{
  "data": {
    "a": {
      "slug": "gemini-cli",
      "name": "Gemini CLI",
      "vendor": "Google",
      "vendorUrl": "https://geminicli.com",
      "company": "google.com",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Google's open-source coding agent for the terminal, in TypeScript on Node 20 or newer, now maintained for Gemini Code Assist Standard and Enterprise users on Google Cloud.",
      "url": "https://www.anchorterminal.com/tools/gemini-cli",
      "markdownUrl": "https://www.anchorterminal.com/tools/gemini-cli.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-cli.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-cli.json",
      "dns": "gemini-cli.grade.anchorterminal.com",
      "repo": "https://github.com/google-gemini/gemini-cli",
      "license": "Apache-2.0",
      "transports": [],
      "packages": [
        {
          "registry": "npm",
          "name": "@google/gemini-cli"
        }
      ],
      "auth": "mixed",
      "authNotes": "Google sign-in works only with a Gemini Code Assist Standard or Enterprise licence. Google AI Pro, Google AI Ultra and the free Code Assist for individuals tier stopped working with Gemini CLI on 18 June 2026. Otherwise use a paid Gemini API key from AI Studio, or Vertex AI credentials. Google's terms forbid using the Gemini CLI sign-in from third-party software.",
      "pricing": "usage",
      "pricingNotes": "Free to install (Apache-2.0). Model access is paid. Use a paid Gemini API key or Vertex AI at token rates, or an existing Code Assist Standard or Enterprise licence. New Standard and Enterprise subscriptions ended on 9 October 2026. Token prices are public without a login, and requests are limited per minute (checked 2026-10-10). The free 1,000 requests a day tier ended on 18 June 2026, and whether an unpaid key still gets 250 Flash requests a day is unclear.",
      "priceSummary": "Pay per use",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-02).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 107000,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-02"
      },
      "docsUrl": "https://geminicli.com/docs/",
      "llmsTxt": "https://geminicli.com/llms.txt",
      "capabilities": [
        "agent.harness",
        "agent.mcp-client",
        "agent.multi-agent"
      ],
      "tags": [
        "official",
        "harness",
        "coding-agent",
        "cli",
        "open-source",
        "typescript",
        "mcp",
        "llms-txt",
        "telemetry-default-on",
        "pre-1.0",
        "gemini-only",
        "sign-in-ended",
        "paid-api-key"
      ],
      "lastRelease": "2026-10-27",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 66,
        "grade": "B",
        "agentReady": false,
        "rank": 508,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 15,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 78,
          "maintenance": 88,
          "payments": 30,
          "reliability": 71,
          "schema": 93,
          "security": 67,
          "transparency": 90
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-01"
        },
        "negative": -7,
        "negativeNotes": [
          "2026-04-24. GHSA-wpqr-6v78-jr5g (CVE-2026-12537), critical. In CI, headless Gemini CLI trusted the workspace folder automatically and loaded its configuration, and `--yolo` ignored fine-grained tool allowlists, so a workflow fed untrusted pull requests or issues could run an attacker's code. Fixed in @google/gemini-cli 0.39.1 and run-gemini-cli 0.1.22 and published, so the deduction is small (-2) (https://api.osv.dev/v1/vulns/GHSA-wpqr-6v78-jr5g)",
          "2026-06-18. Google sign-in for individuals ended on 18 June 2026. The README was corrected on 16 October 2026, but the quota and pricing page (last updated 18 June 2026, read on 1 November) still opens by describing a generous free tier, with 1,000 requests a day by Google sign-in and 250 by an unpaid key, so the claim is misleading. With the README and the authentication page corrected and the page's own banner saying unpaid-tier users moved to Antigravity CLI, the claim now stands on one page, so the deduction is -2, as routerplus and openbb take for one page advertising a free tier that isn't there (https://geminicli.com/docs/resources/quota-and-pricing/)",
          "2026-09-08 and 2026-09-23. 0.59.0 \"Prevented Server-Side Request Forgery (SSRF) during Model Context Protocol (MCP) OAuth metadata discovery and authentication\" and 0.61.0 \"Prevented indirect prompt injection vulnerabilities via build file modifications and untrusted flags\". Both are released fixes of flaws in the CLI's own code, and SECURITY.md says disclosure goes through GitHub Security Advisories, but OSV has no advisory for either, so -3, one term for both (https://github.com/google-gemini/gemini-cli/blob/main/docs/changelogs/index.md)"
        ],
        "verdict": "Apache-2.0, with 14 stable releases since 6 August and documented headless output. Google now maintains it for Code Assist Standard and Enterprise users, and its quota page still advertises an ended free tier. Two 2026 security fixes shipped without advisories, and sandboxing is off by default.",
        "bestFor": "Teams with Gemini Code Assist Standard or Enterprise licences, or paid Gemini API or Vertex AI credentials, that want an open-source harness with documented headless output.",
        "strengths": [
          "Apache-2.0 licence, with CI and end-to-end workflows in the repository and priority-labelled issue triage",
          "A stable release every Tuesday after a week in preview, under a written release policy",
          "Headless JSON and stream-json output with documented exit codes, including 53 for the turn limit",
          "A TOML policy engine with admin policy paths, folder trust on by default and a setting that blocks yolo mode",
          "Pay-per-token access through a Gemini API key or Vertex AI, with token prices published without a login"
        ],
        "weaknesses": [
          "Sandboxing is off by default, and the default macOS profile allows network",
          "Google sign-in for individuals ended on 18 June 2026, but the quota and pricing page still advertises a free tier of 1,000 requests a day",
          "SSRF and prompt-injection fixes in 0.59.0 and 0.61.0 shipped with no published advisory",
          "Usage statistics on by default, with one setting to turn them off",
          "Pre-1.0 at 0.66.0, Gemini models only, and not optimised for the Gemini 4 series"
        ],
        "agentNotes": [
          "Set `GEMINI_TRUST_WORKSPACE` to true only for trusted inputs in CI. Since 0.39.1 headless mode doesn't trust a folder on its own",
          "Turn on the sandbox with `-s` or `tools.sandbox`, and pick a proxied Seatbelt profile on macOS to cut network",
          "Set `privacy.usageStatisticsEnabled` to false to stop usage statistics",
          "Since 0.63.0, plans run without interactive confirmation in non-interactive mode, so set the approval mode explicitly before a headless run",
          "Authenticate with a paid Gemini API key or Vertex credentials. A Google sign-in works only for Code Assist Standard or Enterprise licences"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 3.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 66
          }
        ],
        "editorialScores": {
          "ergonomics": 78,
          "maintenance": 88,
          "payments": 30,
          "reliability": 71,
          "schema": 93,
          "security": 67,
          "transparency": 85
        },
        "provenanceScore": 94,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-01",
            "maintenance": "2026-11-01",
            "payments": "2026-11-01",
            "reliability": "2026-11-01",
            "schema": "2026-11-01",
            "security": "2026-11-01",
            "transparency": "2026-11-01"
          },
          "last": "2026-11-01",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "npm i -g @google/gemini-cli   # or: brew install gemini-cli",
        "headless": {
          "run": "gemini -p \"fix the failing test\" --output-format json --approval-mode auto_edit"
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/gemini-cli"
      },
      "sameCompany": [
        "gemini-4-carbon",
        "gemini-4-hydrogen",
        "gemini-api",
        "vertex-ai",
        "embeddinggemma-2",
        "embeddinggemma-300m",
        "gemini-embedding",
        "vertex-ai-tuning",
        "cloud-run-gpus",
        "google-model-armor",
        "shieldgemma",
        "google-imagen",
        "gemini-omni-1-2-flash",
        "google-veo",
        "google-lyria",
        "google-speech-to-text",
        "google-cloud-tts",
        "gemini-live",
        "google-adk",
        "google-memory-bank",
        "google-secret-manager",
        "google-cloud-document-ai",
        "google-weather-api",
        "chrome-devtools-mcp",
        "puppeteer",
        "mcp-toolbox-databases",
        "google-maps-platform",
        "google-cloud-translation",
        "google-calendar-api",
        "firebase-cloud-messaging",
        "google-cloud-storage",
        "google-drive-api",
        "gemini-enterprise",
        "gemini-decision-1",
        "antigravity-cli",
        "harness2",
        "jules",
        "gemini-spark",
        "google-search-console",
        "google-ads-api",
        "google-forms",
        "google-sheets-api",
        "gmail-api",
        "google-people-api",
        "diffusiongemma-26b-a4b-it",
        "gemma-4-12b-it",
        "gemma-4-26b-a4b-it",
        "gemma-4-31b-it",
        "gemma-4-e2b-it",
        "gemma-4-e4b-it",
        "virustotal"
      ],
      "area": "frameworks",
      "provenance": {
        "legalEntity": "Google LLC",
        "domain": "google.com",
        "domainRegistered": "1997-09-15",
        "endpointOnVendorDomain": null,
        "terms": "https://geminicli.com/docs/resources/tos-privacy",
        "privacy": "https://policies.google.com/privacy",
        "statusPage": "https://aistudio.google.com/status",
        "changelog": "https://geminicli.com/docs/changelogs",
        "securityTxt": "valid",
        "checked": "2026-10-01",
        "notes": [
          "The docs are on geminicli.com. The terms page there maps each sign-in method to its own terms and privacy notice (Gemini Code Assist, the Gemini API unpaid and paid services, Google Cloud).",
          "The status page is the Gemini API's. We found no status page for Gemini Code Assist sign-ins.",
          "Legal entity, domain date and security.txt for google.com are from the gemini-api listing's check of 26 September 2026."
