{ "data": { "a": { "slug": "hermes-agent", "name": "Hermes Agent", "vendor": "Nous Research", "vendorUrl": "https://hermes-agent.nousresearch.com", "kind": "harness", "category": "personal-assistants", "summary": "Open-source personal agent from Nous Research that the owner runs on a computer or server. It answers on messaging apps, keeps memory between sessions, runs scheduled jobs and connects to accounts, models and MCP servers the owner configures.", "url": "https://www.anchorterminal.com/tools/hermes-agent", "markdownUrl": "https://www.anchorterminal.com/tools/hermes-agent.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hermes-agent.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hermes-agent.json", "repo": "https://github.com/NousResearch/hermes-agent", "license": "MIT", "transports": [], "packages": [ { "registry": "oci", "name": "nousresearch/hermes-agent" } ], "auth": "none", "authNotes": "No account of its own. Model and channel keys go in `~/.hermes/.env` or come from Bitwarden, 1Password or a command helper at start-up. Google Workspace, MCP servers and Nous Portal sign in by OAuth, with tokens stored under `~/.hermes/`. The optional API server takes a bearer key set in `API_SERVER_KEY`.", "pricing": "free", "pricingNotes": "Free under the MIT licence. The owner pays the model provider chosen, or nothing with a local model. Nous Portal plans ($0, $20, $100 and $200 a month in credits) and Hermes Cloud hosting ($0.51 a day running on the Standard size, plus inference) are optional and sold separately.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on Hermes Agent's own interfaces. An optional skill lets the agent pay other services over MPP, which is a client and not a way to pay for Hermes (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 253000, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://hermes-agent.nousresearch.com/docs/", "llmsTxt": "https://hermes-agent.nousresearch.com/llms.txt", "capabilities": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "tags": [ "open-source", "self-hosted", "local", "free", "no-card", "python", "docker", "llms-txt", "pre-1.0" ], "lastRelease": "2026-10-11", "graded": true, "anchor": { "graded": true, "score": 67.9, "grade": "B", "agentReady": false, "rank": 244, "ranked": true, "rankOf": 986, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 84, "payments": 60, "reliability": 57, "schema": 80, "security": 75, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": -3, "negativeNotes": [ "2026-10-08. The v0.21.6 release notes list six security fixes, among them a native sign-in flaw that could send login codes to a non-loopback redirect and a quoted display name in the `From` header that affected the email gateway's sender check. SECURITY.md counts unauthorised access to an external surface as in scope, yet the repository shows no published advisory, so owners on older versions have no advisory to act on. Fixed and described in the notes, -3. https://github.com/NousResearch/hermes-agent/releases/tag/v0.21.6; https://github.com/NousResearch/hermes-agent/security/advisories" ], "verdict": "Card payments always ask first and are refused in unattended sessions, and the messaging gateway denies every sender until an allowlist is set. Shell commands run on the host by default with a model judging risk, and sending mail through the Google Workspace skill is held back only by an instruction to the model.", "bestFor": "A technical owner who wants one always-on agent across chat apps with memory and scheduled jobs, on their own machine or a small server, with any model.", "strengths": [ "Every saved-card fill asks for approval, and cron, webhook and API sessions are refused because nobody can confirm", "The messaging gateway denies all senders until an allowlist or a pairing code approved on the CLI is in place", "The docs say no telemetry, usage data or analytics is collected, and conversations, memory and skills stay in `~/.hermes/`", "SECURITY.md states that in-process checks are not a boundary and names OS-level isolation as the only one", "Ten releases between 19 August and 11 October 2026, the latest v0.21.7 on 11 October" ], "weaknesses": [ "The default terminal backend runs commands on the host, and the default `smart` mode lets an auxiliary model approve commands it rates low-risk", "The Google Workspace skill requests full Gmail, Calendar and Drive scopes, and its