{ "data": { "a": { "slug": "cowagent", "name": "CowAgent", "vendor": "zhayujie", "vendorUrl": "https://cowagent.ai", "kind": "harness", "category": "personal-assistants", "summary": "CowAgent is an open-source AI assistant that its owner runs on a computer or server. It plans tasks, runs tools and skills, keeps long-term memory in local files and answers on a web console and messaging apps.", "url": "https://www.anchorterminal.com/tools/cowagent", "markdownUrl": "https://www.anchorterminal.com/tools/cowagent.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cowagent.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cowagent.json", "repo": "https://github.com/zhayujie/CowAgent", "license": "MIT", "transports": [ "http" ], "packages": [ { "registry": "oci", "name": "zhayujie/chatgpt-on-wechat" } ], "auth": "mixed", "authNotes": "No account. The web console listens on 127.0.0.1 with no password by default, and `web_password` adds a login whose session lasts 30 days. `external_api_token` is one Bearer token for the OpenAI-compatible endpoint, which stays off while the token is empty (https://docs.cowagent.ai/channels/web). Messaging channels use each platform's bot token or app secret in `config.json`. Model keys go in `config.json` or environment variables.", "pricing": "free", "pricingNotes": "Free under the MIT licence, with nothing to buy to run it. The owner pays the configured model provider, or nothing with a local model behind an OpenAI-compatible endpoint. The README names LinkAI as a seller of managed hosting, and link-ai.tech did not answer on 12 October 2026, so its prices were not read.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 47400, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://docs.cowagent.ai/intro/index", "llmsTxt": "https://docs.cowagent.ai/llms.txt", "capabilities": [ "assistant.proactive", "assistant.messaging", "assistant.memory", "assistant.self-hosted", "agent.mcp-client", "assistant.accounts" ], "tags": [ "open-source", "self-hosted", "local", "free", "no-card", "llms-txt", "docker", "python", "openai-compatible" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 58.5, "grade": "C", "agentReady": false, "rank": 591, "ranked": true, "rankOf": 986, "categoryRank": 9, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 83, "payments": 60, "reliability": 84, "schema": 67, "security": 43, "transparency": 45 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": -5, "negativeNotes": [ "2026-07-31. Issue #2998 reports that a member of a Feishu group asked the bot for local files and it sent the owner's documents into the group. This is the reporter's account and we did not reproduce it. We confirmed in the master source on 12 October 2026 that group channels accept every group, that full-access is the default and that the proposed sender gating is absent. Open and unfixed, -3. https://github.com/zhayujie/CowAgent/issues/2998", "2026-07-29. Version 2.1.5 fixed a chain in which injected content led the agent to rewrite the MCP config, run arbitrary commands and take keys, and fixed the `edit` tool reaching `~/.cow/.env`. Both are described in the release notes with no advisory. Fixed and documented, -2. https://docs.cowagent.ai/releases/v2.1.5" ], "verdict": "MIT software with seven releases in 90 days, memory kept as plain files in the owner's workspace and three per-session permission modes. Source and Docker installs default to full-access, no action asks for approval, and an open report of 31 July 2026 says group members could reach the owner's files through the bot.", "bestFor": "One technical owner who wants an assistant on WeChat, Feishu, DingTalk, Telegram, Slack or Discord with memory in local files and a choice of Chinese and Western model providers.", "strengths": [ "Memory is plain Markdown under `~/cow` (`MEMORY.md`, `memory/YYYY-MM-DD.md`), readable and removable by the owner", "Three permission modes per session (read-only, workspace-write, full-access), with a global default in `agent_permission_mode`", "The web console binds to 127.0.0.1 by default, and the cloud client loads only when `use_linkai` and a deployment id are both set", "Seven tagged releases between 20 July and 30 September 2026, each with dated notes in the