        ],
        "score": 94
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-cli.json",
      "live": {
        "slug": "gemini-cli",
        "vendorStatus": {
          "page": "https://aistudio.google.com/status",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-09T20:23:47.625419872Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "google-gemini/gemini-cli",
            "version": "v0.68.0",
            "released": "2026-11-10",
            "seenAt": "2026-11-18T17:49:49.317627081Z"
          },
          {
            "registry": "npm",
            "name": "@google/gemini-cli",
            "version": "0.68.0",
            "seenAt": "2026-11-18T17:49:45.976671483Z"
          }
        ],
        "githubStars": 108920,
        "npmWeekly": 495285,
        "securityTxt": {
          "url": "https://google.com/.well-known/security.txt",
          "state": "valid",
          "expires": "2030-04-01T00:00:00z",
          "checkedAt": "2026-11-18T16:31:15.950099081Z"
        },
        "llmsTxt": {
          "url": "https://geminicli.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:14:24.061785542Z"
        },
        "domain": {
          "domain": "google.com",
          "registered": "1997-09-15",
          "source": "https://rdap.verisign.com/com/v1/domain/google.com",
          "checkedAt": "2026-11-15T15:15:24.267716809Z"
        },
        "pages": [
          {
            "url": "https://geminicli.com/docs/changelogs",
            "kind": "changelog",
            "status": 304,
            "checkedAt": "2026-11-18T21:44:13.481777325Z",
            "changedAt": "2026-10-16T22:24:43.917434922Z",
            "fingerprint": "24695165e4c4"
          },
          {
            "url": "https://developers.google.com/gemini-code-assist/docs/deprecations/code-assist-individuals",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:37:54.727400928Z",
            "changedAt": "2026-11-03T07:45:25.386419276Z",
            "fingerprint": "8f4cbb317c56"
          },
          {
            "url": "https://docs.cloud.google.com/gemini/docs/deprecations/features",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:39:35.189738369Z",
            "changedAt": "2026-11-11T16:56:50.58266773Z",
            "fingerprint": "525b9947ebc9"
          },
          {
            "url": "https://geminicli.com/docs/resources/tos-privacy",
            "kind": "terms",
            "status": 304,
            "checkedAt": "2026-11-18T21:44:15.540450912Z",
            "changedAt": "2026-10-16T22:24:46.06478046Z",
            "fingerprint": "5c52aa00c74e"
          }
        ],
        "github": {
          "repo": "google-gemini/gemini-cli",
          "checkedAt": "2026-11-16T12:03:58.8782423Z",
          "stars": 108864,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-16T01:39:00Z",
          "openIssues": 458,
          "openPRs": 271,
          "issuesOpened90d": 463,
          "issuesClosed90d": 568,
          "prsMerged90d": 250,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 44,
            "failure": 6,
            "other": 0,
            "latest": "success",
            "latestAt": "2026-11-13T20:10:34Z"
          },
          "replies": {
            "sampled": 23,
            "unanswered": 21,
            "medianDays": 0.2
          }
        },
        "updatedAt": "2026-11-18T21:44:15.540450912Z"
      }
    },
    "answer": "herdr scores 71.1 (BB) on agent readiness against Gemini CLI's 66 (B), and leads in 1 of 7 scored categories. Gemini CLI leads on reliability, agent ergonomics, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.",
    "b": {
      "slug": "herdr",
      "name": "herdr",
      "vendor": "herdr",
      "vendorUrl": "https://herdr.dev",
      "company": "herdr.dev",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "herdr, now called Herdr TUI, is an open-source terminal workspace manager for coding agents such as Claude Code and Codex. Their terminals keep running in a background server that scripts and agents drive through a CLI and socket API.",
      "url": "https://www.anchorterminal.com/tools/herdr",
      "markdownUrl": "https://www.anchorterminal.com/tools/herdr.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/herdr.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/herdr.json",
      "dns": "herdr.grade.anchorterminal.com",
      "repo": "https://github.com/herdrdev/herdr",
      "license": "Apache-2.0",
      "transports": [],
      "packages": [],
      "auth": "none",
      "authNotes": "No account. The CLI talks to the local server over a socket under the herdr config directory, created owner-only (mode 0600) per the source. Remote machines are reached over the person's own SSH profiles, and herdr leaves SSH authentication to the person.",
      "pricing": "free",
      "pricingNotes": "Free and Apache-2.0 licensed. herdr.dev answers \"Is it free? Yes\" for the app, herdr-core and Herdr TUI, and links no pricing page. The README gives hey@herdr.dev for enterprise and partnership enquiries.",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "Local software with nothing to buy in the repository. No x402, MPP or L402 in the source or docs, read on 2026-11-18.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 51700,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://herdr.dev/tui/docs/",
      "llmsTxt": "https://herdr.dev/llms.txt",
      "capabilities": [
        "agent.multi-agent"
      ],
      "tags": [
        "open-source",
        "apache-2.0",
        "local",
        "free",
        "cli",
        "rust",
        "pre-1.0",
        "agent-skill",
        "no-sandbox",
        "linux",
        "macos",
        "windows"
      ],
      "lastRelease": "2026-10-14",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 71.1,
        "grade": "BB",
        "agentReady": true,
        "rank": 279,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 9,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 73,
          "maintenance": 63,
          "payments": 90,
          "reliability": 65,
          "schema": 91,
          "security": 49,
          "transparency": 70
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal.",
        "bestFor": "A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.",
        "strengths": [
          "`herdr api schema --json` prints a JSON Schema for every socket request, response, error and event, and the docs are versioned per release",
          "`agent prompt --wait` sends a prompt and waits for the agent to settle in one request, and refuses with `agent_blocked` when the agent is at an approval dialogue",
          "Apache-2.0, with no account and no telemetry found in the source. Version and manifest checks to herdr.dev can each be turned off",
          "Six releases from 7 September to 14 October 2026 (0.9.0 to 0.9.5), with a changelog that has Breaking Changes and Removed sections"
        ],
        "weaknesses": [
          "Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 2026",
          "No sandbox and no permission model inside a session. Any process in a pane can send keys to another agent's pane",
          "No SECURITY.md, disclosure policy or security.txt",
          "495 open issues on 18 November 2026, and unsolicited pull requests are closed automatically",
          "herdr.dev now leads with a separate Herdr app, and the privacy page doesn't mention Herdr TUI"
        ],
        "agentNotes": [
          "Check `HERDR_ENV=1` before any herdr command. If it isn't set, tell the person you aren't inside herdr and stop",
          "Use `herdr agent prompt \u003cname\u003e --wait` rather than a separate prompt and wait, so a fast agent can't finish between the two calls",
          "If a wait times out or stalls, read the pane with `herdr agent read` before sending the prompt again, since it may have been delivered",
          "If an agent is `blocked`, show the person the dialogue and let them answer it",
          "Close only the panes, tabs and workspaces you created, unless the person asks otherwise"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 71.1
          }
        ],
        "editorialScores": {
          "ergonomics": 73,
          "maintenance": 63,
          "payments": 90,
          "reliability": 65,
          "schema": 91,
          "security": 49,
          "transparency": 78
        },
        "provenanceScore": 61,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "lastMoved": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "curl -fsSL https://herdr.dev/install.sh | sh   # or: brew install herdr; agent skill: npx skills add herdrdev/herdr --skill herdr -g"
      },
      "letme": {
        "capability": "https://letme.dev/agent.multi-agent",
        "tool": "https://letme.dev/herdr"
      },
      "area": "frameworks",
      "provenance": {
        "legalEntity": "Herdr, Inc.",
        "domain": "herdr.dev",
        "domainRegistered": "",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "https://herdr.dev/privacy/",
        "statusPage": "",
        "changelog": "https://github.com/herdrdev/herdr/blob/master/CHANGELOG.md",
        "securityTxt": "none",
        "checked": "2026-11-18",
        "notes": [
          "herdr.dev's privacy page (last updated 2 November 2026) names Herdr, Inc. It covers the desktop app, the mobile apps and herdr.dev, keeps usage reports for three months and stores no IP addresses. It doesn't mention Herdr TUI. No terms of service are linked from herdr.dev.",
          "herdr.dev's robots.txt allows every agent. The site serves llms.txt, and /.well-known/security.txt answers with the home page, so there is no security.txt (read 18 November 2026).",
          "Local software, so there is no vendor endpoint or status page. Background checks to herdr.dev/latest.json and the manifest service are documented with switches to turn them off.",
          "No SECURITY.md was found in the repository. CI pins actions to commit SHAs and Dependabot is configured."