confirm-before-sending rule is an instruction in SKILL.md, not enforced in code", "Memory writes are saved without approval by default (`memory.write_approval: false`), including from a background review after each turn", "Release v0.21.6 of 8 October 2026 lists six security fixes and the repository has no published security advisory", "15,102 open issues and more than 5,000 open pull requests on 12 October 2026", "The Nous Portal terms grant Nous a licence to train models on customer data when the Portal is the model provider" ], "agentNotes": [ "Set `approvals.mode: manual` before giving it real accounts. The default `smart` lets an auxiliary model approve commands", "Run the gateway with `terminal.backend: docker` or the project's Docker image when it reads mail, web pages or group chats", "Set `memory.write_approval: true` and `skills.write_approval: true` to review what it saves about the owner", "Leave `approvals.cron_mode` and `approvals.unattended_mode` at `deny` for scheduled and webhook runs", "Set `TELEGRAM_ALLOWED_USERS` or the matching allowlist per channel. Never set `GATEWAY_ALLOW_ALL_USERS=true`" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67.9 } ], "editorialScores": { "ergonomics": 80, "maintenance": 84, "payments": 60, "reliability": 57, "schema": 80, "security": 75, "transparency": 73 }, "provenanceScore": 53 }, "connect": { "install": "curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash # then: hermes setup", "headless": { "command": "hermes chat -q \"$TASK\" --format stream-json --max-turns 30" } }, "letme": { "capability": "https://letme.dev/assistant.proactive", "tool": "https://letme.dev/hermes-agent" }, "area": "frameworks", "provenance": { "legalEntity": "Nous Research, Inc.", "domain": "nousresearch.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/NousResearch/hermes-agent/releases", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The site footer reads Nous Research, Inc., and the Nous Portal terms name it as a Delaware corporation.", "No terms or privacy link is given. The Nous Portal terms and privacy policy (both dated 28 September 2026) govern the optional Portal and Hermes Cloud services, not the software the owner runs under the MIT licence, so the licence stands in.", "hermes-agent.nousresearch.com/.well-known/security.txt answered 404. SECURITY.md in the repository gives security@nousresearch.com and GitHub private reporting.", "No status page applies to software the owner runs. None was looked for on the Portal.", "The domain registration date was not looked up." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hermes-agent.json" }, "answer": "Hermes Agent scores 67.9 (B) on agent readiness against Poke's 37.6 (F), and leads in every scored category.", "b": { "slug": "poke", "name": "Poke", "vendor": "The Interaction Company of California Inc.", "vendorUrl": "https://poke.com", "kind": "platform", "category": "personal-assistants", "summary": "Hosted personal assistant from The Interaction Company of California, reached by text on Apple Messages, WhatsApp, Telegram and RCS. It works across the owner's Gmail or Outlook mail, calendar, contacts and connected apps.", "url": "https://www.anchorterminal.com/tools/poke", "markdownUrl": "https://www.anchorterminal.com/tools/poke.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/poke.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/poke.json", "license": "Proprietary service under Poke's Terms of Service. The `poke` npm package (CLI and Node.js SDK) declares MIT", "transports": [ "http" ], "packages": [ { "registry": "npm", "name": "poke" } ], "auth": "api-key", "authNotes": "A person signs up at poke.com and connects a Google or Microsoft account. The Poke API takes `Authorization: Bearer \u003ckey\u003e` with a V2 key created in Kitchen under API Keys. Keys are named, shown once, revocable one at a time and have no scopes. Older `pk_` keys work only on the deprecated endpoint. The CLI signs in with a browser device code and stores credentials in `~/.config/poke/credentials.json`. Third-party MCP servers are connected with an API key or OAuth (https://poke.com/docs/api; https://poke.com/docs/mcp-servers; https://poke.com/docs/creating-recipes).", "pricing": "freemium", "pricingNotes": "Free at $0 with no card. Pro is $19 a month and Ultra $199 a month on monthly billing. Free and Pro have a refilling usage allowance, with no