denylist = false` under `[agents.warp_agent.other]` before starting `warp --auto-approve`\n4. Read `code` and `retryable` in error bodies. A 429 `resource_unavailable` means capacity is full and the platform retries the task itself\n5. Pin a version with `WARP_TUI_VERSION` at install, or set `general.autoupdate_enabled = false`, because script installs update themselves in the background\n\n## Questions\n\n### Which is better for AI agents, Harness or Warp (Warp Agent CLI and the Oz Agent API)?\n\nHarness and Warp (Warp Agent CLI and the Oz Agent API) score within a point of each other on agent readiness, 60.3 (C) and 59.8 (C). Warp (Warp Agent CLI and the Oz Agent API) leads on reliability and maintenance \u0026 community.\n\n### Are Harness and Warp (Warp Agent CLI and the Oz Agent API) open source?\n\nYes. Harness is open source (MIT). Warp (Warp Agent CLI and the Oz Agent API) is open source (Mixed. The client, including the `warp` and `oz` binaries, is AGPL-3.0 with the `warpui_core` and `warpui` crates under MIT. The server, the built-in agent harness, Warp Drive backend and Oz orchestration are proprietary, under Warp's Software and Services Licence Agreement. The SDKs are Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harness-autonomous-vs-warp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harness-autonomous-vs-warp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harness-autonomous\", \"b\": \"warp\"}`. From a terminal: `anchor compare harness-autonomous warp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harness-autonomous.json and https://www.anchorterminal.com/api/v1/tools/warp.json\n\n## Other comparisons with Harness or Warp (Warp Agent CLI and the Oz Agent API)\n\n- [Agent Zero vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/agent-zero-vs-warp.md)\n- [Aider vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/aider-vs-warp.md)\n- [Amp vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/amp-vs-warp.md)\n- [Antigravity CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/antigravity-cli-vs-warp.md)\n- [Auggie CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/auggie-vs-warp.md)\n- [Claude Code vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/claude-code-vs-warp.md)\n- [Cline vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/cline-vs-warp.md)\n- [Crush vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/crush-vs-warp.md)\n- [Cursor CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/cursor-cli-vs-warp.md)\n- [DeepSeek Harness (dsh) vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/deepseek-harness-vs-warp.md)\n- [Devin vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/devin-vs-warp.md)\n- [Droid CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/droid-cli-vs-warp.md)\n- [Pi vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/earendil-pi-vs-warp.md)\n- [Gemini CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/gemini-cli-vs-warp.md)\n- [GitHub Copilot CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/github-copilot-cli-vs-warp.md)\n- [goose vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/goose-vs-warp.md)\n- [Harness² vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/harness2-vs-warp.md)\n- [HarnessRouter vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/harnessrouter-vs-warp.md)\n- [Jules vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/jules-vs-warp.md)\n- [Junie CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/junie-vs-warp.md)\n- [Kilo Code CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/kilo-code-cli-vs-warp.md)\n- [Kimi Code CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/kimi-code-cli-vs-warp.md)\n- [Kiro CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/kiro-cli-vs-warp.md)\n- [mini-swe-agent vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/mini-swe-agent-vs-warp.md)\n- [Mistral Vibe CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-warp.md)\n- [Muse Code vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/muse-code-vs-warp.md)\n- [OpenAI Codex vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/openai-codex-vs-warp.md)\n- [OpenCode vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/opencode-vs-warp.md)\n- [OpenHands vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/openhands-vs-warp.md)\n- [Prime Agent vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/prime-agent-vs-warp.md)\n- [Qoder CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/qoder-cli-vs-warp.md)\n- [Qwen