        ],
        "score": 61
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/herdr.json"
    },
    "edges": [
      {
        "by": 60,
        "category": "payments",
        "leads": "herdr",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "Harness reading of the published rubric. No payment protocol (0). Token prices and plan prices are public without a login (20). The 1,000 requests a day Google sign-in tier ended on 18 June 2026. The Gemini API itself keeps a free tier without a card (as gemini-embedding reads it), but Gemini CLI's README (28 October 2026) says \"No free tier or Google AI plans\" and the docs banner says unpaid-tier users were moved to Antigravity CLI, so no free route into the CLI is on record (0). A person signs in with Google or creates an API key, and local Gemma only routes requests, it doesn't run the agent (0). 0 + 20 + 0 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.",
          "b": "No payment protocol (0). Read with the self-hosted rule. herdr.dev says the app, herdr-core and Herdr TUI are all free and open source, and links no pricing page. Free (30), no card (30), and no account or signup at all (30). 0 + 30 + 30 + 30 = 90."
        },
        "scores": {
          "a": 30,
          "b": 90
        }
      },
      {
        "by": 25,
        "category": "maintenance",
        "leads": "gemini-cli",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "0.66.0 on 2026-10-27 (30). 14 stable releases from 3 August to 1 November (0.54.0, 0.54.4, 0.55.1 and 0.56.0 to 0.66.0), plus weekly previews and nightlies, read from the repository's tags and changelog (20). 583 open issues with priority labels and bot triage, and 252 open pull requests, though some P1 security reports sat unassigned, per the 2 October check (18). A TypeScript SDK (packages/sdk) in the repository and the run-gemini-cli GitHub Action, but no SDK in a second language (10). CI, nightly evals and an Allstar policy (10). 30 + 20 + 18 + 10 + 10 = 88.",
          "b": "v0.9.5 on 14 October 2026, 35 days before the check, and the last commit on master on 29 October (20). Six releases from 7 September to 14 October 2026 (20). 495 open issues and 26 open pull requests. The 25 newest issues were labelled triaged with a priority within a day of opening. Unsolicited pull requests are closed automatically and a monthly workflow closes stale issues (15). Not an MCP server and no official SDK (0). Cargo.lock, Dependabot and CI on three systems, run results unread (8). 20 + 20 + 15 + 0 + 8 = 63."
        },
        "scores": {
          "a": 88,
          "b": 63
        }
      },
      {
        "by": 20,
        "category": "transparency",
        "leads": "gemini-cli",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "Apache-2.0 (30). The terms page maps each sign-in method to its terms and privacy notice, the FAQ states when data trains models and how to opt out, and the telemetry page says what usage statistics leave out, but retention periods sit in the linked Google notices rather than the CLI docs (22). Dated deprecation notices exist. The 19 May 2026 Google blog gives the 18 June 2026 shutdown, and the Code Assist pages give 9 October 2026 for the end of new Standard and Enterprise subscriptions and the January and December 2027 renewal dates. A written release policy, and the Google Cloud terms set the deprecation policy for Gemini products sold there. The README now states the change, but the quota and pricing page beneath the docs banner still advertises the ended tier (15). Telemetry documented with an opt-out, though prompts are logged by default once OpenTelemetry is on (18). 30 + 22 + 15 + 18 = 85.",
          "b": "Apache-2.0 (30). herdr.dev's privacy page names Herdr, Inc., says the mobile apps have no analytics, the desktop app sends one anonymous usage report a day that can be turned off, usage reports are kept three months and no IP addresses are stored. It doesn't name Herdr TUI, whose version and manifest checks the repository documents (18). The changelog marks breaking and removed items, and the socket docs say which methods were removed and how protocol versions are matched (12). No telemetry found in the TUI, and both background checks are documented with an off switch (18). 30 + 18 + 12 + 18 = 78."
        },
        "scores": {
          "a": 90,
          "b": 70
        }
      },
      {
        "by": 18,
        "category": "security",
        "leads": "gemini-cli",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Usage statistics on by default (`privacy.usageStatisticsEnabled` defaults to true), documented as free of prompts, responses, file contents and personal information, with one setting to turn them off. Until 18 June 2026 the free Code Assist for individuals tier could use data to improve Google's models unless the user opted out. Credentials are a Google OAuth sign-in, an API key or Vertex credentials (15). Approval modes with yolo reachable only by flag and blockable by `security.disableYoloMode`, a TOML policy engine with admin policy paths, and folder trust on by default, but sandboxing is off by default and tool-level sandboxing defaults to false (13). Environment-variable redaction, and 0.61.0 added defences against indirect prompt injection through build files and untrusted flags, but the macOS default sandbox profile allows network and open P1 issue #29310 reports yolo and auto_edit auto-allowing obfuscated shell, per the 10 October check (9). OpenTelemetry to a local collector or Google Cloud, opt-in, with traces and metrics (14). SECURITY.md routes reports to g.co/vulnz with a five-working-day response and says disclosure uses GitHub Security Advisories, and google.com has a valid security.txt to 2030. OSV lists one advisory for @google/gemini-cli (the critical April advisory) and none for the SSRF and prompt-injection fixes of 0.59.0 and 0.61.0 (16). SOC 2 isn't scored on the framework reading. 15 + 13 + 9 + 14 + 16 = 67.",
          "b": "Harness reading of the framework checklist, as for Harness and agents-tree. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No account, no telemetry found in the source, and a socket file set to 0600. Version and manifest checks reach herdr.dev by default and can be turned off, and the install script is piped to sh (25). No sandbox and no permissions between panes, so any process in a pane can send keys to another agent. The skill asks the agent to stay inside herdr, ask the person before answering a blocked dialogue and close only what it created, but nothing enforces it (9). Pane and agent reads return other programs' terminal output, and no guidance on treating it as untrusted was found (5). A server log, but no per-call audit log found (5). No SECURITY.md or disclosure policy in the repository, and herdr.dev serves no security.txt. CI pins actions to commit SHAs and Dependabot is on (5). 25 + 9 + 5 + 5 + 5 = 49."