figures published, and Poke continues in a lighter mode past it. Ultra includes a monthly credit pool (1 credit is $1 of usage), with top-ups and optional auto-reload. Poke Human is included with Ultra, with real-world expenses charged at cost. Model usage is not billed separately (https://poke.com/pricing; https://poke.com/docs/usage-and-resets; https://poke.com/faq, checked 2026-10-12).", "priceSummary": "$19 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, llms.txt or the pricing page (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://poke.com/docs", "llmsTxt": "https://poke.com/llms.txt", "capabilities": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "agent.mcp-client" ], "tags": [ "hosted", "closed-source", "messaging", "imessage", "whatsapp", "telegram", "gmail", "outlook", "mcp-client", "api-key", "free-tier", "status-page", "llms-txt", "trains-on-data-by-default" ], "lastRelease": "2026-06-25", "graded": true, "anchor": { "graded": true, "score": 37.6, "grade": "F", "agentReady": false, "rank": 955, "ranked": true, "rankOf": 986, "categoryRank": 15, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 30, "maintenance": 31, "payments": 30, "reliability": 51, "schema": 42, "security": 24, "transparency": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": 0, "verdict": "Hosted assistant that answers in Apple Messages, WhatsApp, Telegram and RCS and acts in Gmail, Outlook, calendars and MCP servers. Plan prices and a status page are public. No approval settings, credential storage, model providers or retention periods are documented, and customer content trains models unless Maximum Privacy is selected.", "bestFor": "One person who wants an assistant in their text messages that reads and drafts mail, manages a calendar and reaches other apps through MCP.", "strengths": [ "Answers on Apple Messages, WhatsApp, Telegram and RCS, with the channel chosen in settings, per the docs welcome page and FAQ", "Free plan with no card, Pro at $19 a month and Ultra at $199 a month, all published without a sign-in", "Connects any remote MCP server by URL, with API key or OAuth, and OAuth servers with Dynamic Client Registration need no setup", "status.poke.com lists App, Email, Integrations, three messaging channels and API, with two incidents from July to 12 October 2026", "Named API keys are created in Kitchen, shown once and revoked one at a time" ], "weaknesses": [ "No documented setting for which actions need approval before Poke sends, deletes or spends. Release notes mention email draft approval only in passing", "Customer content, including email contents, may train AI models unless the user selects Maximum Privacy, per the privacy notice of 11 September 2026", "Model providers, sub-processors, hosting locations and where account tokens are stored are not named in the pages read", "An API key message is processed with full access to email, calendar and integrations. Keys have no scopes", "No security.txt, disclosure policy, bug bounty or certification was found on poke.com", "The terms forbid automated access for scraping and use for benchmarking or competitive analysis. This matters before any probe is run" ], "agentNotes": [ "POST JSON to `https://poke.com/api/v1/inbound/api-message` with a Bearer key from Kitchen. Legacy `pk_` keys work only on the deprecated `/api/v1/inbound-sms/webhook`", "Expect only `{\"success\": true}` back. Poke's answer goes to the owner's message thread, not to the caller", "Do not retry a POST blindly. No idempotency key is documented, and a repeated message may make Poke act twice", "Treat an API key as full access to the owner's mail, calendar and integrations. Create one key per automation and revoke it when done", "Avoid the prefilled integration link with `apiKey` in the query string for real secrets. Enter the key in the form or use `npx poke@latest mcp add -k`" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 37.6 } ], "editorialScores": { "ergonomics": 30, "maintenance": 31, "payments": 30, "reliability": 51, "schema": 42, "security": 24, "transparency": 34 }, "provenanceScore": 81 }, "connect": { "install": "npx poke@latest login", "http": "curl 'https://poke.com/api/v1/inbound/api-message' \\\n -H \"Authorization: Bearer YOUR_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"message\": \"test\"}'" }, "letme": { "capability": "https://letme.dev/assistant.proactive", "tool": "https://letme.dev/poke" }, "area": "frameworks", "unitPrices": [ { "item": "Pro", "unit": "month", "usd": 19, "note": "billed monthly, refilling usage allowance with no published figure" }, { "item": "Ultra", "unit": "month", "usd": 199, "note": "billed monthly, includes a monthly credit pool and Poke Human" }, { "item": "Ultra top-up credit", "unit": "credit", "usd": 1, "note": "1 credit is $1 of usage" } ], "provenance": { "legalEntity": "The Interaction Company of California Inc.", "domain": "poke.com", "domainRegistered": "1997-03-26", "endpointOnVendorDomain": true, "terms": "https://poke.com/terms", "privacy": "https://poke.com/privacy", "statusPage": "https://status.poke.com", "changelog": "https://poke.com/docs/release-notes", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The privacy notice (last updated 11 September 2026) names The Interaction Company of California Inc. and gives 169 Waverley St Apt B, Palo Alto, CA 94301 as the controller's address. The terms (last modified 17 March 2026) name The Interaction Company of California d/b/a Poke.", "Cognition announced on 23 July 2026 that The Interaction Company of California was joining it. The terms and privacy notice read on 12 October 2026 do not name Cognition.", "poke.com/.well-known/security.txt answered 404. poke.com/robots.txt also answered 404, so the host publishes no crawl rules.", "RDAP for poke.com gives a registration date of 1997-03-26 and NameCheap, Inc. as registrar.", "The API answers at poke.com/api/v1, on the vendor's domain." ], "score": 81 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/poke.json", "live": { "slug": "poke", "vendorStatus": { "page": "https://status.poke.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-12T18:57:01.261625139Z" }, "updatedAt": "2026-10-12T18:57:01.261625139Z" } }, "facts": [ { "a": "Agent harness", "b": "Platform", "name": "Kind" }, { "a": "Nous Research", "b": "The Interaction Company of California Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary service under Poke's Terms of Service. The `poke` npm package (CLI and Node.js SDK) declares MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-11", "b": "2026-06-25", "name": "Last release" }, { "a": "no document linked", "b": "2026-03-17", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-09-11", "name": "Privacy policy last updated" }, { "a": "", "b": "yes", "name": "Customer content may train models" }, { "a": "", "b": "yes", "name": "Terms restrict automated access" }, { "a": "", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "253k stars", "b": "none", "name": "Popularity" } ], "faq": [ { "answer": "Hermes Agent scores 67.9 (B) on agent readiness against Poke's 37.6 (F), and leads in every scored category.", "question": "Which is better for AI agents, Hermes Agent or Poke?" }, { "answer": "Hermes Agent is open source (MIT). No open-source release is listed for Poke.", "question": "Are Hermes Agent and Poke open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 57 against 51", "Schema \u0026 documentation, 80 against 42", "Agent ergonomics, 80 against 30", "Security \u0026 auth, 75 against 24", "Payments \u0026 pricing, 60 against 30", "Maintenance \u0026 community, 84 against 31", "Transparency \u0026 trust, 63 against 58" ], "also": [ "No key needed to call it", "Free to start without a card", "Open source" ], "goodFor": "A technical owner who wants one always-on agent across chat apps with memory and scheduled jobs, on their own machine or a small server, with any model.", "slug": "hermes-agent", "watchFor": "The default terminal backend runs commands on the host, and the default `smart` mode lets an auxiliary model approve commands it rates low-risk" }, { "aheadOn": null, "also": [ "No incidents deducted, where Hermes Agent loses 3 points for them" ], "goodFor": "One person who wants an assistant in their text messages that reads and drafts mail, manages a calendar and reaches other apps through MCP.", "slug": "poke", "watchFor": "No documented setting for which actions need approval before Poke sends, deletes or spends. Release notes mention email draft approval only in passing" } ], "job": { "capability": "assistant.proactive", "name": "Assistant proactive" }, "others": [ { "json": "https://www.anchorterminal.com/compare/astrbot-vs-hermes-agent.json", "title": "AstrBot vs Hermes