{ "data": { "similar": [ { "grade": "BB", "json": "https://www.anchorterminal.com/tools/zeroclaw.json", "name": "ZeroClaw", "score": 70.2, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.memory", "assistant.self-hosted", "assistant.accounts", "agent.mcp-client" ], "slug": "zeroclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/nanoclaw.json", "name": "NanoClaw", "score": 68.3, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.memory", "assistant.self-hosted", "agent.mcp-client", "assistant.accounts" ], "slug": "nanoclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/openclaw.json", "name": "OpenClaw", "score": 67.1, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "openclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/ironclaw.json", "name": "IronClaw", "score": 66.7, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "ironclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/nanobot.json", "name": "nanobot", "score": 62.4, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.memory", "assistant.self-hosted", "assistant.accounts", "agent.mcp-client" ], "slug": "nanobot" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/qwenpaw.json", "name": "QwenPaw", "score": 62.2, "shared": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "qwenpaw" } ], "tool": { "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" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 57, "points": 11.4, "reason": "Read with the local-software lines, as the Goose and Khoj dossiers are. An install script, desktop installers for macOS and Windows, a Docker image (`nousresearch/hermes-agent`) and a signed Termux repository, with Python 3.14 stated as the only supported version, but the docs say no supported wheel or source distribution is published (18 of 20). `ci.yaml` runs on every pull request and push to main and the repository holds about 5,700 test files, and a stable release must pass the whole suite. The Actions page we loaded showed only pull-request runs, so the state of main is unconfirmed (18 of 25). 15,102 open issues and more than 5,000 open pull requests on 12 October 2026. New reports get priority and component labels the same day, but the first page held P1 bugs on session state and context compression with no comment (10 of 25). The project moved from date versions to SemVer at v0.21.6 on 8 October 2026, and the v0.21.6 notes, which cover about 2,106 pull requests, have no breaking-change section (6 of 15). Version 0.21.7, before 1.0, on a channel the project calls stable (5 of 15)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 80, "points": 13, "reason": "Harness reading of the framework line, as for Goose. Reference pages for configuration, environment variables, CLI commands and MCP config, and the API server documents its routes, but no OpenAPI file was found (17 of 25). `llms.txt`, a per-section docs index and a full-text file are served (10). The security page says what each guard catches and misses, and pages such as heartbeat against cron say when to use which (16 of 20). Config keys are listed with defaults and allowed values, such as the three approval modes (12 of 15). An FAQ explains error messages and their fixes, and each feature page carries examples (13 of 15). Dated release notes on GitHub with no changelog file, and the version scheme changed in October 2026 (12 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 80, "points": 13, "reason": "Harness reading, scored on what a person or pipeline driving it must supply. A tool search index, toolsets and per-server MCP include and exclude filters keep definitions out of context (22 of 25). `--max-turns` with a default of 500, automatic context compression and a usage report file, though 500 turns is high for an unattended run (15 of 20). `hermes chat -q` with `--format stream-json`, and the FAQ maps errors to fixes (16 of 20). The runs API takes an `Idempotency-Key`, sessions resume, and cron tracks failure streaks and delivery failures apart from run failures (17 of 20). One install command and a setup wizard, but a model provider must be configured first, and the Python library has no published package (10 of 15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 75, "points": 13.13, "reason": "Harness reading used for Goose. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. The FAQ says no telemetry, usage data or analytics is collected and our search of the source found no analytics client in the core, with passive update checks the owner can disable (28). Three approval modes, a fixed blocklist, owner deny rules, `deny` defaults for cron, one-shot and webhook sessions, card fills that always ask, and a gateway that denies all senders by default. Against that, the default backend runs on the host, the default `smart` mode lets an auxiliary model approve commands, container backends skip the check, memory writes are ungated by default, and sending mail through the Google Workspace skill is held back only by an instruction to the model (14). Context files and cron prompts are scanned for injection patterns, URL tools block private addresses, and SECURITY.md says plainly that these are heuristics, that prompt injection alone is out of scope and that untrusted input calls for whole-process sandboxing, which is not the default (10). Logs under `~/.hermes/logs/`, every session in a local database, an approval history that can be mined and an install audit log (12). SECURITY.md with a scope, a 90-day disclosure window, a security address and GitHub private reporting, plus OSV and supply-chain audit workflows and exact dependency pins. No bug bounty by its own statement, no security.txt (404), and no published advisory although v0.21.6 lists six security fixes (11)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 60, "points": 7.5, "reason": "Read with the self-hosted rule. No payment protocol on Hermes Agent's own interfaces (0). The optional MPP skill makes the agent a payer, which this line does not count. The software is free under MIT, needs no account and runs with a local model, so 20, 20 and 20 on the last three lines. Nous sells two optional services we did not score here, Nous Portal plans at $0 to $200 a month and Hermes Cloud at $0.51 a day running on the Standard size, both with public prices." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 84, "points": 7.35, "reason": "v0.21.7 was published on 11 October 2026, the day before this check (30). Ten releases appear between 19 August and 11 October 2026 (20). Issues are labelled by priority and component the day they arrive and v0.21.7 merged about 204 pull requests in three days, but 15,102 issues and more than 5,000 pull requests are open and most of the day's reports had no comment (13 of 25). Not an MCP server, so read as for Goose on builds. The Docker image, desktop bundles, installers and Termux packages are promoted from one release receipt (13 of 15). Exact dependency pins with a lock file, an OSV scanner, a supply-chain audit and Dependabot for Actions, with CI on main unconfirmed (8 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 63, "points": 5.51, "note": "editorial 73, provenance 53", "reason": "MIT (30). The FAQ says nothing is collected and data stays in `~/.hermes/`, and the docs name where memory, sessions, tokens and the vault live. There is no privacy statement for the software itself, the FAQ's claim that API calls go only to the model provider leaves out the web search, speech and browser backends the docs describe elsewhere, and the docs do not mention that the Portal terms allow training on customer data (17 of 30). The CLI reference marks deprecated commands and `hermes migrate` rewrites retired settings, but no deprecation policy or dated notices were found (8 of 20). No telemetry to opt out of per the docs, and update checks can be turned off (18 of 20)." } ], "assessment": { "date": "2026-10-12", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Harness reading, scored on what a person or pipeline driving it must supply. A tool search index, toolsets and per-server MCP include and exclude filters keep definitions out of context (22 of 25). `--max-turns` with a default of 500, automatic context compression and a usage report file, though 500 turns is high for an unattended run (15 of 20). `hermes chat -q` with `--format stream-json`, and the FAQ maps errors to fixes (16 of 20). The runs API takes an `Idempotency-Key`, sessions resume, and cron tracks failure streaks and delivery failures apart from run failures (17 of 20). One install command and a setup wizard, but a model provider must be configured first, and the Python library has no published package (10 of 15).", "maintenance": "v0.21.7 was published on 11 October 2026, the day before this check (30). Ten releases appear between 19 August and 11 October 2026 (20). Issues are labelled by priority and component the day they arrive and v0.21.7 merged about 204 pull requests in three days, but 15,102 issues and more than 5,000 pull requests are open and most of the day's reports had no comment (13 of 25). Not an MCP server, so read as for Goose on builds. The Docker image, desktop bundles, installers and Termux packages are promoted from one release receipt (13 of 15). Exact dependency pins with a lock file, an OSV scanner, a supply-chain audit and Dependabot for Actions, with CI on main unconfirmed (8 of 10).", "payments": "Read with the self-hosted rule. No payment protocol on Hermes Agent's own interfaces (0). The optional MPP skill makes the agent a payer, which this line does not count. The software is free under MIT, needs no account and runs with a local model, so 20, 20 and 20 on the last three lines. Nous sells two optional services we did not score here, Nous Portal plans at $0 to $200 a month and Hermes Cloud at $0.51 a day running on the Standard size, both with public prices.", "reliability": "Read with the local-software lines, as the Goose and Khoj dossiers are. An install script, desktop installers for macOS and Windows, a Docker image (`nousresearch/hermes-agent`) and a signed Termux repository, with Python 3.14 stated as the only supported version, but the docs say no supported wheel or source distribution is published (18 of 20). `ci.yaml` runs on every pull request and push to main and the repository holds about 5,700 test files, and a stable release must pass the whole suite. The Actions page we loaded showed only pull-request runs, so the state of main is unconfirmed (18 of 25). 15,102 open issues and more than 5,000 open pull requests on 12 October 2026. New reports get priority and component labels the same day, but the first page held P1 bugs on session state and context compression with no comment (10 of 25). The project moved from date versions to SemVer at v0.21.6 on 8 October 2026, and the v0.21.6 notes, which cover about 2,106 pull requests, have no breaking-change section (6 of 15). Version 0.21.7, before 1.0, on a channel the project calls stable (5 of 15).", "schema": "Harness reading of the framework line, as for Goose. Reference pages for configuration, environment variables, CLI commands and MCP config, and the API server documents its routes, but no OpenAPI file was found (17 of 25). `llms.txt`, a per-section docs index and a full-text file are served (10). The security page says what each guard catches and misses, and pages such as heartbeat against cron say when to use which (16 of 20). Config keys are listed with defaults and allowed values, such as the three approval modes (12 of 15). An FAQ explains error messages and their fixes, and each feature page carries examples (13 of 15). Dated release notes on GitHub with no changelog file, and the version scheme changed in October 2026 (12 of 15).", "security": "Harness reading used for Goose. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. The FAQ says no telemetry, usage data or analytics is collected and our search of the source found no analytics client in the core, with passive update checks the owner can disable (28). Three approval modes, a fixed blocklist, owner deny rules, `deny` defaults for cron, one-shot and webhook sessions, card fills that always ask, and a gateway that denies all senders by default. Against that, the default backend runs on the host, the default `smart` mode lets an auxiliary model approve commands, container backends skip the check, memory writes are ungated by default, and sending mail through the Google Workspace skill is held back only by an instruction to the model (14). Context files and cron prompts are scanned for injection patterns, URL tools block private addresses, and SECURITY.md says plainly that these are heuristics, that prompt injection alone is out of scope and that untrusted input calls for whole-process sandboxing, which is not the default (10). Logs under `~/.hermes/logs/`, every session in a local database, an approval history that can be mined and an install audit log (12). SECURITY.md with a scope, a 90-day disclosure window, a security address and GitHub private reporting, plus OSV and supply-chain audit workflows and exact dependency pins. No bug bounty by its own statement, no security.txt (404), and no published advisory although v0.21.6 lists six security fixes (11).", "transparency": "MIT (30). The FAQ says nothing is collected and data stays in `~/.hermes/`, and the docs name where memory, sessions, tokens and the vault live. There is no privacy statement for the software itself, the FAQ's claim that API calls go only to the model provider leaves out the web search, speech and browser backends the docs describe elsewhere, and the docs do not mention that the Portal terms allow training on customer data (17 of 30). The CLI reference marks deprecated commands and `hermes migrate` rewrites retired settings, but no deprecation policy or dated notices were found (8 of 20). No telemetry to opt out of per the docs, and update checks can be turned off (18 of 20)." }, "sources": [ { "what": "repository main branch (shallow clone, commit 3f2abce of 12 October 2026)", "url": "https://github.com/NousResearch/hermes-agent", "seen": "2026-10-12" }, { "what": "security policy", "url": "https://github.com/NousResearch/hermes-agent/blob/main/SECURITY.md", "seen": "2026-10-12" }, { "what": "security guide (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/security.md", "seen": "2026-10-12" }, { "what": "memory (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/memory.md", "seen": "2026-10-12" }, { "what": "passwords, logins and card fills (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/credential-vault.md", "seen": "2026-10-12" }, { "what": "secrets (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/secrets/index.md", "seen": "2026-10-12" }, { "what": "cron (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/cron.md", "seen": "2026-10-12" }, { "what": "heartbeat (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/heartbeat.md", "seen": "2026-10-12" }, { "what": "messaging gateway (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/messaging/index.md", "seen": "2026-10-12" }, { "what": "MCP client (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/mcp.md", "seen": "2026-10-12" }, { "what": "API server (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/api-server.md", "seen": "2026-10-12" }, { "what": "FAQ, data and telemetry (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/reference/faq.md", "seen": "2026-10-12" }, { "what": "Google Workspace skill scopes and rules", "url": "https://github.com/NousResearch/hermes-agent/blob/main/skills/productivity/google-workspace/scripts/setup.py", "seen": "2026-10-12" }, { "what": "toolsets", "url": "https://github.com/NousResearch/hermes-agent/blob/main/toolsets.py", "seen": "2026-10-12" }, { "what": "stable release process (docs source)", "url": "https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/stable-releases.md", "seen": "2026-10-12" }, { "what": "releases", "url": "https://github.com/NousResearch/hermes-agent/releases", "seen": "2026-10-12" }, { "what": "v0.21.6 release notes", "url": "https://github.com/NousResearch/hermes-agent/releases/tag/v0.21.6", "seen": "2026-10-12" }, { "what": "security advisories (none published)", "url": "https://github.com/NousResearch/hermes-agent/security/advisories", "seen": "2026-10-12" }, { "what": "open issues", "url": "https://github.com/NousResearch/hermes-agent/issues", "seen": "2026-10-12" }, { "what": "CI workflow runs", "url": "https://github.com/NousResearch/hermes-agent/actions/workflows/ci.yaml", "seen": "2026-10-12" }, { "what": "home page, plans and footer", "url": "https://hermes-agent.nousresearch.com/", "seen": "2026-10-12" }, { "what": "llms.txt", "url": "https://hermes-agent.nousresearch.com/llms.txt", "seen": "2026-10-12" }, { "what": "security.txt (404)", "url": "https://hermes-agent.nousresearch.com/.well-known/security.txt", "seen": "2026-10-12" }, { "what": "Hermes Cloud prices", "url": "https://portal.nousresearch.com/cloud", "seen": "2026-10-12" }, { "what": "Nous Portal terms of service, 28 September 2026", "url": "https://portal.nousresearch.com/terms", "seen": "2026-10-12" }, { "what": "Nous Portal privacy policy, 28 September 2026", "url": "https://portal.nousresearch.com/privacy", "seen": "2026-10-12" } ], "openQuestions": [ "Kind is `harness`. Hermes Agent is an agent program the owner runs, which is the closest kind the briefs define, and Reliability and Payments are read as local, self-hosted software", "The Nous Portal terms and privacy policy are not linked as `provenance.terms` and `provenance.privacy`, because they govern the optional hosted services and not the software under the MIT licence. The licence stands in", "Hermes Cloud, the hosted version, was not graded. It has its own prices, runs on Nous infrastructure and would be read as a hosted service", "Unchecked: whether CI passes on main today. The Actions page showed only pull-request runs", "Unchecked: the full text of the six security fixes in v0.21.6. Our reader returned the first line of each, and the affected versions were not stated", "Unchecked: release dates before 19 August 2026 and the first release date. GitHub's robots.txt closes the tags and commits pages to Anthropic agents, and the clone held three days of history", "Unchecked: whether an OpenAPI file exists for the API server. None was found in the docs pages read", "Unchecked: whether the Docker image name in the docs resolves on Docker Hub, and the domain registration date", "Whether the Nous Portal free plan needs a card was not established", "The star count is as GitHub's page showed it on 12 October 2026, rounded to the thousand", "github.com's robots.txt answered 200 and closes commits, tags, tree and raw paths to ClaudeBot and anthropic-ai. We read the source from a shallow clone and the releases, advisories, issues and Actions pages, none of which it closes. hermes-agent.nousresearch.com and portal.nousresearch.com answered 200, and nousresearch.com's robots.txt disallows its terms and privacy paths, which we did not read" ] }, "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" }, "notable": [ "SECURITY.md says the only security boundary against an adversarial model is the operating system, and that the approval gate, output redaction and pattern scanners are heuristics (https://github.com/NousResearch/hermes-agent/blob/main/SECURITY.md)", "The default approval mode is `smart`, in which an auxiliary model approves low-risk commands and denies dangerous ones (https://hermes-agent.nousresearch.com/docs/user-guide/security)", "Every saved-card fill asks first, and cron, webhook and API server sessions are refused (https://hermes-agent.nousresearch.com/docs/user-guide/features/credential-vault)", "The Google Workspace skill requests eight scopes including `gmail.send`, `gmail.modify`, `calendar` and `drive` (https://github.com/NousResearch/hermes-agent/blob/main/skills/productivity/google-workspace/scripts/setup.py)", "Memory is saved without approval unless `memory.write_approval` is set to true (https://hermes-agent.nousresearch.com/docs/user-guide/features/memory)", "The FAQ says Hermes Agent collects no telemetry, usage data or analytics (https://hermes-agent.nousresearch.com/docs/reference/faq)", "v0.21.6 of 8 October 2026 lists security fixes for dashboard authentication, repository git filters and the email gateway sender check (https://github.com/NousResearch/hermes-agent/releases/tag/v0.21.6)", "GitHub shows no published security advisories for the repository on 12 October 2026 (https://github.com/NousResearch/hermes-agent/security/advisories)", "Nous Portal terms of 28 September 2026, section 12.3, grant Nous Research a licence to use customer data to train models (https://portal.nousresearch.com/terms)", "Hermes Cloud instances cost $0.51 a day running and $0.03 a day stopped on the Standard size, with inference billed separately (https://portal.nousresearch.com/cloud)" ], "area": "frameworks", "details": [ { "label": "Where it runs", "value": "The owner's computer, server or container (Linux, macOS, Windows, WSL2, Android through Termux), with a desktop app, a terminal UI and a gateway process. Nous also sells hosted instances as Hermes Cloud, which this listing does not grade" }, { "label": "What it does without asking", "value": "Runs shell commands and edits files on the host. Dangerous command patterns go through approval, default mode `smart`, where an auxiliary model approves low-risk commands, denies dangerous ones and asks about the rest. `manual` always asks and `off` or `--yolo` never does. A fixed blocklist cannot be overridden" }, { "label": "Sending, paying, deleting", "value": "Saved-card fills always ask and are refused in cron, webhook and API sessions. Address fills need no confirmation. The Google Workspace skill tells the model to confirm before sending mail or changing calendar, Drive, Docs or Sheets, which is an instruction and not a code gate. Recursive deletes and SQL drops trigger approval" }, { "label": "Unattended runs", "value": "Cron jobs, `/heartbeat` prompts and webhook-triggered jobs. `approvals.cron_mode`, `single_query_mode` and `unattended_mode` default to `deny`, which blocks a dangerous command without asking. Cron sessions cannot create cron jobs" }, { "label": "Accounts and credentials", "value": "Google Workspace by OAuth (Gmail read, send and modify, Calendar, Drive, Contacts read-only, Sheets, Docs) with the token in `~/.hermes/google_token.json`. Mail over IMAP and SMTP. Site logins and cards in a Fernet-encrypted vault under `~/.hermes/vault/`, filled into the page without reaching the model, or read from 1Password or Bitwarden. API keys in `~/.hermes/.env` or an external secret manager. MCP OAuth tokens in `~/.hermes/mcp-tokens/`" }, { "label": "Memory", "value": "`MEMORY.md` (2,200 characters) and `USER.md` (1,375 characters) in `~/.hermes/memories/`, plain files the owner can edit or delete. Every session is stored in SQLite at `~/.hermes/state.db` with full-text search, removed with `hermes sessions delete` or `prune`. External memory providers such as Honcho and Mem0 are optional plugins" }, { "label": "Channels", "value": "Telegram, Discord, Slack, WhatsApp, Signal, SMS, email, Matrix, Mattermost, Microsoft Teams, Google Chat, LINE, iMessage through BlueBubbles or Photon, DingTalk, Feishu, WeCom, Weixin, QQ, IRC, ntfy, webhooks and an OpenAI-compatible API server" }, { "label": "Who can message it", "value": "Nobody by default. Per-channel allowlists, a cross-channel allowlist or a pairing code approved with `hermes pairing approve`. All authorised senders are trusted equally" }, { "label": "Model providers", "value": "Any the owner configures, among them Nous Portal, OpenRouter, OpenAI, Anthropic, Google, Ollama and LM Studio. Prompts and tool results go to that provider and to any auxiliary model, web search, speech or cloud browser backend that is turned on" }, { "label": "Sandbox", "value": "Terminal backends local (default, on the host), SSH, Docker, Singularity, Modal, Daytona and Vercel Sandbox. Container backends skip the dangerous-command check. The code execution tool, MCP subprocesses, plugins and skills run in the agent process whatever the backend" }, { "label": "MCP client", "value": "stdio and HTTP servers with OAuth 2.1, per-server `tools.include` and `tools.exclude`, a catalogue of reviewed servers, and a filtered environment for stdio servers" }, { "label": "Telemetry", "value": "None, per the FAQ. Passive update checks can be turned off" }, { "label": "Cost of a month", "value": "The software is free. Model usage is billed by the provider chosen, or nothing with a local model. Optional Nous Portal plans are $0, $20, $100 and $200 a month, and an optional Hermes Cloud instance is $0.51 a day running on the Standard size (about $15 for 30 days) plus inference" }, { "label": "Releases", "value": "v0.21.7 on 11 October 2026 and v0.21.6 on 8 October, after eight date-versioned releases from 19 August to 24 September 2026" }, { "label": "Security advisories", "value": "None published on GitHub on 12 October 2026. The v0.21.6 notes list fixes for dashboard sign-in, git filter programs and the email sender allowlist" } ], "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, "checks": [ { "check": "Legal entity named", "value": "Nous Research, Inc.", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "nousresearch.com, no registry record we could read", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the MIT licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hermes-agent.json" }, "verify": { "accepts": "a page on nousresearch.com or one of its subdomains, or the README of github.com/NousResearch/hermes-agent", "badgeUrl": "https://www.anchorterminal.com/badges/hermes-agent.svg", "body": { "slug": "hermes-agent", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/hermes-agent", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/hermes-agent\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/hermes-agent.svg\" alt=\"Hermes Agent on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Hermes Agent on Anchor Terminal](https://www.anchorterminal.com/badges/hermes-agent.svg)](https://www.anchorterminal.com/tools/hermes-agent)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/hermes-agent\"\u003eHermes Agent on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/hermes-agent", "json": "https://www.anchorterminal.com/tools/hermes-agent.