        },
        "scores": {
          "a": 67,
          "b": 49
        }
      },
      {
        "by": 6,
        "category": "reliability",
        "leads": "gemini-cli",
        "name": "Reliability",
        "reasons": {
          "a": "Local-package reading. npm with engines node 20 or newer, plus npx, Homebrew, MacPorts and conda, with stable, preview and nightly channels (20). Public CI with ci.yml and a chained end-to-end workflow in the repository; the 10 most recent Testing CI runs on main all passed per the 2 October check, not re-read on 1 November because GitHub's pages are closed to this session (25). 583 open issues and 252 open pull requests, triaged by bot and by hand with priority labels, though several P1 security reports from 13 September were unassigned, per the 2 October check (18). releases.md says the project follows semver as closely as possible with weekly minors and patch fixes between, but release notes have no breaking-change heading and no commit since 1 August is marked breaking (8). 0.66.0, pre-1.0 (0). 20 + 25 + 18 + 8 + 0 = 71.",
          "b": "Read as local software, as for agents-tree and Harness. Official release binaries for Linux, macOS and Windows x86_64 with an install script, and Homebrew and mise in the README. The Homebrew formula wasn't read (20). .github/workflows/ci.yml runs checks and tests on ubuntu, macOS and Windows for every push and pull request, but run results couldn't be read from this session, so 15, the value this run gives public CI with unread results. 495 issues were open on 18 November 2026. The 25 newest, opened 15 to 18 November, all carry a triaged label and a priority (p1 or p2), several of them bugs, so reports are sorted within a day but many stay open (15). Semver tags and a Keep a Changelog file with Breaking Changes and Removed sections (15). Version 0.9.5, not 1.0, and not declared stable (0). 20 + 15 + 15 + 15 + 0 = 65."
        },
        "scores": {
          "a": 71,
          "b": 65
        }
      },
      {
        "by": 5,
        "category": "ergonomics",
        "leads": "gemini-cli",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Framework reading, adapted to a harness driven by a pipeline. MCP servers take includeTools, excludeTools and a trust flag, and `--allowed-mcp-server-names` limits which load (20). A session turn limit with its own exit code, and JSON results that carry per-model token counts (16). Documented exit codes and an error object in JSON output (18). `--resume` and checkpointing (14). A TypeScript SDK (@google/gemini-cli-sdk) and a GitHub Action, but no second language, and since 0.39.1 a CI run has to set `GEMINI_TRUST_WORKSPACE` to work in its own checkout (10).",
          "b": "Framework reading, how much an agent has to carry. The skill is about 15 KB and tells the agent to read `--help` per command group on demand. Reads take `--lines` and `--source recent` (20 of 25). Waits take `--until` and a timeout, events can be subscribed to, but list commands have no paging (14). Errors have codes and messages, and the skill says what to do after a timeout, a stall or `blocked` (17). `agent prompt --wait` submits and waits in one request to avoid a race, `agent.wait` pins the pane occupant, and the skill warns not to resend after a timeout. No idempotency keys (14). Most commands default to the caller's or focused pane. No SDK, only the CLI and raw socket (8). 20 + 14 + 17 + 14 + 8 = 73."
        },
        "scores": {
          "a": 78,
          "b": 73
        }
      }
    ],
    "facts": [
      {
        "a": "Agent harness",
        "b": "Agent harness",
        "name": "Kind"
      },
      {
        "a": "Google",
        "b": "herdr",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Apache-2.0",
        "b": "Apache-2.0",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-27",
        "b": "2026-10-14",
        "name": "Last release"
      },
      {
        "a": "couldn't be read",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "2026-10-01",
        "b": "2026-11-02",
        "name": "Privacy policy last updated"
      },
      {
        "a": "yes",
        "b": "not read yet",
        "name": "Customer content may train models"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Terms restrict automated access"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "couldn't be read",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "107k stars",
        "b": "52k stars",
        "name": "Popularity"
      },
      {
        "a": "3.5/5 (2)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "herdr scores 71.1 (BB) on agent readiness against Gemini CLI's 66 (B), and leads in 1 of 7 scored categories. Gemini CLI leads on reliability, agent ergonomics, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.",
        "question": "Which is better for AI agents, Gemini CLI or herdr?"
      },
      {
        "answer": "Yes. Gemini CLI is open source (Apache-2.0). herdr is open source (Apache-2.0).",
        "question": "Are Gemini CLI and herdr open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 71 against 65",
          "Agent ergonomics, 78 against 73",
          "Security \u0026 auth, 67 against 49",
          "Maintenance \u0026 community, 88 against 63",
          "Transparency \u0026 trust, 90 against 70"
        ],
        "also": null,
        "goodFor": "Teams with Gemini Code Assist Standard or Enterprise licences, or paid Gemini API or Vertex AI credentials, that want an open-source harness with documented headless output.",
        "slug": "gemini-cli",
        "watchFor": "Sandboxing is off by default, and the default macOS profile allows network"
      },
      {
        "aheadOn": [
          "Payments \u0026 pricing, 90 against 30"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "No key needed to call it",
          "No incidents deducted, where Gemini CLI loses 7 points for them"
        ],
        "goodFor": "A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.",
        "slug": "herdr",
        "watchFor": "Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 2026"
      }
    ],
    "history": {
      "gemini-cli": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 1.2,
          "from": 64.8,
          "fromGrade": "B",
          "to": 66,
          "toGrade": "B"
        },
        {
          "causes": [
            "correction"
          ],
          "date": "2026-11-01",
          "delta": -2,
          "from": 66.8,
          "fromGrade": "B",
          "to": 64.8,
          "toGrade": "B"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-27",
          "delta": 0.1,
          "from": 66.7,
          "fromGrade": "B",
          "to": 66.8,
          "toGrade": "B"
        }
      ],
      "herdr": [
        {
          "causes": [
            "terms",
            "evidence"
          ],
          "date": "2026-11-18",
          "delta": 4.2,
          "from": 66.9,
          "fromGrade": "B",
          "to": 71.1,
          "toGrade": "BB"
        }
      ]
    },
    "job": {
      "capability": "agent.multi-agent",
      "name": "Multi-agent orchestration"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-gemini-cli.json",
        "title": "Agent Zero vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/aider-vs-gemini-cli.json",
        "title": "Aider vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/aider-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-gemini-cli.json",
        "title": "Amp vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/amp-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-gemini-cli.json",
        "title": "Antigravity CLI vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-gemini-cli.json",
        "title": "Auggie CLI vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-gemini-cli.json",
        "title": "AXLR vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli.json",
        "title": "boxes.dev vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli.json",
        "title": "Claude Code vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-gemini-cli.json",
        "title": "Click vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-gemini-cli.json",
        "title": "Cline vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/cline-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/conductor-vs-gemini-cli.json",
        "title": "Conductor vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/conductor-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-gemini-cli.json",
        "title": "Crush vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-gemini-cli.json",
        "title": "Cursor CLI vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-gemini-cli.json",
        "title": "DeepSeek Harness (dsh) vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-gemini-cli.json",
        "title": "dsh-superagent (DeepSeek) vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/devin-vs-gemini-cli.json",
        "title": "Devin vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/devin-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/droid-cli-vs-gemini-cli.json",
        "title": "Droid CLI vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/droid-cli-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli.json",
        "title": "Pi vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/emdash-vs-gemini-cli.json",
        "title": "Emdash vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/emdash-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-github-copilot-cli.json",