Agent", "url": "https://www.anchorterminal.com/compare/astrbot-vs-hermes-agent" }, { "json": "https://www.anchorterminal.com/compare/astrbot-vs-poke.json", "title": "AstrBot vs Poke", "url": "https://www.anchorterminal.com/compare/astrbot-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-hermes-agent.json", "title": "CowAgent vs Hermes Agent", "url": "https://www.anchorterminal.com/compare/cowagent-vs-hermes-agent" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-poke.json", "title": "CowAgent vs Poke", "url": "https://www.anchorterminal.com/compare/cowagent-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/gaia-vs-hermes-agent.json", "title": "GAIA vs Hermes Agent", "url": "https://www.anchorterminal.com/compare/gaia-vs-hermes-agent" }, { "json": "https://www.anchorterminal.com/compare/gaia-vs-poke.json", "title": "GAIA vs Poke", "url": "https://www.anchorterminal.com/compare/gaia-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-hermes-agent.json", "title": "Gemini Spark vs Hermes Agent", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-hermes-agent" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-poke.json", "title": "Gemini Spark vs Poke", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/grok-bot-vs-hermes-agent.json", "title": "Grok Bot vs Hermes Agent", "url": "https://www.anchorterminal.com/compare/grok-bot-vs-hermes-agent" }, { "json": "https://www.anchorterminal.com/compare/grok-bot-vs-poke.json", "title": "Grok Bot vs Poke", "url": "https://www.anchorterminal.com/compare/grok-bot-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/haven-vs-hermes-agent.json", "title": "Haven vs Hermes Agent", "url": "https://www.anchorterminal.com/compare/haven-vs-hermes-agent" }, { "json": "https://www.anchorterminal.com/compare/haven-vs-poke.json", "title": "Haven vs Poke", "url": "https://www.anchorterminal.com/compare/haven-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-instinct.json", "title": "Hermes Agent vs Instinct", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-instinct" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-ironclaw.json", "title": "Hermes Agent vs IronClaw", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-ironclaw" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-leon.json", "title": "Hermes Agent vs Leon", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-leon" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-lindy.json", "title": "Hermes Agent vs Lindy", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-lindy" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-nanobot.json", "title": "Hermes Agent vs nanobot", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-nanobot" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-nanoclaw.json", "title": "Hermes Agent vs NanoClaw", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-nanoclaw" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-openai-dots.json", "title": "Hermes Agent vs Dots", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-openai-dots" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-openclaw.json", "title": "Hermes Agent vs OpenClaw", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-openclaw" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-picoclaw.json", "title": "Hermes Agent vs PicoClaw", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-picoclaw" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.json", "title": "Hermes Agent vs QwenPaw", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-zeroclaw.json", "title": "Hermes Agent vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-zo-computer.json", "title": "Hermes Agent vs Zo Computer", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-zo-computer" }, { "json": "https://www.anchorterminal.com/compare/instinct-vs-poke.json", "title": "Instinct vs Poke", "url": "https://www.anchorterminal.com/compare/instinct-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-poke.json", "title": "IronClaw vs Poke", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/leon-vs-poke.json", "title": "Leon vs Poke", "url": "https://www.anchorterminal.com/compare/leon-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/lindy-vs-poke.json", "title": "Lindy vs Poke", "url": "https://www.anchorterminal.com/compare/lindy-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/nanobot-vs-poke.json", "title": "nanobot vs Poke", "url": "https://www.anchorterminal.com/compare/nanobot-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/nanoclaw-vs-poke.json", "title": "NanoClaw