docs", "Tests run on Python 3.11 and 3.13 for every push to master, and the 15 newest master runs we saw passed on 12 October 2026" ], "weaknesses": [ "Source and Docker installs default to full-access, and no mode asks the owner before a shell command, a file send or an MCP call", "The permission checks read arguments and are not an OS sandbox, as the source says. The `bash` blocklist covers only root deletion, disk wiping and power commands", "Issue #2998, open since 31 July 2026, reports the bot sending the owner's local documents into a Feishu group. Its fix is not on master", "No setting limits which Telegram, Slack or Discord users may message the bot, and those channels reply in every group", "No SECURITY.md, security.txt, privacy policy or terms. Model keys sit in `config.json` and MCP keys in `mcp.json` as plain text" ], "agentNotes": [ "Set `agent_permission_mode` to `workspace-write` or `read-only` before connecting any channel. Source and Docker installs default to `full-access`", "Keep the bot out of group chats that include other people. Any member who mentions it reaches the same tools as the owner", "Set `web_password` before changing `web_host` to `0.0.0.0`. The password is empty by default", "Set `external_api_token` to enable `POST /v1/chat/completions`, and send `conversation_id` to keep one session. The `model` field does not select a model", "Run it in a container for a hard boundary. The docs and the source both say the permission modes are not isolation" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.5 } ], "editorialScores": { "ergonomics": 59, "maintenance": 83, "payments": 60, "reliability": 84, "schema": 67, "security": 43, "transparency": 62 }, "provenanceScore": 27 }, "connect": { "install": "bash \u003c(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh) # or: curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml \u0026\u0026 docker compose up -d", "http": "curl http://localhost:9899/v1/chat/completions -H \"Authorization: Bearer $TOKEN\" -H \"Content-Type: application/json\" -d '{\"model\":\"cowagent\",\"conversation_id\":\"example-conversation\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'" }, "letme": { "capability": "https://letme.dev/assistant.proactive", "tool": "https://letme.dev/cowagent" }, "area": "frameworks", "provenance": { "legalEntity": "", "domain": "cowagent.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://docs.cowagent.ai/releases/overview", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "No company or legal entity is named for CowAgent. The licence names zhayujie, and the cowagent.ai footer reads Copyright 2026 CowAgent.", "The README lists sales@simple-future.tech and LinkAI (link-ai.tech) for enterprise services and managed hosting. link-ai.tech did not answer our robots.txt request on 12 October 2026, so none of its pages were read.", "cowagent.ai links no terms and no privacy policy. Its sitemap lists the home, download and blog pages only.", "cowagent.ai answers `/.well-known/security.txt` and `/llms.txt` with the home page, so neither file exists. docs.cowagent.ai serves an llms.txt.", "The registration date of cowagent.ai was not looked up." ], "score": 27 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cowagent.json" }, "answer": "IronClaw scores 66.7 (B) on agent readiness against CowAgent's 58.5 (C), and leads in 4 of 7 scored categories. CowAgent leads on reliability and maintenance \u0026 community.", "b": { "slug": "ironclaw", "name": "IronClaw", "vendor": "NEAR AI", "vendorUrl": "https://www.ironclaw.com", "kind": "harness", "category": "personal-assistants", "summary": "IronClaw is an open-source personal AI assistant written in Rust by NEAR AI. The owner runs it as a local service with a web interface, Slack and Telegram channels, Google and GitHub extensions, scheduled automations and persistent memory.", "url": "https://www.anchorterminal.com/tools/ironclaw", "markdownUrl": "https://www.anchorterminal.com/tools/ironclaw.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ironclaw.