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/hermes-agent.md", "slim": "https://www.anchorterminal.com/tools/hermes-agent.min.md" }, "markdown": "## Overview\n\n**Grade B · 67.9/100 · rank #244 of 986 · #3 in Personal assistants · not agent-ready · confidence medium**\n\n\n## Assessment\n\nCard 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## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Nous Research (https://hermes-agent.nousresearch.com) |\n| Kind | Agent harness |\n| Category | Personal assistants (https://www.anchorterminal.com/categories/personal-assistants) |\n| Auth | None · 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`. |\n| Pricing | Free (Free · OSS) · 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. |\n| x402 | No · 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). |\n| Licence | MIT |\n| Packages | oci: `nousresearch/hermes-agent` |\n| Source | https://github.com/NousResearch/hermes-agent |\n| Docs | https://hermes-agent.nousresearch.com/docs/ |\n| llms.txt | https://hermes-agent.nousresearch.com/llms.txt |\n| Last release | 2026-10-11 |\n| GitHub stars | 253,000 (as of 2026-10-12) |\n| Where it runs | The owner's computer, server or container (Linux, macOS, Windows, WSL2, Android through Termux), with a desktop app, a terminal UI and a gateway process. Nous also sells hosted instances as Hermes Cloud, which this listing does not grade |\n| What it does without asking | Runs shell commands and edits files on the host. Dangerous command patterns go through approval, default mode `smart`, where an auxiliary model approves low-risk commands, denies dangerous ones and asks about the rest. `manual` always asks and `off` or `--yolo` never does. A fixed blocklist cannot be overridden |\n| Sending, paying, deleting | Saved-card fills always ask and are refused in cron, webhook and API sessions. Address fills need no confirmation. The Google Workspace skill tells the model to confirm before sending mail or changing calendar, Drive, Docs or Sheets, which is an instruction and not a code gate. Recursive deletes and SQL drops trigger approval |\n| Unattended runs | Cron jobs, `/heartbeat` prompts and webhook-triggered jobs. `approvals.cron_mode`, `single_query_mode` and `unattended_mode` default to `deny`, which blocks a dangerous command without asking. Cron sessions cannot create cron jobs |\n| Accounts and credentials | Google Workspace by OAuth (Gmail read, send and modify, Calendar, Drive, Contacts read-only, Sheets, Docs) with the token in `~/.hermes/google_token.json`. Mail over IMAP and SMTP. Site logins and cards in a Fernet-encrypted vault under `~/.hermes/vault/`, filled into the page without reaching the model, or read from 1Password or Bitwarden. API keys in `~/.hermes/.env` or an external secret manager. MCP OAuth tokens in `~/.hermes/mcp-tokens/` |\n| Memory | `MEMORY.md` (2,200 characters) and `USER.md` (1,375 characters) in `~/.hermes/memories/`, plain files the owner can edit or delete. Every session is stored in SQLite at `~/.hermes/state.db` with full-text search, removed with `hermes sessions delete` or `prune`. External memory providers such as Honcho and Mem0 are optional plugins |\n| Channels | Telegram, Discord, Slack, WhatsApp, Signal, SMS, email, Matrix, Mattermost, Microsoft Teams, Google Chat, LINE, iMessage through BlueBubbles or Photon, DingTalk, Feishu, WeCom, Weixin, QQ, IRC, ntfy, webhooks and an OpenAI-compatible API server |\n| Who can message it | Nobody by default. Per-channel allowlists, a cross-channel allowlist or a pairing code approved with `hermes pairing approve`. All authorised senders are trusted equally |\n| Model providers | Any the owner configures, among them Nous Portal, OpenRouter, OpenAI, Anthropic, Google, Ollama and LM Studio. Prompts and tool results go to that provider and to any auxiliary model, web search, speech or cloud browser backend that is turned on |\n| Sandbox | Terminal backends local (default, on the host), SSH, Docker, Singularity, Modal, Daytona and Vercel Sandbox. Container backends skip the dangerous-command check. The code execution tool, MCP subprocesses, plugins and skills run in the agent process whatever the backend |\n| MCP client | stdio and HTTP servers with OAuth 2.1, per-server `tools.include` and `tools.exclude`, a catalogue of reviewed servers, and a filtered environment for stdio servers |\n| Telemetry | None, per the FAQ. Passive update checks can be turned off |\n| Cost of a month | The software is free. Model usage is billed by the provider chosen, or nothing with a local model. Optional Nous Portal plans are $0, $20, $100 and $200 a month, and an optional Hermes Cloud instance is $0.51 a day running on the Standard size (about $15 for 30 days) plus inference |\n| Releases | v0.21.7 on 11 October 2026 and v0.21.6 on 8 October, after eight date-versioned releases from 19 August to 24 September 2026 |\n| Security advisories | None published on GitHub on 12 October 2026. The v0.21.6 notes list fixes for dashboard sign-in, git filter programs and the email sender allowlist |\n| Capabilities | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, assistant.self-hosted, agent.mcp-client |\n| Tags | open-source, self-hosted, local, free, no-card, python, docker, llms-txt, pre-1.0 |\n| JSON | https://www.anchorterminal.com/api/v1/tools/hermes-agent.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-12 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 57 | 11.4 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 80 | 13.0 |\n| Agent ergonomics | 13% | 16.2 | 80 | 13.0 |\n| Security \u0026 auth | 14% | 17.5 | 75 | 13.1 |\n| Payments \u0026 pricing | 10% | 12.5 | 60 | 7.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 84 | 7.3 |\n| Transparency \u0026 trust (editorial 73, provenance 53) | 7% | 8.8 | 63 | 5.5 |\n| Negative events | up to −15 | up to −15 | 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 | -3 |\n| **Total** | | | | **67.9 → B** |\n\n### Why each score\n\n- Reliability 57: Read with the local-software lines, as the Goose and Khoj dossiers are. An install script, desktop installers for macOS and Windows, a Docker image (`nousresearch/hermes-agent`) and a signed Termux repository, with Python 3.14 stated as the only supported version, but the docs say no supported wheel or source distribution is published (18 of 20). `ci.yaml` runs on every pull request and push to main and the repository holds about 5,700 test files, and a stable release must pass the whole suite. The Actions page we loaded showed only pull-request runs, so the state of main is unconfirmed (18 of 25). 