        "title": "Gemini CLI vs GitHub Copilot CLI",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-github-copilot-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-goose.json",
        "title": "Gemini CLI vs goose",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-goose"
      },
      {
        "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-harnessrouter.json",
        "title": "Gemini CLI vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-jules.json",
        "title": "Gemini CLI vs Jules",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-junie.json",
        "title": "Gemini CLI vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-junie"
      },
      {
        "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/gemini-cli-vs-kimi-code-cli.json",
        "title": "Gemini CLI vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-kiro-cli.json",
        "title": "Gemini CLI vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-letta.json",
        "title": "Gemini CLI vs Letta",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-mini-swe-agent.json",
        "title": "Gemini CLI vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-minimax-code.json",
        "title": "Gemini CLI vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-mistral-vibe-cli.json",
        "title": "Gemini CLI vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-muse-code.json",
        "title": "Gemini CLI vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api.json",
        "title": "Gemini CLI vs OpenAI Agents API",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-codex.json",
        "title": "Gemini CLI vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-codex"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-opencode.json",
        "title": "Gemini CLI vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-openhands.json",
        "title": "Gemini CLI vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-openmausbot.json",
        "title": "Gemini CLI vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-orca.json",
        "title": "Gemini CLI vs Orca",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-paseo.json",
        "title": "Gemini CLI vs Paseo",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-prime-agent.json",
        "title": "Gemini CLI vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-qoder-cli.json",
        "title": "Gemini CLI vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-qwen-code.json",
        "title": "Gemini CLI vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-reflection-mirror.json",
        "title": "Gemini CLI vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-rovo-dev-cli.json",
        "title": "Gemini CLI vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-sculptor.json",
        "title": "Gemini CLI vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-t3-code.json",
        "title": "Gemini CLI vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-traycer.json",
        "title": "Gemini CLI vs Traycer",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-unstoppable.json",
        "title": "Gemini CLI vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-verdent.json",
        "title": "Gemini CLI vs Verdent",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-vibe-trading.json",
        "title": "Gemini CLI vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-vibe-trading"
      },
      {
        "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/agent-relay-vs-gemini-cli.json",
        "title": "Agent Relay vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/agent-relay-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-relay-vs-herdr.json",
        "title": "Agent Relay vs herdr",
        "url": "https://www.anchorterminal.com/compare/agent-relay-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-herdr.json",
        "title": "Amp vs herdr",
        "url": "https://www.anchorterminal.com/compare/amp-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-herdr.json",
        "title": "Antigravity CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-herdr.json",
        "title": "Auggie CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-herdr.json",
        "title": "AXLR vs herdr",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-herdr.json",
        "title": "boxes.dev vs herdr",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-code-vs-herdr.json",
        "title": "Claude Code vs herdr",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/clawboo-vs-gemini-cli.json",
        "title": "Clawboo vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/clawboo-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/clawboo-vs-herdr.json",
        "title": "Clawboo vs herdr",
        "url": "https://www.anchorterminal.com/compare/clawboo-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cli-manager-vs-gemini-cli.json",
        "title": "CLI Manager vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/cli-manager-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cli-manager-vs-herdr.json",
        "title": "CLI Manager vs herdr",
        "url": "https://www.anchorterminal.com/compare/cli-manager-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-herdr.json",
        "title": "Cline vs herdr",
        "url": "https://www.anchorterminal.com/compare/cline-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/conductor-vs-herdr.json",
        "title": "Conductor vs herdr",
        "url": "https://www.anchorterminal.com/compare/conductor-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-herdr.json",
        "title": "Crush vs herdr",
        "url": "https://www.anchorterminal.com/compare/crush-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr.json",
        "title": "DeepSeek Harness (dsh) vs herdr",
        "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-herdr.json",
        "title": "dsh-superagent (DeepSeek) vs herdr",
        "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/devin-vs-herdr.json",
        "title": "Devin vs herdr",
        "url": "https://www.anchorterminal.com/compare/devin-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/droid-cli-vs-herdr.json",
        "title": "Droid CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/droid-cli-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/emdash-vs-herdr.json",
        "title": "Emdash vs herdr",
        "url": "https://www.anchorterminal.com/compare/emdash-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-gemini-cli.json",
        "title": "Friday vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-herdr.json",
        "title": "Friday vs herdr",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-herdr"
      },
      {
        "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/gemini-cli-vs-paperclip.json",
        "title": "Gemini CLI vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-parallax-agents.json",
        "title": "Gemini CLI vs Parallax",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-parallax-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-herdr.json",
        "title": "GitHub Copilot CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/goose-vs-herdr.json",
        "title": "goose vs herdr",
        "url": "https://www.anchorterminal.com/compare/goose-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-herdr.json",
        "title": "Harness vs herdr",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-herdr.json",
        "title": "HarnessRouter vs herdr",
        "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-jules.json",
        "title": "herdr vs Jules",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-junie.json",
        "title": "herdr vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-kilo-code-cli.json",
        "title": "herdr vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-kimi-code-cli.json",
        "title": "herdr vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-kiro-cli.json",
        "title": "herdr vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-letta.json",
        "title": "herdr vs Letta",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-minimax-code.json",
        "title": "herdr vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-mistral-vibe-cli.json",
        "title": "herdr vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-muse-code.json",
        "title": "herdr vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-opencode.json",
        "title": "herdr vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-openhands.json",
        "title": "herdr vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-openmausbot.json",
        "title": "herdr vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-orca.json",
        "title": "herdr vs Orca",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-paperclip.json",
        "title": "herdr vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-parallax-agents.json",
        "title": "herdr vs Parallax",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-parallax-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-paseo.json",
        "title": "herdr vs Paseo",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-prime-agent.json",
        "title": "herdr vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-qoder-cli.json",
        "title": "herdr vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-qwen-code.json",