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ironclaw.json", "repo": "https://github.com/nearai/ironclaw", "license": "MIT OR Apache-2.0", "transports": [ "http" ], "packages": [], "auth": "mixed", "authNotes": "`ironclaw onboard` writes a bearer token to `~/.ironclaw/reborn/webui-token` and prints a login link that carries it as a `token` query parameter. The same token authorises the web interface and the Responses API with operator rights. Multi-user deployments can add Google or GitHub single sign-on and per-user API tokens with owner, admin or member roles. Connected accounts use OAuth (Google, Slack), a Telegram pairing code, or keys held in the encrypted secret store. The web interface binds to 127.0.0.1:3000 unless `--host` is changed (https://docs.ironclaw.com/using/webui.md).", "pricing": "freemium", "pricingNotes": "Free to self-host under MIT or Apache-2.0, with model usage billed by whichever provider the owner selects, or nothing with Ollama. NEAR AI sells hosted instances on ironclaw.com as Starter (shown as $5 beside $0 a month, 1 agent, $5 credits), Basic at $20 a month (2 agents, $20 credits) and Pro+ at $200 a month (5 agents, $200 credits). The page does not say whether a card is needed. NEAR AI Cloud inference is priced per million tokens on near.ai/pricing (checked 2026-10-12).", "priceSummary": "$20 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the release notes (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 12648, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://docs.ironclaw.com", "llmsTxt": "https://docs.ironclaw.com/llms.txt", "capabilities": [ "assistant.proactive", "assistant.messaging", "assistant.accounts", "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "tags": [ "open-source", "self-hosted", "rust", "wasm", "telegram", "slack", "gmail", "mcp", "hosted-option", "llms-txt" ], "lastRelease": "2026-09-29", "graded": true, "anchor": { "graded": true, "score": 66.7, "grade": "B", "agentReady": false, "rank": 288, "ranked": true, "rankOf": 986, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 74, "payments": 60, "reliability": 67, "schema": 74, "security": 66, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": -2, "negativeNotes": [ "2026-10-12. The ironclaw.com home page lists Discord and Signal among integrations, while the channel docs for the current release say Discord, Signal, WeChat and WeCom are not part of the 1.0 release, which shipped on 27 July 2026. The docs site also says it documents the latest stable release while its heartbeat, cron, shell and WASM pages name settings absent from the 1.4.1 source. A misleading claim, at the minimum, -2. https://www.ironclaw.com/; https://docs.ironclaw.com/channels/overview.md; https://github.com/nearai/ironclaw/blob/ironclaw-v1.4.1/docs/capabilities/routines/heartbeat.mdx" ], "verdict": "Credentials stay in an encrypted store and are injected at the host boundary, and extensions declare per-tool permissions, network targets and OAuth scopes. The global auto-approve setting defaults to on in the 1.4.1 source, so tools marked ask, such as `gmail.send_message`, run unprompted until the owner turns it off.", "bestFor": "One technical owner who wants a self-hosted assistant over Gmail, Calendar, Slack and Telegram with credentials kept out of the model's reach.", "strengths": [ "Dual MIT or Apache-2.0 licence, with installers for seven targets on GitHub releases and no account needed to run it", "Each extension tool declares a default permission, effects, network targets and OAuth scopes in `manifest.toml`. Gmail reads use `gmail.readonly` and sends use `gmail.send`", "Secrets are encrypted with AES-256-GCM per the README, with the master key in the OS keychain, and are injected into requests outside the sandbox", "No analytics library was found in the 1.4.1 source. Trace Commons is opt-in and has no default endpoint", "Six stable releases between 27 July and 29 September 2026, each with dated notes and upgrade steps" ], "weaknesses": [ "Global auto-approve defaults to on in the 1.4.1 source, so tools marked ask (send, trash, delete) run without a prompt. Only financial, approval and budget effects always ask", "The `main` branch has had no commit since 10 September 2026, and open reports filed since mid-September show no replies. 