15,102 open issues and more than 5,000 open pull requests on 12 October 2026. New reports get priority and component labels the same day, but the first page held P1 bugs on session state and context compression with no comment (10 of 25). The project moved from date versions to SemVer at v0.21.6 on 8 October 2026, and the v0.21.6 notes, which cover about 2,106 pull requests, have no breaking-change section (6 of 15). Version 0.21.7, before 1.0, on a channel the project calls stable (5 of 15).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 80: Harness reading of the framework line, as for Goose. Reference pages for configuration, environment variables, CLI commands and MCP config, and the API server documents its routes, but no OpenAPI file was found (17 of 25). `llms.txt`, a per-section docs index and a full-text file are served (10). The security page says what each guard catches and misses, and pages such as heartbeat against cron say when to use which (16 of 20). Config keys are listed with defaults and allowed values, such as the three approval modes (12 of 15). An FAQ explains error messages and their fixes, and each feature page carries examples (13 of 15). Dated release notes on GitHub with no changelog file, and the version scheme changed in October 2026 (12 of 15).\n- Agent ergonomics 80: Harness reading, scored on what a person or pipeline driving it must supply. A tool search index, toolsets and per-server MCP include and exclude filters keep definitions out of context (22 of 25). `--max-turns` with a default of 500, automatic context compression and a usage report file, though 500 turns is high for an unattended run (15 of 20). `hermes chat -q` with `--format stream-json`, and the FAQ maps errors to fixes (16 of 20). The runs API takes an `Idempotency-Key`, sessions resume, and cron tracks failure streaks and delivery failures apart from run failures (17 of 20). One install command and a setup wizard, but a model provider must be configured first, and the Python library has no published package (10 of 15).\n- Security \u0026 auth 75: Harness reading used for Goose. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. The FAQ says no telemetry, usage data or analytics is collected and our search of the source found no analytics client in the core, with passive update checks the owner can disable (28). Three approval modes, a fixed blocklist, owner deny rules, `deny` defaults for cron, one-shot and webhook sessions, card fills that always ask, and a gateway that denies all senders by default. Against that, the default backend runs on the host, the default `smart` mode lets an auxiliary model approve commands, container backends skip the check, memory writes are ungated by default, and sending mail through the Google Workspace skill is held back only by an instruction to the model (14). Context files and cron prompts are scanned for injection patterns, URL tools block private addresses, and SECURITY.md says plainly that these are heuristics, that prompt injection alone is out of scope and that untrusted input calls for whole-process sandboxing, which is not the default (10). Logs under `~/.hermes/logs/`, every session in a local database, an approval history that can be mined and an install audit log (12). SECURITY.md with a scope, a 90-day disclosure window, a security address and GitHub private reporting, plus OSV and supply-chain audit workflows and exact dependency pins. No bug bounty by its own statement, no security.txt (404), and no published advisory although v0.21.6 lists six security fixes (11).\n- Payments \u0026 pricing 60: Read with the self-hosted rule. No payment protocol on Hermes Agent's own interfaces (0). The optional MPP skill makes the agent a payer, which this line does not count. The software is free under MIT, needs no account and runs with a local model, so 20, 20 and 20 on the last three lines. Nous sells two optional services we did not score here, Nous Portal plans at $0 to $200 a month and Hermes Cloud at $0.51 a day running on the Standard size, both with public prices.\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 84: v0.21.7 was published on 11 October 2026, the day before this check (30). Ten releases appear between 19 August and 11 October 2026 (20). Issues are labelled by priority and component the day they arrive and v0.21.7 merged about 204 pull requests in three days, but 15,102 issues and more than 5,000 pull requests are open and most of the day's reports had no comment (13 of 25). Not an MCP server, so read as for Goose on builds. The Docker image, desktop bundles, installers and Termux packages are promoted from one release receipt (13 of 15). Exact dependency pins with a lock file, an OSV scanner, a supply-chain audit and Dependabot for Actions, with CI on main unconfirmed (8 of 10).\n- Transparency \u0026 trust 63: MIT (30). The FAQ says nothing is collected and data stays in `~/.hermes/`, and the docs name where memory, sessions, tokens and the vault live. There is no privacy statement for the software itself, the FAQ's claim that API calls go only to the model provider leaves out the web search, speech and browser backends the docs describe elsewhere, and the docs do not mention that the Portal terms allow training on customer data (17 of 30). The CLI reference marks deprecated commands and `hermes migrate` rewrites retired settings, but no deprecation policy or dated notices were found (8 of 20). No telemetry to opt out of per the docs, and update checks can be turned off (18 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (22 items): https://www.anchorterminal.com/fixes/hermes-agent.md (JSON https://www.anchorterminal.com/fixes/hermes-agent.json)\n\n### What we couldn't check\n\n- Kind is `harness`. Hermes Agent is an agent program the owner runs, which is the closest kind the briefs define, and Reliability and Payments are read as local, self-hosted software\n- The Nous Portal terms and privacy policy are not linked as `provenance.terms` and `provenance.privacy`, because they govern the optional hosted services and not the software under the MIT licence. The licence stands in\n- Hermes Cloud, the hosted version, was not graded. It has its own prices, runs on Nous infrastructure and would be read as a hosted service\n- Unchecked: whether CI passes on main today. The Actions page showed only pull-request runs\n- Unchecked: the full text of the six security fixes in v0.21.6. Our reader returned the first line of each, and the affected versions were not stated\n- Unchecked: release dates before 19 August 2026 and the first release date. GitHub's robots.txt closes the tags and commits pages to Anthropic agents, and the clone held three days of history\n- Unchecked: whether an OpenAPI