{ "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": "CowAgent scores 58.5 (C) on agent readiness against Gemini Spark's 24.5 (F), and leads in 5 of 7 scored categories. Gemini Spark leads on security \u0026 auth.", "b": { "slug": "gemini-spark", "name": "Gemini Spark", "vendor": "Google LLC", "vendorUrl": "https://gemini.google/us/overview/agent/spark/", "kind": "platform", "category": "personal-assistants", "summary": "Gemini Spark is Google's hosted personal AI agent inside the Gemini app. It runs tasks and schedules in Google's cloud across Gmail, Calendar, Drive and other connected apps for Google AI Pro and Ultra subscribers.", "url": "https://www.anchorterminal.com/tools/gemini-spark", "markdownUrl": "https://www.anchorterminal.com/tools/gemini-spark.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-spark.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-spark.json", "license": "Proprietary hosted service under the Google Terms of Service", "transports": [], "packages": [], "auth": "oauth", "authNotes": "No credential for an outside agent exists, because no public API was found. A person signs in to the Gemini app with a personal Google Account and needs a Google AI Pro or Ultra subscription (https://support.google.com/gemini/answer/17094507). Connected apps are off by default and are switched on in settings (https://gemini.google/us/overview/agent/spark/). Third-party and custom apps are linked to the Google Account and can be unlinked in Connected Apps settings or on the account's Linked apps page. A custom MCP server that lacks Dynamic Client Registration takes credentials the user enters (https://support.google.com/gemini/answer/17209137). Google tells users not to type sign-in or payment details into a task thread and to enter them on the web page in take control mode (https://support.google.com/gemini/answer/17094507).", "pricing": "paid", "pricingNotes": "Spark needs a Google AI Pro or Ultra subscription. US prices are $19.99 a month for Pro and $99.99 or $199.99 a month for Ultra, with Spark use counted against compute-based limits that refresh every five hours up to a weekly limit (https://gemini.google/us/subscriptions/; https://support.google.com/gemini/answer/16275805). The subscriptions page lists Spark under Ultra as first access in select countries, while the help page names Pro and Ultra. No free tier includes Spark. The page links a two-month trial offer whose terms were not read (checked 2026-10-12).", "priceSummary": "$19.99 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the pages read, and no public API to carry one (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://support.google.com/gemini/answer/17094507", "capabilities": [ "assistant.proactive", "assistant.accounts", "assistant.memory", "agent.mcp-client" ], "tags": [ "hosted", "consumer", "closed-source", "no-api", "beta", "ios", "android", "macos", "web", "browser-agent", "approvals", "mcp-client", "subscription", "trains-on-data-by-default" ], "lastRelease": "2026-05-19", "graded": true, "anchor": { "graded": true, "score": 24.5, "grade": "F", "agentReady": false, "rank": 974, "ranked": true, "rankOf": 986, "categoryRank": 18, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 9, "maintenance": 17, "payments": 10, "reliability": 14, "schema": 17, "security": 60, "transparency": 49 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": 0, "verdict": "Google's help pages state what Spark confirms before doing, how to delete its remote browser and code data, and the risks of prompt injection. Spark has no public API, Google calls it experimental, and it runs only with Keep Activity on, the setting under which chats are used for model training and human review.", "bestFor": "A person who already keeps mail, calendar and files in a personal Google Account and accepts Keep Activity being on.", "strengths": [ "Google says Spark asks for confirmation before sending communications, modifying data, making purchases, submitting web forms and using Sign in with Google", "Connected apps are off by default, and write actions through a custom MCP server need manual confirmation, per Google's help pages", "The help page names prompt injection, gives four examples of what an injected instruction could do, and says the safeguards do not guarantee protection", "Each task thread has a work panel listing completed and planned steps, files read or updated, schedules, and the skills and apps used", "Published limits of 15 running tasks and 50 active schedules, and plan prices of $19.99 to $199.99 a month in the US" ], "weaknesses": [ "No public API, SDK or MCP server for an outside agent was found. Spark is reached in the Gemini mobile app, the Mac app and gemini.google.com", "Google's help page calls Spark an experimental feature in early development, and the Privacy Hub calls it beta", "Spark runs only with Keep Activity on. With that setting on, Google uses activity to train generative AI models and human reviewers read some chats", "Chats already reviewed by human reviewers are kept for up to three years and are not deleted when the user deletes activity", "Google states that Gemini can perform bulk actions on private Google Tasks without confirmation", "The remote