1,363 issues and 183 pull requests are open", "Docs pages for heartbeat, cron, shell and WASM limits name settings such as `HEARTBEAT_ENABLED` and `ALLOW_LOCAL_TOOLS` that do not appear in the 1.4.1 source", "No SECURITY.md, security.txt or published GitHub advisory was found", "The home page lists Discord and Signal integrations, while the channel docs say both are not part of the 1.0 release" ], "agentNotes": [ "Open Settings and turn off global auto-approve, or set send and delete tools to ask each time, before connecting mail or chat accounts", "Install with the release installer and run `ironclaw onboard`. 1.x does not migrate 0.29 data, so use a fresh home directory", "Call `POST /api/v1/responses` with the bearer token from `~/.ironclaw/reborn/webui-token`. Keep under 30 requests in 60 seconds", "Resolve approval and OAuth gates in the web interface. The Responses API fails the turn instead of surfacing them", "Connect MCP servers over HTTP only. The stdio transport is rejected" ], "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": 66.7 } ], "editorialScores": { "ergonomics": 69, "maintenance": 74, "payments": 60, "reliability": 67, "schema": 74, "security": 66, "transparency": 79 }, "provenanceScore": 71 }, "connect": { "install": "IRONCLAW_RELEASE_TAG=ironclaw-v1.4.1\ncurl --proto '=https' --tlsv1.2 -LsSf \"https://github.com/nearai/ironclaw/releases/download/${IRONCLAW_RELEASE_TAG}/ironclaw-installer.sh\" | sh\nironclaw onboard" }, "letme": { "capability": "https://letme.dev/assistant.proactive", "tool": "https://letme.dev/ironclaw" }, "area": "frameworks", "unitPrices": [ { "item": "Hosted Basic plan (2 agents, $20 credits)", "unit": "month", "usd": 20, "note": "NEAR AI Cloud, per ironclaw.com" }, { "item": "Hosted Pro+ plan (5 agents, $200 credits)", "unit": "month", "usd": 200, "note": "NEAR AI Cloud, per ironclaw.com" } ], "provenance": { "legalEntity": "Jasnah, Inc. d/b/a NEAR AI", "domain": "ironclaw.com", "domainRegistered": "2018-01-04", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://near.ai/privacy-policy", "statusPage": "", "changelog": "https://github.com/nearai/ironclaw/releases", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The NEAR AI terms of service (updated 24 September 2026) name Jasnah, Inc. d/b/a NEAR AI under Delaware law and cover NEAR AI Cloud and its API. They do not mention IronClaw or agent hosting, so no terms link is set and the MIT or Apache-2.0 licence stands in for the self-hosted software.", "The privacy policy (updated 4 September 2026) lists ironclaw.com, agent.near.ai, the IronClaw framework and IronHub among what it covers.", "The ironclaw.com home page says Built by Near Foundation and its footer says by NEAR AI.", "security.txt answered 404 on www.ironclaw.com, docs.ironclaw.com and near.ai.", "RDAP for ironclaw.com gives a registration date of 2018-01-04 and Cloudflare, Inc. as registrar, last changed 2026-04-20.", "A self-hosted instance answers on its owner's own host. Hosted instances answer at \u003cinstance-id\u003e.agents.near.ai per the quickstart." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ironclaw.json" }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "zhayujie", "b": "NEAR AI", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "MIT OR Apache-2.0", "name": "Licence" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-30", "b": "2026-09-29", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "47k stars", "b": "13k stars", "name": "Popularity" } ], "faq": [ { "answer": "IronClaw scores 66.7 (B) on agent readiness against CowAgent's 58.5 (C), and leads in 4 of 7 scored categories. CowAgent leads on reliability and maintenance \u0026 community.", "question": "Which is better for AI agents, CowAgent or IronClaw?" }, { "answer": "Yes. CowAgent is open source (MIT). IronClaw is open source (MIT OR Apache-2.0).", "question": "Are CowAgent and IronClaw open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 84 against 67", "Maintenance \u0026 community, 83 against 74" ], "also": [ "Free to start without a card" ], "goodFor": "One technical owner who wants an assistant on WeChat, Feishu, DingTalk, Telegram, Slack or Discord with memory in local files and a choice of Chinese and Western model providers.", "slug": "cowagent", "watchFor": "Source and Docker installs default to full-access, and no mode asks the owner before a shell command, a