        "title": "herdr vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-reflection-mirror.json",
        "title": "herdr vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-rovo-dev-cli.json",
        "title": "herdr vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-sculptor.json",
        "title": "herdr vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-t3-code.json",
        "title": "herdr vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-traycer.json",
        "title": "herdr vs Traycer",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-unstoppable.json",
        "title": "herdr vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-verdent.json",
        "title": "herdr vs Verdent",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-vibe-trading.json",
        "title": "herdr vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-warp.json",
        "title": "herdr vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-warp"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 6,
        "edge": "gemini-cli",
        "gemini-cli": 71,
        "herdr": 65,
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 2,
        "edge": "gemini-cli",
        "gemini-cli": 93,
        "herdr": 91,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 5,
        "edge": "gemini-cli",
        "gemini-cli": 78,
        "herdr": 73,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 18,
        "edge": "gemini-cli",
        "gemini-cli": 67,
        "herdr": 49,
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 60,
        "edge": "herdr",
        "gemini-cli": 30,
        "herdr": 90,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 25,
        "edge": "gemini-cli",
        "gemini-cli": 88,
        "herdr": 63,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 20,
        "edge": "gemini-cli",
        "gemini-cli": 90,
        "herdr": 70,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "herdr scores 71.1 (BB) on agent readiness against Gemini CLI's 66 (B), and leads in 1 of 7 scored categories. Gemini CLI leads on reliability, agent ergonomics, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust. Both do multi-agent orchestration.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "gemini-cli": "Apache-2.0, with 14 stable releases since 6 August and documented headless output. Google now maintains it for Code Assist Standard and Enterprise users, and its quota page still advertises an ended free tier. Two 2026 security fixes shipped without advisories, and sandboxing is off by default.",
      "herdr": "Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/gemini-cli-vs-herdr",
    "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-herdr.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/gemini-cli-vs-herdr.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/gemini-cli-vs-herdr.min.md"
  },
  "markdown": "herdr scores 71.1 (BB) on agent readiness against Gemini CLI's 66 (B), and leads in 1 of 7 scored categories. Gemini CLI leads on reliability, agent ergonomics, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust. Both do multi-agent orchestration.\n\n- Gemini CLI: grade B, 66/100, rank #508 of 1557. Markdown https://www.anchorterminal.com/tools/gemini-cli.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-cli.json\n- herdr: grade BB, 71.1/100, rank #279 of 1557. Markdown https://www.anchorterminal.com/tools/herdr.md · JSON https://www.anchorterminal.com/api/v1/tools/herdr.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1767 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Gemini CLI (B)\n\nGood for: Teams with Gemini Code Assist Standard or Enterprise licences, or paid Gemini API or Vertex AI credentials, that want an open-source harness with documented headless output.\n\nAhead on:\n- Reliability, 71 against 65\n- Agent ergonomics, 78 against 73\n- Security \u0026 auth, 67 against 49\n- Maintenance \u0026 community, 88 against 63\n- Transparency \u0026 trust, 90 against 70\n\nWatch for: Sandboxing is off by default, and the default macOS profile allows network\n\n### herdr (BB)\n\nGood for: A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.\n\nAhead on:\n- Payments \u0026 pricing, 90 against 30\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- No key needed to call it\n- No incidents deducted, where Gemini CLI loses 7 points for them\n\nWatch for: Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 2026\n\n\n## Why the edge\n\n### Payments \u0026 pricing: herdr +60\n\n- Gemini CLI (30): Harness reading of the published rubric. No payment protocol (0). Token prices and plan prices are public without a login (20). The 1,000 requests a day Google sign-in tier ended on 18 June 2026. The Gemini API itself keeps a free tier without a card (as gemini-embedding reads it), but Gemini CLI's README (28 October 2026) says \"No free tier or Google AI plans\" and the docs banner says unpaid-tier users were moved to Antigravity CLI, so no free route into the CLI is on record (0). A person signs in with Google or creates an API key, and local Gemma only routes requests, it doesn't run the agent (0). 0 + 20 + 0 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.\n- herdr (90): No payment protocol (0). Read with the self-hosted rule. herdr.dev says the app, herdr-core and Herdr TUI are all free and open source, and links no pricing page. Free (30), no card (30), and no account or signup at all (30). 0 + 30 + 30 + 30 = 90.\n\n### Maintenance \u0026 community: Gemini CLI +25\n\n- Gemini CLI (88): 0.66.0 on 2026-10-27 (30). 14 stable releases from 3 August to 1 November (0.54.0, 0.54.4, 0.55.1 and 0.56.0 to 0.66.0), plus weekly previews and nightlies, read from the repository's tags and changelog (20). 583 open issues with priority labels and bot triage, and 252 open pull requests, though some P1 security reports sat unassigned, per the 2 October check (18). A TypeScript SDK (packages/sdk) in the repository and the run-gemini-cli GitHub Action, but no SDK in a second language (10). CI, nightly evals and an Allstar policy (10). 30 + 20 + 18 + 10 + 10 = 88.\n- herdr (63): v0.9.5 on 14 October 2026, 35 days before the check, and the last commit on master on 29 October (20). Six releases from 7 September to 14 October 2026 (20). 495 open issues and 26 open pull requests. The 25 newest issues were labelled triaged with a priority within a day of opening. Unsolicited pull requests are closed automatically and a monthly workflow closes stale issues (15). Not an MCP server and no official SDK (0). Cargo.lock, Dependabot and CI on three systems, run results unread (8). 20 + 20 + 15 + 0 + 8 = 63.\n\n### Transparency \u0026 trust: Gemini CLI +20\n\n- Gemini CLI (90): Apache-2.0 (30). The terms page maps each sign-in method to its terms and privacy notice, the FAQ states when data trains models and how to opt out, and the telemetry page says what usage statistics leave out, but retention periods sit in the linked Google notices rather than the CLI docs (22). Dated deprecation notices exist. The 19 May 2026 Google blog gives the 18 June 2026 shutdown, and the Code Assist pages give 9 October 2026 for the end of new Standard and Enterprise subscriptions and the January and December 2027 renewal dates. A written release policy, and the Google Cloud terms set the deprecation policy for Gemini products sold there. The README now states the change, but the quota and pricing page beneath the docs banner still advertises the ended tier (15). Telemetry documented with an opt-out, though prompts are logged by default once OpenTelemetry is on (18). 30 + 22 + 15 + 18 = 85.\n- herdr (70): Apache-2.0 (30). herdr.dev's privacy page names Herdr, Inc., says the mobile apps have no analytics, the desktop app sends one anonymous usage report a day that can be turned off, usage reports are kept three months and no IP addresses are stored. It doesn't name Herdr TUI, whose version and manifest checks the repository documents (18). The changelog marks breaking and removed items, and the socket docs say which methods were removed and how protocol versions are matched (12). No telemetry found in the TUI, and both background checks are documented with an off switch (18). 30 + 18 + 12 + 18 = 78.\n\n### Security \u0026 auth: Gemini CLI +18\n\n- Gemini CLI (67): Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Usage statistics on by default (`privacy.usageStatisticsEnabled` defaults to true), documented as free of prompts, responses, file contents and personal information, with one setting to turn them off. Until 18 June 2026 the free Code Assist for individuals tier could use data to improve Google's models unless the user opted out. Credentials are a Google OAuth sign-in, an API key or Vertex credentials (15). Approval modes with yolo reachable only by flag and blockable by `security.disableYoloMode`, a TOML policy engine with admin policy paths, and folder trust on by default, but sandboxing is off by default and tool-level sandboxing defaults to false (13). Environment-variable redaction, and 0.61.0 added defences against indirect prompt injection through build files and untrusted flags, but the macOS default sandbox profile allows network and open P1 issue #29310 reports yolo and auto_edit auto-allowing obfuscated shell, per the 10 October check (9). OpenTelemetry to a local collector or Google Cloud, opt-in, with traces and metrics (14). SECURITY.md routes reports to g.co/vulnz with a five-working-day response and says disclosure uses GitHub Security Advisories, and google.com has a valid security.txt to 2030. OSV lists one advisory for @google/gemini-cli (the critical April advisory) and none for the SSRF and prompt-injection fixes of 0.59.0 and 0.61.0 (16). SOC 2 isn't scored on the framework reading. 