file exists for the API server. None was found in the docs pages read\n- Unchecked: whether the Docker image name in the docs resolves on Docker Hub, and the domain registration date\n- Whether the Nous Portal free plan needs a card was not established\n- The star count is as GitHub's page showed it on 12 October 2026, rounded to the thousand\n- github.com's robots.txt answered 200 and closes commits, tags, tree and raw paths to ClaudeBot and anthropic-ai. We read the source from a shallow clone and the releases, advisories, issues and Actions pages, none of which it closes. hermes-agent.nousresearch.com and portal.nousresearch.com answered 200, and nousresearch.com's robots.txt disallows its terms and privacy paths, which we did not read\n\n### Sources\n\n- repository main branch (shallow clone, commit 3f2abce of 12 October 2026): \u003chttps://github.com/NousResearch/hermes-agent\u003e (seen 2026-10-12)\n- security policy: \u003chttps://github.com/NousResearch/hermes-agent/blob/main/SECURITY.md\u003e (seen 2026-10-12)\n- security guide (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/security.md\u003e (seen 2026-10-12)\n- memory (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/memory.md\u003e (seen 2026-10-12)\n- passwords, logins and card fills (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/credential-vault.md\u003e (seen 2026-10-12)\n- secrets (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/secrets/index.md\u003e (seen 2026-10-12)\n- cron (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/cron.md\u003e (seen 2026-10-12)\n- heartbeat (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/heartbeat.md\u003e (seen 2026-10-12)\n- messaging gateway (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/messaging/index.md\u003e (seen 2026-10-12)\n- MCP client (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/mcp.md\u003e (seen 2026-10-12)\n- API server (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/api-server.md\u003e (seen 2026-10-12)\n- FAQ, data and telemetry (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/reference/faq.md\u003e (seen 2026-10-12)\n- Google Workspace skill scopes and rules: \u003chttps://github.com/NousResearch/hermes-agent/blob/main/skills/productivity/google-workspace/scripts/setup.py\u003e (seen 2026-10-12)\n- toolsets: \u003chttps://github.com/NousResearch/hermes-agent/blob/main/toolsets.py\u003e (seen 2026-10-12)\n- stable release process (docs source): \u003chttps://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/stable-releases.md\u003e (seen 2026-10-12)\n- releases: \u003chttps://github.com/NousResearch/hermes-agent/releases\u003e (seen 2026-10-12)\n- v0.21.6 release notes: \u003chttps://github.com/NousResearch/hermes-agent/releases/tag/v0.21.6\u003e (seen 2026-10-12)\n- security advisories (none published): \u003chttps://github.com/NousResearch/hermes-agent/security/advisories\u003e (seen 2026-10-12)\n- open issues: \u003chttps://github.com/NousResearch/hermes-agent/issues\u003e (seen 2026-10-12)\n- CI workflow runs: \u003chttps://github.com/NousResearch/hermes-agent/actions/workflows/ci.yaml\u003e (seen 2026-10-12)\n- home page, plans and footer: \u003chttps://hermes-agent.nousresearch.com/\u003e (seen 2026-10-12)\n- llms.txt: \u003chttps://hermes-agent.nousresearch.com/llms.txt\u003e (seen 2026-10-12)\n- security.txt (404): \u003chttps://hermes-agent.nousresearch.com/.well-known/security.txt\u003e (seen 2026-10-12)\n- Hermes Cloud prices: \u003chttps://portal.nousresearch.com/cloud\u003e (seen 2026-10-12)\n- Nous Portal terms of service, 28 September 2026: \u003chttps://portal.nousresearch.com/terms\u003e (seen 2026-10-12)\n- Nous Portal privacy policy, 28 September 2026: \u003chttps://portal.nousresearch.com/privacy\u003e (seen 2026-10-12)\n\n## Who's behind it (provenance 53/100, checked 2026-10-12)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Nous Research, Inc. | 20/20 |\n| Domain age | nousresearch.com, no registry record we could read | 0/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | nothing hosted, so the MIT licence stands in | 10/10 |\n| Privacy policy | nothing hosted, not scored | n/a |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n\nThe site footer reads Nous Research, Inc., and the Nous Portal terms name it as a Delaware corporation.\n\nNo 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.\n\nhermes-agent.nousresearch.com/.well-known/security.txt answered 404. SECURITY.md in the repository gives security@nousresearch.com and GitHub private reporting.\n\nNo status page applies to software the owner runs. None was looked for on the Portal.\n\nThe domain registration date was not looked up.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full.\n\n\n**Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored.\n\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Strengths\n\n- Every saved-card fill asks for approval, and cron, webhook and API sessions are refused because nobody can confirm\n- The messaging gateway denies all senders until an allowlist or a pairing code approved on the CLI is in place\n- The docs say no telemetry, usage data or analytics is collected, and conversations, memory and skills stay in `~/.hermes/`\n- SECURITY.md states that in-process checks are not a boundary and names OS-level isolation as the only one\n- Ten releases between 19 August and 11 October 2026, the latest v0.21.7 on 11 October\n\n## Weaknesses\n\n- 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- 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\n- Memory writes are saved without approval by default (`memory.write_approval: false`), including from a background review after each turn\n- Release v0.21.6 of 8 October 2026 lists six security fixes and the repository has no published security advisory\n- 15,102 open issues and more than 5,000 open pull requests on 12 October 2026\n- The Nous Portal terms grant Nous a licence to train models on customer data when the Portal is the model provider\n\n## Before you call it (notes for agents)\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## Connect\n\nInstall:\n\n```bash\ncurl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash # then: hermes setup\n```\n\nHeadless / CI:\n\n```json\n{\n \"command\": \"hermes chat -q \\\"$TASK\\\" --format stream-json --max-turns 30\"\n}\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| ZeroClaw | BB | 70.2 | 161 | assistant.proactive, assistant.messaging, assistant.memory, assistant.self-hosted, assistant.accounts, agent.mcp-client | no | https://www.anchorterminal.com/tools/zeroclaw.md |\n| NanoClaw | B | 68.3 | 229 | assistant.proactive, assistant.messaging, assistant.memory, assistant.self-hosted, agent.mcp-client, assistant.accounts | no | https://www.anchorterminal.com/tools/nanoclaw.md |\n| OpenClaw | B | 67.1 | 270 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/openclaw.md |\n| IronClaw | B | 66.7 | 288 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/ironclaw.md |\n| nanobot | B | 62.4 | 446 | assistant.proactive, assistant.messaging, assistant.memory, assistant.self-hosted, assistant.accounts, agent.mcp-client | no | https://www.anchorterminal.com/tools/nanobot.md |\n| QwenPaw | B | 62.2 | 454 | assistant.proactive, assistant.messaging, assistant.accounts, assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/qwenpaw.