file send or an MCP call" }, { "aheadOn": [ "Schema \u0026 documentation, 74 against 67", "Agent ergonomics, 69 against 59", "Security \u0026 auth, 66 against 43", "Transparency \u0026 trust, 75 against 45" ], "also": null, "goodFor": "One technical owner who wants a self-hosted assistant over Gmail, Calendar, Slack and Telegram with credentials kept out of the model's reach.", "slug": "ironclaw", "watchFor": "Global auto-approve defaults to on in the 1.4.1 source, so tools marked ask (send, trash, delete) run without a prompt. Only financial, approval and budget effects always ask" } ], "job": { "capability": "assistant.proactive", "name": "Assistant proactive" }, "others": [ { "json": "https://www.anchorterminal.com/compare/astrbot-vs-cowagent.json", "title": "AstrBot vs CowAgent", "url": "https://www.anchorterminal.com/compare/astrbot-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/astrbot-vs-ironclaw.json", "title": "AstrBot vs IronClaw", "url": "https://www.anchorterminal.com/compare/astrbot-vs-ironclaw" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-gaia.json", "title": "CowAgent vs GAIA", "url": "https://www.anchorterminal.com/compare/cowagent-vs-gaia" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark.json", "title": "CowAgent vs Gemini Spark", "url": "https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-grok-bot.json", "title": "CowAgent vs Grok Bot", "url": "https://www.anchorterminal.com/compare/cowagent-vs-grok-bot" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-haven.json", "title": "CowAgent vs Haven", "url": "https://www.anchorterminal.com/compare/cowagent-vs-haven" }, { "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-instinct.json", "title": "CowAgent vs Instinct", "url": "https://www.anchorterminal.com/compare/cowagent-vs-instinct" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-leon.json", "title": "CowAgent vs Leon", "url": "https://www.anchorterminal.com/compare/cowagent-vs-leon" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-lindy.json", "title": "CowAgent vs Lindy", "url": "https://www.anchorterminal.com/compare/cowagent-vs-lindy" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-nanobot.json", "title": "CowAgent vs nanobot", "url": "https://www.anchorterminal.com/compare/cowagent-vs-nanobot" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-nanoclaw.json", "title": "CowAgent vs NanoClaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-nanoclaw" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-openai-dots.json", "title": "CowAgent vs Dots", "url": "https://www.anchorterminal.com/compare/cowagent-vs-openai-dots" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-openclaw.json", "title": "CowAgent vs OpenClaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-openclaw" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-picoclaw.json", "title": "CowAgent vs PicoClaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-picoclaw" }, { "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/cowagent-vs-qwenpaw.json", "title": "CowAgent vs QwenPaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-zeroclaw.json", "title": "CowAgent vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-zo-computer.json", "title": "CowAgent vs Zo Computer", "url": "https://www.anchorterminal.com/compare/cowagent-vs-zo-computer" }, { "json": "https://www.anchorterminal.com/compare/gaia-vs-ironclaw.json", "title": "GAIA vs IronClaw", "url": "https://www.anchorterminal.com/compare/gaia-vs-ironclaw" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-ironclaw.json", "title": "Gemini Spark vs IronClaw", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-ironclaw" }, { "json": "https://www.anchorterminal.com/compare/grok-bot-vs-ironclaw.json", "title": "Grok Bot vs IronClaw", "url": "https://www.anchorterminal.com/compare/grok-bot-vs-ironclaw" }, { "json": "https://www.anchorterminal.com/compare/haven-vs-ironclaw.json", "title": "Haven vs IronClaw", "url": "https://www.anchorterminal.com/compare/haven-vs-ironclaw" }, { "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/instinct-vs-ironclaw.json", "title": "Instinct vs IronClaw", "url": "https://www.anchorterminal.com/compare/instinct-vs-ironclaw" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-leon.json", "title": "IronClaw