vs Poke", "url": "https://www.anchorterminal.com/compare/nanoclaw-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/openai-dots-vs-poke.json", "title": "Dots vs Poke", "url": "https://www.anchorterminal.com/compare/openai-dots-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/openclaw-vs-poke.json", "title": "OpenClaw vs Poke", "url": "https://www.anchorterminal.com/compare/openclaw-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/picoclaw-vs-poke.json", "title": "PicoClaw vs Poke", "url": "https://www.anchorterminal.com/compare/picoclaw-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/poke-vs-qwenpaw.json", "title": "Poke vs QwenPaw", "url": "https://www.anchorterminal.com/compare/poke-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/poke-vs-zeroclaw.json", "title": "Poke vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/poke-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/poke-vs-zo-computer.json", "title": "Poke vs Zo Computer", "url": "https://www.anchorterminal.com/compare/poke-vs-zo-computer" } ], "scores": [ { "by": 6, "edge": "hermes-agent", "hermes-agent": 57, "key": "reliability", "name": "Reliability", "poke": 51, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 38, "edge": "hermes-agent", "hermes-agent": 80, "key": "schema", "name": "Schema \u0026 documentation", "poke": 42, "weight": 13 }, { "by": 50, "edge": "hermes-agent", "hermes-agent": 80, "key": "ergonomics", "name": "Agent ergonomics", "poke": 30, "weight": 13 }, { "by": 51, "edge": "hermes-agent", "hermes-agent": 75, "key": "security", "name": "Security \u0026 auth", "poke": 24, "weight": 14 }, { "by": 30, "edge": "hermes-agent", "hermes-agent": 60, "key": "payments", "name": "Payments \u0026 pricing", "poke": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 53, "edge": "hermes-agent", "hermes-agent": 84, "key": "maintenance", "name": "Maintenance \u0026 community", "poke": 31, "weight": 7 }, { "by": 5, "edge": "hermes-agent", "hermes-agent": 63, "key": "transparency", "name": "Transparency \u0026 trust", "poke": 58, "weight": 7 } ], "summary": "Hermes Agent scores 67.9 (B) on agent readiness against Poke's 37.6 (F), and leads in every scored category. Both do assistant proactive.", "verdicts": { "hermes-agent": "Card payments always ask first and are refused in unattended sessions, and the messaging gateway denies every sender until an allowlist is set. Shell commands run on the host by default with a model judging risk, and sending mail through the Google Workspace skill is held back only by an instruction to the model.", "poke": "Hosted assistant that answers in Apple Messages, WhatsApp, Telegram and RCS and acts in Gmail, Outlook, calendars and MCP servers. Plan prices and a status page are public. No approval settings, credential storage, model providers or retention periods are documented, and customer content trains models unless Maximum Privacy is selected." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/hermes-agent-vs-poke", "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-poke.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/hermes-agent-vs-poke.md", "slim": "https://www.anchorterminal.com/compare/hermes-agent-vs-poke.min.md" }, "markdown": "Hermes Agent scores 67.9 (B) on agent readiness against Poke's 37.6 (F), and leads in every scored category. Both do assistant proactive.\n\n- Hermes Agent: grade B, 67.9/100, rank #244 of 986. Markdown https://www.anchorterminal.com/tools/hermes-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/hermes-agent.json\n- Poke: grade F, 37.6/100, rank #955 of 986. Markdown https://www.anchorterminal.com/tools/poke.md · JSON https://www.anchorterminal.com/api/v1/tools/poke.json\n- Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 190 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md\n\n## Which one, for what\n\n### Hermes Agent (B)\n\nGood for: A technical owner who wants one always-on agent across chat apps with memory and scheduled jobs, on their own machine or a small server, with any model.