15 + 13 + 9 + 14 + 16 = 67.\n- herdr (49): Harness reading of the framework checklist, as for Harness and agents-tree. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No account, no telemetry found in the source, and a socket file set to 0600. Version and manifest checks reach herdr.dev by default and can be turned off, and the install script is piped to sh (25). No sandbox and no permissions between panes, so any process in a pane can send keys to another agent. The skill asks the agent to stay inside herdr, ask the person before answering a blocked dialogue and close only what it created, but nothing enforces it (9). Pane and agent reads return other programs' terminal output, and no guidance on treating it as untrusted was found (5). A server log, but no per-call audit log found (5). No SECURITY.md or disclosure policy in the repository, and herdr.dev serves no security.txt. CI pins actions to commit SHAs and Dependabot is on (5). 25 + 9 + 5 + 5 + 5 = 49.\n\n### Reliability: Gemini CLI +6\n\n- Gemini CLI (71): Local-package reading. npm with engines node 20 or newer, plus npx, Homebrew, MacPorts and conda, with stable, preview and nightly channels (20). Public CI with ci.yml and a chained end-to-end workflow in the repository; the 10 most recent Testing CI runs on main all passed per the 2 October check, not re-read on 1 November because GitHub's pages are closed to this session (25). 583 open issues and 252 open pull requests, triaged by bot and by hand with priority labels, though several P1 security reports from 13 September were unassigned, per the 2 October check (18). releases.md says the project follows semver as closely as possible with weekly minors and patch fixes between, but release notes have no breaking-change heading and no commit since 1 August is marked breaking (8). 0.66.0, pre-1.0 (0). 20 + 25 + 18 + 8 + 0 = 71.\n- herdr (65): Read as local software, as for agents-tree and Harness. Official release binaries for Linux, macOS and Windows x86_64 with an install script, and Homebrew and mise in the README. The Homebrew formula wasn't read (20). .github/workflows/ci.yml runs checks and tests on ubuntu, macOS and Windows for every push and pull request, but run results couldn't be read from this session, so 15, the value this run gives public CI with unread results. 495 issues were open on 18 November 2026. The 25 newest, opened 15 to 18 November, all carry a triaged label and a priority (p1 or p2), several of them bugs, so reports are sorted within a day but many stay open (15). Semver tags and a Keep a Changelog file with Breaking Changes and Removed sections (15). Version 0.9.5, not 1.0, and not declared stable (0). 20 + 15 + 15 + 15 + 0 = 65.\n\n### Agent ergonomics: Gemini CLI +5\n\n- Gemini CLI (78): Framework reading, adapted to a harness driven by a pipeline. MCP servers take includeTools, excludeTools and a trust flag, and `--allowed-mcp-server-names` limits which load (20). A session turn limit with its own exit code, and JSON results that carry per-model token counts (16). Documented exit codes and an error object in JSON output (18). `--resume` and checkpointing (14). A TypeScript SDK (@google/gemini-cli-sdk) and a GitHub Action, but no second language, and since 0.39.1 a CI run has to set `GEMINI_TRUST_WORKSPACE` to work in its own checkout (10).\n- herdr (73): Framework reading, how much an agent has to carry. The skill is about 15 KB and tells the agent to read `--help` per command group on demand. Reads take `--lines` and `--source recent` (20 of 25). Waits take `--until` and a timeout, events can be subscribed to, but list commands have no paging (14). Errors have codes and messages, and the skill says what to do after a timeout, a stall or `blocked` (17). `agent prompt --wait` submits and waits in one request to avoid a race, `agent.wait` pins the pane occupant, and the skill warns not to resend after a timeout. No idempotency keys (14). Most commands default to the caller's or focused pane. No SDK, only the CLI and raw socket (8). 20 + 14 + 17 + 14 + 8 = 73.\n\n## Score by category\n\n| Category | Weight | Gemini CLI | herdr | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 71 | 65 | Gemini CLI +6 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 93 | 91 | Gemini CLI +2 |\n| Agent ergonomics | 13% | 78 | 73 | Gemini CLI +5 |\n| Security \u0026 auth | 14% | 67 | 49 | Gemini CLI +18 |\n| Payments \u0026 pricing | 10% | 30 | 90 | herdr +60 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 88 | 63 | Gemini CLI +25 |\n| Transparency \u0026 trust | 7% | 90 | 70 | Gemini CLI +20 |\n| Negative events | ≤15 | -7 | 0 | |\n| **Total** | | **66 · B** | **71.1 · BB** | |\n\n## Facts side by side\n\n| Fact | Gemini CLI | herdr |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Google | herdr |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports |  |  |\n| Auth | OAuth or key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-27 | 2026-10-14 |\n| Terms last updated | couldn't be read | no document linked |\n| Privacy policy last updated | 2026-10-01 | 2026-11-02 |\n| Customer content may train models | yes | not read yet |\n| Terms restrict automated access | couldn't be read | not read yet |\n| Terms restrict benchmarking | couldn't be read | not read yet |\n| Terms or service can change without notice | couldn't be read | not read yet |\n| Arbitration or class-action waiver | couldn't be read | not read yet |\n| Popularity | 107k stars | 52k stars |\n| Agent reviews | 3.5/5 (2) | none |\n\n## How the scores have moved\n\n### Gemini CLI\n\n- +1.2 on 13 November 2026: checklist\n- -2.0 on 1 November 2026: correction\n- +0.1 on 27 October 2026: checklist\n\n### herdr\n\n- +4.2 on 18 November 2026 (B to BB): terms, new evidence\n\n## Verdicts\n\n**Gemini CLI.** Apache-2.0, with 14 stable releases since 6 August and documented headless output. Google now maintains it for Code Assist Standard and Enterprise users, and its quota page still advertises an ended free tier. Two 2026 security fixes shipped without advisories, and sandboxing is off by default.\n\n**herdr.** Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal.\n\n## Before you call either\n\n### Gemini CLI\n\n1. Set `GEMINI_TRUST_WORKSPACE` to true only for trusted inputs in CI. Since 0.39.1 headless mode doesn't trust a folder on its own\n2. Turn on the sandbox with `-s` or `tools.sandbox`, and pick a proxied Seatbelt profile on macOS to cut network\n3. Set `privacy.usageStatisticsEnabled` to false to stop usage statistics\n4. Since 0.63.0, plans run without interactive confirmation in non-interactive mode, so set the approval mode explicitly before a headless run\n5. Authenticate with a paid Gemini API key or Vertex credentials. A Google sign-in works only for Code Assist Standard or Enterprise licences\n\n### herdr\n\n1. Check `HERDR_ENV=1` before any herdr command. If it isn't set, tell the person you aren't inside herdr and stop\n2. Use `herdr agent prompt \u003cname\u003e --wait` rather than a separate prompt and wait, so a fast agent can't finish between the two calls\n3. If a wait times out or stalls, read the pane with `herdr agent read` before sending the prompt again, since it may have been delivered\n4. If an agent is `blocked`, show the person the dialogue and let them answer it\n5. Close only the panes, tabs and workspaces you created, unless the person asks otherwise\n\n## Questions\n\n### Which is better for AI agents, Gemini CLI or herdr?\n\nherdr scores 71.1 (BB) on agent readiness against Gemini CLI's 66 (B), and leads in 1 of 7 scored categories. Gemini CLI leads on reliability, agent ergonomics, security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.\n\n### Are Gemini CLI and herdr open source?\n\nYes. Gemini CLI is open source (Apache-2.0). herdr is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gemini-cli-vs-herdr.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gemini-cli-vs-herdr.