vs Leon", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-leon" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-lindy.json", "title": "IronClaw vs Lindy", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-lindy" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-nanobot.json", "title": "IronClaw vs nanobot", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-nanobot" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-nanoclaw.json", "title": "IronClaw vs NanoClaw", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-nanoclaw" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-openai-dots.json", "title": "IronClaw vs Dots", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-openai-dots" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-openclaw.json", "title": "IronClaw vs OpenClaw", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-openclaw" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-picoclaw.json", "title": "IronClaw vs PicoClaw", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-picoclaw" }, { "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/ironclaw-vs-qwenpaw.json", "title": "IronClaw vs QwenPaw", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-zeroclaw.json", "title": "IronClaw vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-zo-computer.json", "title": "IronClaw vs Zo Computer", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-zo-computer" } ], "scores": [ { "by": 17, "cowagent": 84, "edge": "cowagent", "ironclaw": 67, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 7, "cowagent": 67, "edge": "ironclaw", "ironclaw": 74, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 10, "cowagent": 59, "edge": "ironclaw", "ironclaw": 69, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 23, "cowagent": 43, "edge": "ironclaw", "ironclaw": 66, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "cowagent": 60, "edge": "", "ironclaw": 60, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 9, "cowagent": 83, "edge": "cowagent", "ironclaw": 74, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 30, "cowagent": 45, "edge": "ironclaw", "ironclaw": 75, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "IronClaw scores 66.7 (B) on agent readiness against CowAgent's 58.5 (C), and leads in 4 of 7 scored categories. CowAgent leads on reliability and maintenance \u0026 community. Both do assistant proactive.", "verdicts": { "cowagent": "MIT software with seven releases in 90 days, memory kept as plain files in the owner's workspace and three per-session permission modes. Source and Docker installs default to full-access, no action asks for approval, and an open report of 31 July 2026 says group members could reach the owner's files through the bot.", "ironclaw": "Credentials stay in an encrypted store and are injected at the host boundary, and extensions declare per-tool permissions, network targets and OAuth scopes. The global auto-approve setting defaults to on in the 1.4.1 source, so tools marked ask, such as `gmail.send_message`, run unprompted until the owner turns it off." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cowagent-vs-ironclaw", "json": "https://www.anchorterminal.com/compare/cowagent-vs-ironclaw.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cowagent-vs-ironclaw.md", "slim": "https://www.anchorterminal.com/compare/cowagent-vs-ironclaw.min.md" }, "markdown": "IronClaw scores 66.7 (B) on agent readiness against CowAgent's 58.5 (C), and leads in 4 of 7 scored categories. CowAgent leads on reliability and maintenance \u0026 community. Both do assistant proactive.\n\n- CowAgent: grade C, 58.5/100, rank #591 of 986. Markdown https://www.anchorterminal.com/tools/cowagent.md · JSON https://www.anchorterminal.com/api/v1/tools/cowagent.json\n- IronClaw: grade B, 66.7/100, rank #288 of 986. Markdown https://www.anchorterminal.com/tools/ironclaw.md · JSON https://www.anchorterminal.com/api/v1/tools/ironclaw.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### CowAgent (C)\n\nGood for: One technical owner who wants an assistant on WeChat, Feishu, DingTalk, Telegram, Slack or Discord with memory in local files and a choice of Chinese and Western model providers.