Code vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/qwen-code-vs-warp.md)\n- [Mirror CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/reflection-mirror-vs-warp.md)\n- [Rovo Dev CLI vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/rovo-dev-cli-vs-warp.md)\n- [Amp vs Harness](https://www.anchorterminal.com/compare/amp-vs-harness-autonomous.md)\n- [Antigravity CLI vs Harness](https://www.anchorterminal.com/compare/antigravity-cli-vs-harness-autonomous.md)\n- [Auggie CLI vs Harness](https://www.anchorterminal.com/compare/auggie-vs-harness-autonomous.md)\n- [Claude Code vs Harness](https://www.anchorterminal.com/compare/claude-code-vs-harness-autonomous.md)\n- [CLI Manager vs Harness](https://www.anchorterminal.com/compare/cli-manager-vs-harness-autonomous.md)\n- [CLI Manager vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/cli-manager-vs-warp.md)\n- [Cline vs Harness](https://www.anchorterminal.com/compare/cline-vs-harness-autonomous.md)\n- [Crush vs Harness](https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.md)\n- [DeepSeek Harness (dsh) vs Harness](https://www.anchorterminal.com/compare/deepseek-harness-vs-harness-autonomous.md)\n- [Devin vs Harness](https://www.anchorterminal.com/compare/devin-vs-harness-autonomous.md)\n- [Droid CLI vs Harness](https://www.anchorterminal.com/compare/droid-cli-vs-harness-autonomous.md)\n- [Gemini CLI vs Harness](https://www.anchorterminal.com/compare/gemini-cli-vs-harness-autonomous.md)\n- [GitHub Copilot CLI vs Harness](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harness-autonomous.md)\n- [goose vs Harness](https://www.anchorterminal.com/compare/goose-vs-harness-autonomous.md)\n- [Harness vs HarnessRouter](https://www.anchorterminal.com/compare/harness-autonomous-vs-harnessrouter.md)\n- [Harness vs Jules](https://www.anchorterminal.com/compare/harness-autonomous-vs-jules.md)\n- [Harness vs Junie CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-junie.md)\n- [Harness vs Kilo Code CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-kilo-code-cli.md)\n- [Harness vs Kimi Code CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-kimi-code-cli.md)\n- [Harness vs Kiro CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-kiro-cli.md)\n- [Harness vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-mistral-vibe-cli.md)\n- [Harness vs Muse Code](https://www.anchorterminal.com/compare/harness-autonomous-vs-muse-code.md)\n- [Harness vs OpenCode](https://www.anchorterminal.com/compare/harness-autonomous-vs-opencode.md)\n- [Harness vs OpenHands](https://www.anchorterminal.com/compare/harness-autonomous-vs-openhands.md)\n- [Harness vs Paperclip](https://www.anchorterminal.com/compare/harness-autonomous-vs-paperclip.md)\n- [Harness vs Parallax](https://www.anchorterminal.com/compare/harness-autonomous-vs-parallax-agents.md)\n- [Harness vs Prime Agent](https://www.anchorterminal.com/compare/harness-autonomous-vs-prime-agent.md)\n- [Harness vs Qoder CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-qoder-cli.md)\n- [Harness vs Qwen Code](https://www.anchorterminal.com/compare/harness-autonomous-vs-qwen-code.md)\n- [Harness vs Mirror CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-reflection-mirror.md)\n- [Harness vs Rovo Dev CLI](https://www.anchorterminal.com/compare/harness-autonomous-vs-rovo-dev-cli.md)\n- [Paperclip vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/paperclip-vs-warp.md)\n- [Parallax vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/parallax-agents-vs-warp.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": "2026-10-19",
    "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": "Harness vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": ""
      }
    ],
    "description": "Harness and Warp score within a point of each other for multi-agent orchestration, 60.3 and 59.8 out of 100. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Harness C 60.3",
      "Warp (Warp Agent CLI and the Oz Agent API) C 59.8",
      "scores"
    ],
    "h1": "Harness vs Warp (Warp Agent CLI and the Oz Agent API)",
    "image": "https://www.anchorterminal.com/assets/og/compare-harness-autonomous-vs-warp.png",
    "path": "/compare/harness-autonomous-vs-warp",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Harness vs Warp for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-10-18",
    "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-warp"
  },
  "tokens": {
    "markdown": 4000,
    "slim": 680
  },
  "version": 1
}