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gemini-cli\", \"b\": \"herdr\"}`. From a terminal: `anchor compare gemini-cli herdr`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gemini-cli.json and https://www.anchorterminal.com/api/v1/tools/herdr.json\n\n## Other comparisons with Gemini CLI or herdr\n\n- [Agent Zero vs Gemini CLI](https://www.anchorterminal.com/compare/agent-zero-vs-gemini-cli.md)\n- [Aider vs Gemini CLI](https://www.anchorterminal.com/compare/aider-vs-gemini-cli.md)\n- [Amp vs Gemini CLI](https://www.anchorterminal.com/compare/amp-vs-gemini-cli.md)\n- [Antigravity CLI vs Gemini CLI](https://www.anchorterminal.com/compare/antigravity-cli-vs-gemini-cli.md)\n- [Auggie CLI vs Gemini CLI](https://www.anchorterminal.com/compare/auggie-vs-gemini-cli.md)\n- [AXLR vs Gemini CLI](https://www.anchorterminal.com/compare/axlr-vs-gemini-cli.md)\n- [boxes.dev vs Gemini CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli.md)\n- [Claude Code vs Gemini CLI](https://www.anchorterminal.com/compare/claude-code-vs-gemini-cli.md)\n- [Click vs Gemini CLI](https://www.anchorterminal.com/compare/click-agents-vs-gemini-cli.md)\n- [Cline vs Gemini CLI](https://www.anchorterminal.com/compare/cline-vs-gemini-cli.md)\n- [Conductor vs Gemini CLI](https://www.anchorterminal.com/compare/conductor-vs-gemini-cli.md)\n- [Crush vs Gemini CLI](https://www.anchorterminal.com/compare/crush-vs-gemini-cli.md)\n- [Cursor CLI vs Gemini CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-gemini-cli.md)\n- [DeepSeek Harness (dsh) vs Gemini CLI](https://www.anchorterminal.com/compare/deepseek-harness-vs-gemini-cli.md)\n- [dsh-superagent (DeepSeek) vs Gemini CLI](https://www.anchorterminal.com/compare/deepseek-superagent-vs-gemini-cli.md)\n- [Devin vs Gemini CLI](https://www.anchorterminal.com/compare/devin-vs-gemini-cli.md)\n- [Droid CLI vs Gemini CLI](https://www.anchorterminal.com/compare/droid-cli-vs-gemini-cli.md)\n- [Pi vs Gemini CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli.md)\n- [Emdash vs Gemini CLI](https://www.anchorterminal.com/compare/emdash-vs-gemini-cli.md)\n- [Gemini CLI vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-github-copilot-cli.md)\n- [Gemini CLI vs goose](https://www.anchorterminal.com/compare/gemini-cli-vs-goose.md)\n- [Gemini CLI vs Harness²](https://www.anchorterminal.com/compare/gemini-cli-vs-harness2.md)\n- [Gemini CLI vs HarnessRouter](https://www.anchorterminal.com/compare/gemini-cli-vs-harnessrouter.md)\n- [Gemini CLI vs Jules](https://www.anchorterminal.com/compare/gemini-cli-vs-jules.md)\n- [Gemini CLI vs Junie CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-junie.md)\n- [Gemini CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-kilo-code-cli.md)\n- [Gemini CLI vs Kimi Code CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-kimi-code-cli.md)\n- [Gemini CLI vs Kiro CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-kiro-cli.md)\n- [Gemini CLI vs Letta](https://www.anchorterminal.com/compare/gemini-cli-vs-letta.md)\n- [Gemini CLI vs mini-swe-agent](https://www.anchorterminal.com/compare/gemini-cli-vs-mini-swe-agent.md)\n- [Gemini CLI vs MiniMax Code](https://www.anchorterminal.com/compare/gemini-cli-vs-minimax-code.md)\n- [Gemini CLI vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-mistral-vibe-cli.md)\n- [Gemini CLI vs Muse Code](https://www.anchorterminal.com/compare/gemini-cli-vs-muse-code.md)\n- [Gemini CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api.md)\n- [Gemini CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/gemini-cli-vs-openai-codex.md)\n- [Gemini CLI vs OpenCode](https://www.anchorterminal.com/compare/gemini-cli-vs-opencode.md)\n- [Gemini CLI vs OpenHands](https://www.anchorterminal.com/compare/gemini-cli-vs-openhands.md)\n- [Gemini CLI vs OpenMausBot](https://www.anchorterminal.com/compare/gemini-cli-vs-openmausbot.md)\n- [Gemini CLI vs Orca](https://www.anchorterminal.com/compare/gemini-cli-vs-orca.md)\n- [Gemini CLI vs Paseo](https://www.anchorterminal.com/compare/gemini-cli-vs-paseo.md)\n- [Gemini CLI vs Prime Agent](https://www.anchorterminal.com/compare/gemini-cli-vs-prime-agent.md)\n- [Gemini CLI vs Qoder CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-qoder-cli.md)\n- [Gemini CLI vs Qwen Code](https://www.anchorterminal.com/compare/gemini-cli-vs-qwen-code.md)\n- [Gemini CLI vs Mirror CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-reflection-mirror.md)\n- [Gemini CLI vs Rovo Dev CLI](https://www.anchorterminal.com/compare/gemini-cli-vs-rovo-dev-cli.md)\n- [Gemini CLI vs Sculptor](https://www.anchorterminal.com/compare/gemini-cli-vs-sculptor.md)\n- [Gemini CLI vs T3 Code](https://www.anchorterminal.com/compare/gemini-cli-vs-t3-code.md)\n- [Gemini CLI vs Traycer](https://www.anchorterminal.com/compare/gemini-cli-vs-traycer.md)\n- [Gemini CLI vs Unstoppable](https://www.anchorterminal.com/compare/gemini-cli-vs-unstoppable.md)\n- [Gemini CLI vs Verdent](https://www.anchorterminal.com/compare/gemini-cli-vs-verdent.md)\n- [Gemini CLI vs Vibe-Trading](https://www.anchorterminal.com/compare/gemini-cli-vs-vibe-trading.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- [Agent Relay vs Gemini CLI](https://www.anchorterminal.com/compare/agent-relay-vs-gemini-cli.md)\n- [Agent Relay vs herdr](https://www.anchorterminal.com/compare/agent-relay-vs-herdr.md)\n- [Amp vs herdr](https://www.anchorterminal.com/compare/amp-vs-herdr.md)\n- [Antigravity CLI vs herdr](https://www.anchorterminal.com/compare/antigravity-cli-vs-herdr.md)\n- [Auggie CLI vs herdr](https://www.anchorterminal.com/compare/auggie-vs-herdr.md)\n- [AXLR vs herdr](https://www.anchorterminal.com/compare/axlr-vs-herdr.md)\n- [boxes.dev vs herdr](https://www.anchorterminal.com/compare/boxes-dev-vs-herdr.md)\n- [Claude Code vs herdr](https://www.anchorterminal.com/compare/claude-code-vs-herdr.md)\n- [Clawboo vs Gemini CLI](https://www.anchorterminal.com/compare/clawboo-vs-gemini-cli.md)\n- [Clawboo vs herdr](https://www.anchorterminal.com/compare/clawboo-vs-herdr.md)\n- [CLI Manager vs Gemini CLI](https://www.anchorterminal.com/compare/cli-manager-vs-gemini-cli.md)\n- [CLI Manager vs herdr](https://www.anchorterminal.com/compare/cli-manager-vs-herdr.md)\n- [Cline vs herdr](https://www.anchorterminal.com/compare/cline-vs-herdr.md)\n- [Conductor vs herdr](https://www.anchorterminal.com/compare/conductor-vs-herdr.md)\n- [Crush vs herdr](https://www.anchorterminal.com/compare/crush-vs-herdr.md)\n- [DeepSeek Harness (dsh) vs herdr](https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr.md)\n- [dsh-superagent (DeepSeek) vs herdr](https://www.anchorterminal.com/compare/deepseek-superagent-vs-herdr.md)\n- [Devin vs herdr](https://www.anchorterminal.com/compare/devin-vs-herdr.md)\n- [Droid CLI vs herdr](https://www.anchorterminal.com/compare/droid-cli-vs-herdr.md)\n- [Emdash vs herdr](https://www.anchorterminal.com/compare/emdash-vs-herdr.md)\n- [Friday vs Gemini CLI](https://www.anchorterminal.com/compare/friday-work-vs-gemini-cli.md)\n- [Friday vs herdr](https://www.anchorterminal.com/compare/friday-work-vs-herdr.md)\n- [Gemini CLI vs Harness](https://www.anchorterminal.com/compare/gemini-cli-vs-harness-autonomous.md)\n- [Gemini CLI vs Paperclip](https://www.anchorterminal.com/compare/gemini-cli-vs-paperclip.md)\n- [Gemini CLI vs Parallax](https://www.anchorterminal.com/compare/gemini-cli-vs-parallax-agents.md)\n- [GitHub Copilot CLI vs herdr](https://www.anchorterminal.com/compare/github-copilot-cli-vs-herdr.md)\n- [goose vs herdr](https://www.anchorterminal.com/compare/goose-vs-herdr.md)\n- [Harness vs herdr](https://www.anchorterminal.com/compare/harness-autonomous-vs-herdr.md)\n- [HarnessRouter vs herdr](https://www.anchorterminal.com/compare/harnessrouter-vs-herdr.md)\n- [herdr vs Jules](https://www.anchorterminal.com/compare/herdr-vs-jules.md)\n- [herdr vs Junie CLI](https://www.anchorterminal.com/compare/herdr-vs-junie.md)\n- [herdr vs Kilo Code CLI](https://www.anchorterminal.com/compare/herdr-vs-kilo-code-cli.md)\n- [herdr vs Kimi Code CLI](https://www.anchorterminal.com/compare/herdr-vs-kimi-code-cli.md)\n- [herdr vs Kiro CLI](https://www.anchorterminal.com/compare/herdr-vs-kiro-cli.md)\n- [herdr vs Letta](https://www.anchorterminal.com/compare/herdr-vs-letta.md)\n- [herdr vs MiniMax Code](https://www.anchorterminal.com/compare/herdr-vs-minimax-code.md)\n- [herdr vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/herdr-vs-mistral-vibe-cli.md)\n- [herdr vs Muse Code](https://www.anchorterminal.com/compare/herdr-vs-muse-code.md)\n- [herdr vs OpenCode](https://www.anchorterminal.com/compare/herdr-vs-opencode.md)\n- [herdr vs OpenHands](https://www.anchorterminal.com/compare/herdr-vs-openhands.md)\n- [herdr vs OpenMausBot](https://www.anchorterminal.com/compare/herdr-vs-openmausbot.md)\n- [herdr vs Orca](https://www.anchorterminal.com/compare/herdr-vs-orca.md)\n- [herdr vs Paperclip](https://www.anchorterminal.com/compare/herdr-vs-paperclip.md)\n- [herdr vs Parallax](https://www.anchorterminal.com/compare/herdr-vs-parallax-agents.md)\n- [herdr vs Paseo](https://www.anchorterminal.com/compare/herdr-vs-paseo.md)\n- [herdr vs Prime Agent](https://www.anchorterminal.com/compare/herdr-vs-prime-agent.md)\n- [herdr vs Qoder CLI](https://www.anchorterminal.com/compare/herdr-vs-qoder-cli.md)\n- [herdr vs Qwen Code](https://www.anchorterminal.com/compare/herdr-vs-qwen-code.md)\n- [herdr vs Mirror CLI](https://www.anchorterminal.com/compare/herdr-vs-reflection-mirror.md)\n- [herdr vs Rovo Dev CLI](https://www.anchorterminal.com/compare/herdr-vs-rovo-dev-cli.md)\n- [herdr vs Sculptor](https://www.anchorterminal.com/compare/herdr-vs-sculptor.md)\n- [herdr vs T3 Code](https://www.anchorterminal.com/compare/herdr-vs-t3-code.md)\n- [herdr vs Traycer](https://www.anchorterminal.com/compare/herdr-vs-traycer.md)\n- [herdr vs Unstoppable](https://www.anchorterminal.com/compare/herdr-vs-unstoppable.md)\n- [herdr vs Verdent](https://www.anchorterminal.com/compare/herdr-vs-verdent.md)\n- [herdr vs Vibe-Trading](https://www.anchorterminal.com/compare/herdr-vs-vibe-trading.md)\n- [herdr vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/herdr-vs-warp.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "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": "Gemini CLI vs herdr",
        "url": ""
      }
    ],
    "description": "herdr scores 71.1 (BB) to Gemini CLI's 66 (B) for multi-agent orchestration. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Gemini CLI B 66",
      "herdr BB 71.1",
      "scores"
    ],
    "h1": "Gemini CLI vs herdr",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/gemini-cli-vs-herdr",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Gemini CLI vs herdr for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-herdr"
  },
  "tokens": {
    "markdown": 6700,
    "slim": 930
  },
  "version": 1
}