\n\nAhead on:\n- Reliability, 84 against 67\n- Maintenance \u0026 community, 83 against 74\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: Source and Docker installs default to full-access, and no mode asks the owner before a shell command, a file send or an MCP call\n\n### IronClaw (B)\n\nGood for: One technical owner who wants a self-hosted assistant over Gmail, Calendar, Slack and Telegram with credentials kept out of the model's reach.\n\nAhead on:\n- Schema \u0026 documentation, 74 against 67\n- Agent ergonomics, 69 against 59\n- Security \u0026 auth, 66 against 43\n- Transparency \u0026 trust, 75 against 45\n\nWatch for: Global auto-approve defaults to on in the 1.4.1 source, so tools marked ask (send, trash, delete) run without a prompt. Only financial, approval and budget effects always ask\n\n\n## Score by category\n\n| Category | Weight | CowAgent | IronClaw | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 84 | 67 | CowAgent +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 67 | 74 | IronClaw +7 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 69 | IronClaw +10 |\n| Security \u0026 auth | 14% (17.5 this run) | 43 | 66 | IronClaw +23 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 74 | CowAgent +9 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 45 | 75 | IronClaw +30 |\n| Negative events | ≤15 | -5 | -2 | |\n| **Total** | | **58.5 · C** | **66.7 · B** | |\n\n## Facts side by side\n\n| Fact | CowAgent | IronClaw |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | zhayujie | NEAR AI |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | MIT OR Apache-2.0 |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-30 | 2026-09-29 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no date given |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | 47k stars | 13k stars |\n\n## Verdicts\n\n**CowAgent.** MIT software with seven releases in 90 days, memory kept as plain files in the owner's workspace and three per-session permission modes. Source and Docker installs default to full-access, no action asks for approval, and an open report of 31 July 2026 says group members could reach the owner's files through the bot.\n\n**IronClaw.** Credentials stay in an encrypted store and are injected at the host boundary, and extensions declare per-tool permissions, network targets and OAuth scopes. The global auto-approve setting defaults to on in the 1.4.1 source, so tools marked ask, such as `gmail.send_message`, run unprompted until the owner turns it off.\n\n## Before you call either\n\n### CowAgent\n\n1. Set `agent_permission_mode` to `workspace-write` or `read-only` before connecting any channel. Source and Docker installs default to `full-access`\n2. Keep the bot out of group chats that include other people. Any member who mentions it reaches the same tools as the owner\n3. Set `web_password` before changing `web_host` to `0.0.0.0`. The password is empty by default\n4. Set `external_api_token` to enable `POST /v1/chat/completions`, and send `conversation_id` to keep one session. The `model` field does not select a model\n5. Run it in a container for a hard boundary. The docs and the source both say the permission modes are not isolation\n\n### IronClaw\n\n1. Open Settings and turn off global auto-approve, or set send and delete tools to ask each time, before connecting mail or chat accounts\n2. Install with the release installer and run `ironclaw onboard`. 1.x does not migrate 0.29 data, so use a fresh home directory\n3. Call `POST /api/v1/responses` with the bearer token from `~/.ironclaw/reborn/webui-token`. Keep under 30 requests in 60 seconds\n4. Resolve approval and OAuth gates in the web interface. The Responses API fails the turn instead of surfacing them\n5. Connect MCP servers over HTTP only. The stdio transport is rejected\n\n## Questions\n\n### Which is better for AI agents, CowAgent or IronClaw?\n\nIronClaw scores 66.7 (B) on agent readiness against CowAgent's 58.5 (C), and leads in 4 of 7 scored categories. CowAgent leads on reliability and maintenance \u0026 community.\n\n### Are CowAgent and IronClaw open source?\n\nYes. CowAgent is open source (MIT). IronClaw is open source (MIT OR Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cowagent-vs-ironclaw.