\n\nAhead on:\n- Reliability, 57 against 51\n- Schema \u0026 documentation, 80 against 42\n- Agent ergonomics, 80 against 30\n- Security \u0026 auth, 75 against 24\n- Payments \u0026 pricing, 60 against 30\n- Maintenance \u0026 community, 84 against 31\n- Transparency \u0026 trust, 63 against 58\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\n- Open source\n\nWatch for: The default terminal backend runs commands on the host, and the default `smart` mode lets an auxiliary model approve commands it rates low-risk\n\n### Poke (F)\n\nGood for: One person who wants an assistant in their text messages that reads and drafts mail, manages a calendar and reaches other apps through MCP.\n\nAlso in its favour:\n- No incidents deducted, where Hermes Agent loses 3 points for them\n\nWatch for: No documented setting for which actions need approval before Poke sends, deletes or spends. Release notes mention email draft approval only in passing\n\n\n## Score by category\n\n| Category | Weight | Hermes Agent | Poke | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 57 | 51 | Hermes Agent +6 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 42 | Hermes Agent +38 |\n| Agent ergonomics | 13% (16.2 this run) | 80 | 30 | Hermes Agent +50 |\n| Security \u0026 auth | 14% (17.5 this run) | 75 | 24 | Hermes Agent +51 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 30 | Hermes Agent +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 84 | 31 | Hermes Agent +53 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 63 | 58 | Hermes Agent +5 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **67.9 · B** | **37.6 · F** | |\n\n## Facts side by side\n\n| Fact | Hermes Agent | Poke |\n| --- | --- | --- |\n| Kind | Agent harness | Platform |\n| Vendor | Nous Research | The Interaction Company of California Inc. |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Proprietary service under Poke's Terms of Service. The `poke` npm package (CLI and Node.js SDK) declares MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-11 | 2026-06-25 |\n| Terms last updated | no document linked | 2026-03-17 |\n| Privacy policy last updated | no document linked | 2026-09-11 |\n| Customer content may train models | | yes |\n| Terms restrict automated access | | yes |\n| Terms restrict benchmarking | | yes |\n| Terms or service can change without notice | | yes |\n| Arbitration or class-action waiver | | yes |\n| Popularity | 253k stars | none |\n\n## Verdicts\n\n**Hermes Agent.** Card payments always ask first and are refused in unattended sessions, and the messaging gateway denies every sender until an allowlist is set. Shell commands run on the host by default with a model judging risk, and sending mail through the Google Workspace skill is held back only by an instruction to the model.\n\n**Poke.** Hosted assistant that answers in Apple Messages, WhatsApp, Telegram and RCS and acts in Gmail, Outlook, calendars and MCP servers. Plan prices and a status page are public. No approval settings, credential storage, model providers or retention periods are documented, and customer content trains models unless Maximum Privacy is selected.\n\n## Before you call either\n\n### Hermes Agent\n\n1. Set `approvals.mode: manual` before giving it real accounts. The default `smart` lets an auxiliary model approve commands\n2. Run the gateway with `terminal.backend: docker` or the project's Docker image when it reads mail, web pages or group chats\n3. Set `memory.write_approval: true` and `skills.write_approval: true` to review what it saves about the owner\n4. Leave `approvals.cron_mode` and `approvals.unattended_mode` at `deny` for scheduled and webhook runs\n5. Set `TELEGRAM_ALLOWED_USERS` or the matching allowlist per channel. Never set `GATEWAY_ALLOW_ALL_USERS=true`\n\n### Poke\n\n1. POST JSON to `https://poke.com/api/v1/inbound/api-message` with a Bearer key from Kitchen. Legacy `pk_` keys work only on the deprecated `/api/v1/inbound-sms/webhook`\n2. Expect only `{\"success\": true}` back. Poke's answer goes to the owner's message thread, not to the caller\n3. Do not retry a POST blindly. No idempotency key is documented, and a repeated message may make Poke act twice\n4. Treat an API key as full access to the owner's mail, calendar and integrations. Create one key per automation and revoke it when done\n5. Avoid the prefilled integration link with `apiKey` in the query string for real secrets. Enter the key in the form or use `npx poke@latest mcp add -k`\n\n## Questions\n\n### Which is better for AI agents, Hermes Agent or Poke?\n\nHermes Agent scores 67.9 (B) on agent readiness against Poke's 37.6 (F), and leads in every scored category.\n\n### Are Hermes Agent and Poke open source?