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- SECURITY.md says the only security boundary against an adversarial model is the operating system, and that the approval gate, output redaction and pattern scanners are heuristics (source: \u003chttps://github.com/NousResearch/hermes-agent/blob/main/SECURITY.md\u003e)\n- The default approval mode is `smart`, in which an auxiliary model approves low-risk commands and denies dangerous ones (source: \u003chttps://hermes-agent.nousresearch.com/docs/user-guide/security\u003e)\n- Every saved-card fill asks first, and cron, webhook and API server sessions are refused (source: \u003chttps://hermes-agent.nousresearch.com/docs/user-guide/features/credential-vault\u003e)\n- The Google Workspace skill requests eight scopes including `gmail.send`, `gmail.modify`, `calendar` and `drive` (source: \u003chttps://github.com/NousResearch/hermes-agent/blob/main/skills/productivity/google-workspace/scripts/setup.py\u003e)\n- Memory is saved without approval unless `memory.write_approval` is set to true (source: \u003chttps://hermes-agent.nousresearch.com/docs/user-guide/features/memory\u003e)\n- The FAQ says Hermes Agent collects no telemetry, usage data or analytics (source: \u003chttps://hermes-agent.nousresearch.com/docs/reference/faq\u003e)\n- v0.21.6 of 8 October 2026 lists security fixes for dashboard authentication, repository git filters and the email gateway sender check (source: \u003chttps://github.com/NousResearch/hermes-agent/releases/tag/v0.21.6\u003e)\n- GitHub shows no published security advisories for the repository on 12 October 2026 (source: \u003chttps://github.com/NousResearch/hermes-agent/security/advisories\u003e)\n- Nous Portal terms of 28 September 2026, section 12.3, grant Nous Research a licence to use customer data to train models (source: \u003chttps://portal.nousresearch.com/terms\u003e)\n- Hermes Cloud instances cost $0.51 a day running and $0.03 a day stopped on the Standard size, with inference billed separately (source: \u003chttps://portal.nousresearch.com/cloud\u003e)\n\n- #3 of 20 in 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## Compare\n\n- [AstrBot vs Hermes Agent](https://www.anchorterminal.com/compare/astrbot-vs-hermes-agent.md): C 58.8 vs B 67.9\n- [CowAgent vs Hermes Agent](https://www.anchorterminal.com/compare/cowagent-vs-hermes-agent.md): C 58.5 vs B 67.9\n- [GAIA vs Hermes Agent](https://www.anchorterminal.com/compare/gaia-vs-hermes-agent.md): D 49.5 vs B 67.9\n- [Gemini Spark vs Hermes Agent](https://www.anchorterminal.com/compare/gemini-spark-vs-hermes-agent.md): F 24.5 vs B 67.9\n- [Grok Bot vs Hermes Agent](https://www.anchorterminal.com/compare/grok-bot-vs-hermes-agent.md): E 45.2 vs B 67.9\n- [Haven vs Hermes Agent](https://www.anchorterminal.com/compare/haven-vs-hermes-agent.md): F 22.2 vs B 67.9\n- [Hermes Agent vs Instinct](https://www.anchorterminal.com/compare/hermes-agent-vs-instinct.md): B 67.9 vs F 11.4\n- [Hermes Agent vs IronClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-ironclaw.md): B 67.9 vs B 66.7\n- [Hermes Agent vs Leon](https://www.anchorterminal.com/compare/hermes-agent-vs-leon.md): B 67.9 vs E 41\n- [Hermes Agent vs Lindy](https://www.anchorterminal.com/compare/hermes-agent-vs-lindy.md): B 67.9 vs F 32.3\n- [Hermes Agent vs nanobot](https://www.anchorterminal.com/compare/hermes-agent-vs-nanobot.md): B 67.9 vs B 62.4\n- [Hermes Agent vs NanoClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-nanoclaw.md): B 67.9 vs B 68.3\n- [Hermes Agent vs Dots](https://www.anchorterminal.com/compare/hermes-agent-vs-openai-dots.md): B 67.9 vs F 28.3\n- [Hermes Agent vs OpenClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-openclaw.md): B 67.9 vs B 67.1\n- [Hermes Agent vs PicoClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-picoclaw.md): B 67.9 vs D 46.1\n- [Hermes Agent vs Poke](https://www.anchorterminal.com/compare/hermes-agent-vs-poke.md): B 67.9 vs F 37.6\n- [Hermes Agent vs QwenPaw](https://www.anchorterminal.com/compare/hermes-agent-vs-qwenpaw.md): B 67.9 vs B 62.2\n- [Hermes Agent vs ZeroClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-zeroclaw.md): B 67.9 vs BB 70.2\n- [Hermes Agent vs Zo Computer](https://www.anchorterminal.com/compare/hermes-agent-vs-zo-computer.md): B 67.9 vs E 43.1\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on nousresearch.com or one of its subdomains, or the README of github.com/NousResearch/hermes-agent. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"hermes-agent\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/hermes-agent\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/hermes-agent.svg\" alt=\"Hermes Agent on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Hermes Agent on Anchor Terminal](https://www.anchorterminal.com/badges/hermes-agent.svg)](https://www.anchorterminal.com/tools/hermes-agent)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/hermes-agent\"\u003eHermes Agent on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Hermes Agent is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/hermes-agent-dark.png\n- Light: https://www.anchorterminal.com/assets/share/hermes-agent-light.png\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": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Personal assistants", "url": "https://www.anchorterminal.com/categories/personal-assistants" }, { "name": "Hermes Agent", "url": "" } ], "description": "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.", "facts": [ "rank #244 of 986", "None auth", "0 desk reviews" ], "h1": "Hermes Agent", "image": "https://www.anchorterminal.com/assets/og/tools-hermes-agent.png", "path": "/tools/hermes-agent", "published": "2026-10-01", "section": "tools", "title": "Hermes Agent review (2026): pricing, alternatives and grade B", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/tools/hermes-agent" }, "tokens": { "markdown": 8100, "slim": 2130 }, "version": 1 }