browser saves cookies holding website sign-in details for later sessions until the user deletes them or turns Spark off", "No status page or SLA for Spark was linked from the pages read, and the bug bounty site linked from Google's terms is drawn by script and was unread" ], "agentNotes": [ "Do not plan an integration against Spark. No public API or MCP server was found, and a person must hold a Google AI Pro or Ultra subscription", "Expect a confirmation request before sends, edits, purchases and web form submissions, and note that bulk changes to private Google Tasks run without one", "Delete remote browser data and remote code execution data in Gemini Spark Settings after a sensitive session. Deleting a task thread or Gemini Apps activity does not remove them", "Keep within 15 running tasks and 50 active schedules. A schedule does not run when 15 tasks are running or the usage limit is reached", "Treat every safety statement here as Google's own description. None was tested, and no message was sent to the service" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 24.5 } ], "editorialScores": { "ergonomics": 9, "maintenance": 17, "payments": 10, "reliability": 14, "schema": 17, "security": 60, "transparency": 44 }, "provenanceScore": 54 }, "letme": { "capability": "https://letme.dev/assistant.proactive", "tool": "https://letme.dev/gemini-spark" }, "area": "frameworks", "unitPrices": [ { "item": "Google AI Pro", "unit": "month", "usd": 19.99, "note": "US price, includes Spark with 4 times the standard usage limit" }, { "item": "Google AI Ultra (5x)", "unit": "month", "usd": 99.99, "note": "US price, 5 times the Pro usage limit" }, { "item": "Google AI Ultra (20x)", "unit": "month", "usd": 199.99, "note": "US price, 20 times the Pro usage limit" } ], "provenance": { "legalEntity": "Google LLC", "domain": "gemini.google", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://policies.google.com/terms", "privacy": "https://support.google.com/gemini/answer/13594961", "statusPage": "", "changelog": "https://gemini.google/us/release-notes/", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The Gemini Apps Privacy Notice says Gemini Apps are supplied by Google Ireland Limited in the European Economic Area and Switzerland and by Google LLC everywhere else. Spark is not available in the European Economic Area or Switzerland.", "Google's service-specific terms page lists Gemini Apps under the Google Terms of Service (effective 30 July 2026), the Generative AI Prohibited Use Policy and the Gemini Apps Agentic Calling Additional Terms of Service. The Generative AI Additional Terms of Service that the subscriptions page links say they stopped applying on 22 May 2024.", "The privacy link is the Gemini Apps Privacy Hub, which holds the Gemini Apps Privacy Notice (last updated 29 June 2026) and the Spark data questions (hub last updated 24 September 2026). The notice supplements the Google Privacy Policy at policies.google.com/privacy (effective 12 October 2026).", "No status page for Gemini Apps or Spark was linked from any page read.", "The release notes are the Gemini app's. Their only entry about Spark is dated 19 May 2026.", "gemini.google/.well-known/security.txt answered 404. Google's terms link bughunters.google.com as its safety and bug testing programmes. That site's home page is drawn by script and was unread.", "gemini.google is a name under Google's own .google top-level domain. Its registration date was not looked up.", "policies.google.com/robots.txt answered 404, read as no rules. The robots.txt files of gemini.google, support.google.com and bughunters.google.com allow the pages read." ], "score": 54 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-spark.json" }, "facts": [ { "a": "Agent harness", "b": "Platform", "name": "Kind" }, { "a": "zhayujie", "b": "Google LLC", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth", "name": "Auth" }, { "a": "Free", "b": "Paid", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary hosted service under the Google Terms of Service", "name": "Licence" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-09-30", "b": "2026-05-19", "name": "Last release" }, { "a": "no document linked", "b": "2026-07-30", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-09-24", "name": "Privacy policy last updated" }, { "a": "", "b": "yes, with an opt-out", "name": "Customer content may train models" }, { "a": "", "b": "yes", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "47k stars", "b": "none", "name": "Popularity" } ], "faq": [ { "answer": "CowAgent scores 58.5 (C) on agent readiness against Gemini Spark's 24.5 (F), and leads in 5 of 7 scored categories. Gemini Spark leads on security \u0026 auth.", "question": "Which is better for AI agents, CowAgent or Gemini Spark?" }, { "answer": "CowAgent is open source (MIT). No open-source release is listed for Gemini Spark.", "question": "Are CowAgent and Gemini Spark open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 84 against 14", "Schema \u0026 documentation, 67 against 17", "Agent ergonomics, 59 against 9", "Payments \u0026 pricing, 60 against 10", "Maintenance \u0026 community, 83 against 17" ], "also": [ "Free to start without a card", "Open