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cowagent-vs-ironclaw.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cowagent\", \"b\": \"ironclaw\"}`. From a terminal: `anchor compare cowagent ironclaw`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cowagent.json and https://www.anchorterminal.com/api/v1/tools/ironclaw.json\n\n## Other comparisons with CowAgent or IronClaw\n\n- [AstrBot vs CowAgent](https://www.anchorterminal.com/compare/astrbot-vs-cowagent.md)\n- [AstrBot vs IronClaw](https://www.anchorterminal.com/compare/astrbot-vs-ironclaw.md)\n- [CowAgent vs GAIA](https://www.anchorterminal.com/compare/cowagent-vs-gaia.md)\n- [CowAgent vs Gemini Spark](https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark.md)\n- [CowAgent vs Grok Bot](https://www.anchorterminal.com/compare/cowagent-vs-grok-bot.md)\n- [CowAgent vs Haven](https://www.anchorterminal.com/compare/cowagent-vs-haven.md)\n- [CowAgent vs Hermes Agent](https://www.anchorterminal.com/compare/cowagent-vs-hermes-agent.md)\n- [CowAgent vs Instinct](https://www.anchorterminal.com/compare/cowagent-vs-instinct.md)\n- [CowAgent vs Leon](https://www.anchorterminal.com/compare/cowagent-vs-leon.md)\n- [CowAgent vs Lindy](https://www.anchorterminal.com/compare/cowagent-vs-lindy.md)\n- [CowAgent vs nanobot](https://www.anchorterminal.com/compare/cowagent-vs-nanobot.md)\n- [CowAgent vs NanoClaw](https://www.anchorterminal.com/compare/cowagent-vs-nanoclaw.md)\n- [CowAgent vs Dots](https://www.anchorterminal.com/compare/cowagent-vs-openai-dots.md)\n- [CowAgent vs OpenClaw](https://www.anchorterminal.com/compare/cowagent-vs-openclaw.md)\n- [CowAgent vs PicoClaw](https://www.anchorterminal.com/compare/cowagent-vs-picoclaw.md)\n- [CowAgent vs Poke](https://www.anchorterminal.com/compare/cowagent-vs-poke.md)\n- [CowAgent vs QwenPaw](https://www.anchorterminal.com/compare/cowagent-vs-qwenpaw.md)\n- [CowAgent vs ZeroClaw](https://www.anchorterminal.com/compare/cowagent-vs-zeroclaw.md)\n- [CowAgent vs Zo Computer](https://www.anchorterminal.com/compare/cowagent-vs-zo-computer.md)\n- [GAIA vs IronClaw](https://www.anchorterminal.com/compare/gaia-vs-ironclaw.md)\n- [Gemini Spark vs IronClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-ironclaw.md)\n- [Grok Bot vs IronClaw](https://www.anchorterminal.com/compare/grok-bot-vs-ironclaw.md)\n- [Haven vs IronClaw](https://www.anchorterminal.com/compare/haven-vs-ironclaw.md)\n- [Hermes Agent vs IronClaw](https://www.anchorterminal.com/compare/hermes-agent-vs-ironclaw.md)\n- [Instinct vs IronClaw](https://www.anchorterminal.com/compare/instinct-vs-ironclaw.md)\n- [IronClaw vs Leon](https://www.anchorterminal.com/compare/ironclaw-vs-leon.md)\n- [IronClaw vs Lindy](https://www.anchorterminal.com/compare/ironclaw-vs-lindy.md)\n- [IronClaw vs nanobot](https://www.anchorterminal.com/compare/ironclaw-vs-nanobot.md)\n- [IronClaw vs NanoClaw](https://www.anchorterminal.com/compare/ironclaw-vs-nanoclaw.md)\n- [IronClaw vs Dots](https://www.anchorterminal.com/compare/ironclaw-vs-openai-dots.md)\n- [IronClaw vs OpenClaw](https://www.anchorterminal.com/compare/ironclaw-vs-openclaw.md)\n- [IronClaw vs PicoClaw](https://www.anchorterminal.com/compare/ironclaw-vs-picoclaw.md)\n- [IronClaw vs Poke](https://www.anchorterminal.com/compare/ironclaw-vs-poke.md)\n- [IronClaw vs QwenPaw](https://www.anchorterminal.com/compare/ironclaw-vs-qwenpaw.md)\n- [IronClaw vs ZeroClaw](https://www.anchorterminal.com/compare/ironclaw-vs-zeroclaw.md)\n- [IronClaw vs Zo Computer](https://www.anchorterminal.com/compare/ironclaw-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": "CowAgent vs IronClaw", "url": "" } ], "description": "IronClaw scores 66.7 (B) to CowAgent's 58.5 (C) for assistant proactive. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "CowAgent C 58.5", "IronClaw B 66.7", "scores" ], "h1": "CowAgent vs IronClaw", "image": "https://www.anchorterminal.com/assets/og/compare-cowagent-vs-ironclaw.png", "path": "/compare/cowagent-vs-ironclaw", "published": "2026-10-01", "section": "tools", "title": "CowAgent vs IronClaw for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/cowagent-vs-ironclaw" }, "tokens": { "markdown": 2550, "slim": 530 }, "version": 1 }