\n\nHermes Agent is open source (MIT). No open-source release is listed for Poke.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/hermes-agent-vs-poke.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hermes-agent-vs-poke.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"hermes-agent\", \"b\": \"poke\"}`. From a terminal: `anchor compare hermes-agent poke`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hermes-agent.json and https://www.anchorterminal.com/api/v1/tools/poke.json\n\n## Other comparisons with Hermes Agent or Poke\n\n- [AstrBot vs Hermes Agent](https://www.anchorterminal.com/compare/astrbot-vs-hermes-agent.md)\n- [AstrBot vs Poke](https://www.anchorterminal.com/compare/astrbot-vs-poke.md)\n- [CowAgent vs Hermes Agent](https://www.anchorterminal.com/compare/cowagent-vs-hermes-agent.md)\n- [CowAgent vs Poke](https://www.anchorterminal.com/compare/cowagent-vs-poke.md)\n- [GAIA vs Hermes Agent](https://www.anchorterminal.com/compare/gaia-vs-hermes-agent.md)\n- [GAIA vs Poke](https://www.anchorterminal.com/compare/gaia-vs-poke.md)\n- [Gemini Spark vs Hermes Agent](https://www.anchorterminal.com/compare/gemini-spark-vs-hermes-agent.md)\n- [Gemini Spark vs Poke](https://www.anchorterminal.com/compare/gemini-spark-vs-poke.md)\n- [Grok Bot vs Hermes Agent](https://www.anchorterminal.com/compare/grok-bot-vs-hermes-agent.md)\n- [Grok Bot vs Poke](https://www.anchorterminal.com/compare/grok-bot-vs-poke.md)\n- [Haven vs Hermes Agent](https://www.anchorterminal.com/compare/haven-vs-hermes-agent.md)\n- [Haven vs Poke](https://www.anchorterminal.com/compare/haven-vs-poke.md)\n- [Hermes Agent vs Instinct](https://www.anchorterminal.com/compare/hermes-agent-vs-instinct.md)\n- [Hermes Agent vs IronClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-ironclaw.md)\n- [Hermes Agent vs Leon](https://www.anchorterminal.com/compare/hermes-agent-vs-leon.md)\n- [Hermes Agent vs Lindy](https://www.anchorterminal.com/compare/hermes-agent-vs-lindy.md)\n- [Hermes Agent vs nanobot](https://www.anchorterminal.com/compare/hermes-agent-vs-nanobot.md)\n- [Hermes Agent vs NanoClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-nanoclaw.md)\n- [Hermes Agent vs Dots](https://www.anchorterminal.com/compare/hermes-agent-vs-openai-dots.md)\n- [Hermes Agent vs OpenClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-openclaw.md)\n- [Hermes Agent vs PicoClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-picoclaw.md)\n- [Hermes Agent vs QwenPaw](https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.md)\n- [Hermes Agent vs ZeroClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-zeroclaw.md)\n- [Hermes Agent vs Zo Computer](https://www.anchorterminal.com/compare/hermes-agent-vs-zo-computer.md)\n- [Instinct vs Poke](https://www.anchorterminal.com/compare/instinct-vs-poke.md)\n- [IronClaw vs Poke](https://www.anchorterminal.com/compare/ironclaw-vs-poke.md)\n- [Leon vs Poke](https://www.anchorterminal.com/compare/leon-vs-poke.md)\n- [Lindy vs Poke](https://www.anchorterminal.com/compare/lindy-vs-poke.md)\n- [nanobot vs Poke](https://www.anchorterminal.com/compare/nanobot-vs-poke.md)\n- [NanoClaw vs Poke](https://www.anchorterminal.com/compare/nanoclaw-vs-poke.md)\n- [Dots vs Poke](https://www.anchorterminal.com/compare/openai-dots-vs-poke.md)\n- [OpenClaw vs Poke](https://www.anchorterminal.com/compare/openclaw-vs-poke.md)\n- [PicoClaw vs Poke](https://www.anchorterminal.com/compare/picoclaw-vs-poke.md)\n- [Poke vs QwenPaw](https://www.anchorterminal.com/compare/poke-vs-qwenpaw.md)\n- [Poke vs ZeroClaw](https://www.anchorterminal.com/compare/poke-vs-zeroclaw.md)\n- [Poke vs Zo Computer](https://www.anchorterminal.com/compare/poke-vs-zo-computer.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-12", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Hermes Agent vs Poke", "url": "" } ], "description": "Hermes Agent scores 67.9 (B) to Poke's 37.6 (F) for assistant proactive. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Hermes Agent B 67.9", "Poke F 37.6", "scores" ], "h1": "Hermes Agent vs Poke", "image": "https://www.anchorterminal.com/assets/og/compare-hermes-agent-vs-poke.png", "path": "/compare/hermes-agent-vs-poke", "published": "2026-10-01", "section": "tools", "title": "Hermes Agent vs Poke for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-poke" }, "tokens": { "markdown": 2600, "slim": 680 }, "version": 1 }