source" ], "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": [ "Security \u0026 auth, 60 against 43" ], "also": [ "No incidents deducted, where CowAgent loses 5 points for them" ], "goodFor": "A person who already keeps mail, calendar and files in a personal Google Account and accepts Keep Activity being on.", "slug": "gemini-spark", "watchFor": "No public API, SDK or MCP server for an outside agent was found. Spark is reached in the Gemini mobile app, the Mac app and gemini.google.com" } ], "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-gemini-spark.json", "title": "AstrBot vs Gemini Spark", "url": "https://www.anchorterminal.com/compare/astrbot-vs-gemini-spark" }, { "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-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-ironclaw.json", "title": "CowAgent vs IronClaw", "url": "https://www.anchorterminal.com/compare/cowagent-vs-ironclaw" }, { "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-gemini-spark.json", "title": "GAIA vs Gemini Spark", "url": "https://www.anchorterminal.com/compare/gaia-vs-gemini-spark" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-grok-bot.json", "title": "Gemini Spark vs Grok Bot", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-grok-bot" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-haven.json", "title": "Gemini Spark vs Haven", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-haven" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-hermes-agent.json", "title": "Gemini Spark vs Hermes Agent", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-hermes-agent" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-instinct.json", "title": "Gemini Spark vs Instinct", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-instinct" }, { "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/gemini-spark-vs-leon.json", "title": "Gemini Spark vs Leon", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-leon" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-lindy.json", "title": "Gemini Spark vs Lindy", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-lindy" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-nanobot.json", "title": "Gemini Spark vs nanobot", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-nanobot" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-nanoclaw.json", "title": "Gemini Spark vs NanoClaw", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-nanoclaw" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-openai-dots.json", "title": "Gemini Spark vs Dots", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-openai-dots" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-openclaw.json", "title": "Gemini Spark vs OpenClaw", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-openclaw" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-picoclaw.json", "title": "Gemini Spark vs PicoClaw", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-picoclaw" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-poke.json", "title": "Gemini Spark vs Poke", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw.json", "title": "Gemini Spark vs QwenPaw", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-zeroclaw.json", "title": "Gemini Spark vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-zo-computer.json", "title": "Gemini Spark vs Zo Computer", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-zo-computer" } ], "scores": [ { "by": 70, "cowagent": 84, "edge": "cowagent", "gemini-spark": 14, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 50, "cowagent": 67, "edge": "cowagent", "gemini-spark": 17, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 50, "cowagent": 59, "edge": "cowagent", "gemini-spark": 9, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 17, "cowagent": 43, "edge": "gemini-spark", "gemini-spark": 60, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 50, "cowagent": 60, "edge": "cowagent", "gemini-spark": 10, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 66, "cowagent": 83, "edge": "cowagent", "gemini-spark": 17, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 4, "cowagent": 45, "edge": "gemini-spark", "gemini-spark": 49, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "CowAgent scores 58.5 (C) on agent readiness against Gemini Spark's 24.5 (F), and leads in 5 of 7 scored categories. Gemini Spark leads on security \u0026 auth. 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.", "gemini-spark": "Google's help pages state what Spark confirms before doing, how to delete its remote browser and code data, and the risks of prompt injection. Spark has no public API, Google calls it experimental, and it runs only with Keep Activity on, the setting under which chats are used for model training and human review." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark", "json": "https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark.md", "slim": "https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark.min.md" }, "markdown": "CowAgent scores 58.5 (C) on agent readiness against Gemini Spark's 24.5 (F), and leads in 5 of 7 scored categories. Gemini Spark leads on security \u0026 auth. 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- Gemini Spark: grade F, 24.5/100, rank #974 of 986. Markdown https://www.anchorterminal.com/tools/gemini-spark.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-spark.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 14\n- Schema \u0026 documentation, 67 against 17\n- Agent ergonomics, 59 against 9\n- Payments \u0026 pricing, 60 against 10\n- Maintenance \u0026 community, 83 against 17\n\nAlso in its favour:\n- Free to start without a card\n- Open source\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### Gemini Spark (F)\n\nGood for: A person who already keeps mail, calendar and files in a personal Google Account and accepts Keep Activity being on.\n\nAhead on:\n- Security \u0026 auth, 60 against 43\n\nAlso in its favour:\n- No incidents deducted, where CowAgent loses 5 points for them\n\nWatch for: No public API, SDK or MCP server for an outside agent was found. Spark is reached in the Gemini mobile app, the Mac app and gemini.google.com\n\n\n## Score by category\n\n| Category | Weight | CowAgent | Gemini Spark | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 84 | 14 | CowAgent +70 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 67 | 17 | CowAgent +50 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 9 | CowAgent +50 |\n| Security \u0026 auth | 14% (17.5 this run) | 43 | 60 | Gemini Spark +17 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 10 | CowAgent +50 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 17 | CowAgent +66 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 45 | 49 | Gemini Spark +4 |\n| Negative events | ≤15 | -5 | 0 | |\n| **Total** | | **58.5 · C** | **24.5 · F** | |\n\n## Facts side by side\n\n| Fact | CowAgent | Gemini Spark |\n| --- | --- | --- |\n| Kind | Agent harness | Platform |\n| Vendor | zhayujie | Google LLC |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | |\n| Auth | OAuth or key | OAuth |\n| Pricing | Free | Paid |\n| x402 | no | no |\n| Licence | MIT | Proprietary hosted service under the Google Terms of Service |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | no |\n| Last release | 2026-09-30 | 2026-05-19 |\n| Terms last updated | no document linked | 2026-07-30 |\n| Privacy policy last updated | no document linked | 2026-09-24 |\n| Customer content may train models | | yes, with an opt-out |\n| Terms restrict automated access | | yes |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | not found in the text |\n| Popularity | 47k stars | none |\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**Gemini Spark.** Google's help pages state what Spark confirms before doing, how to delete its remote browser and code data, and the risks of prompt injection. Spark has no public API, Google calls it experimental, and it runs only with Keep Activity on, the setting under which chats are used for model training and human review.\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### Gemini Spark\n\n1. Do not plan an integration against Spark. No public API or MCP server was found, and a person must hold a Google AI Pro or Ultra subscription\n2. Expect a confirmation request before sends, edits, purchases and web form submissions, and note that bulk changes to private Google Tasks run without one\n3. Delete remote browser data and remote code execution data in Gemini Spark Settings after a sensitive session. Deleting a task thread or Gemini Apps activity does not remove them\n4. Keep within 15 running tasks and 50 active schedules. A schedule does not run when 15 tasks are running or the usage limit is reached\n5. Treat every safety statement here as Google's own description. None was tested, and no message was sent to the service\n\n## Questions\n\n### Which is better for AI agents, CowAgent or Gemini Spark?\n\nCowAgent scores 58.5 (C) on agent readiness against Gemini Spark's 24.5 (F), and leads in 5 of 7 scored categories. Gemini Spark leads on security \u0026 auth.\n\n### Are CowAgent and Gemini Spark open source?\n\nCowAgent is open source (MIT). No open-source release is listed for Gemini Spark.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cowagent\", \"b\": \"gemini-spark\"}`. From a terminal: `anchor compare cowagent gemini-spark`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cowagent.json and https://www.anchorterminal.com/api/v1/tools/gemini-spark.json\n\n## Other comparisons with CowAgent or Gemini Spark\n\n- [AstrBot vs CowAgent](https://www.anchorterminal.com/compare/astrbot-vs-cowagent.md)\n- [AstrBot vs Gemini Spark](https://www.anchorterminal.com/compare/astrbot-vs-gemini-spark.md)\n- [CowAgent vs GAIA](https://www.anchorterminal.com/compare/cowagent-vs-gaia.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 IronClaw](https://www.anchorterminal.com/compare/cowagent-vs-ironclaw.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 Gemini Spark](https://www.anchorterminal.com/compare/gaia-vs-gemini-spark.md)\n- [Gemini Spark vs Grok Bot](https://www.anchorterminal.com/compare/gemini-spark-vs-grok-bot.md)\n- [Gemini Spark vs Haven](https://www.anchorterminal.com/compare/gemini-spark-vs-haven.md)\n- [Gemini Spark vs Hermes Agent](https://www.anchorterminal.com/compare/gemini-spark-vs-hermes-agent.md)\n- [Gemini Spark vs Instinct](https://www.anchorterminal.com/compare/gemini-spark-vs-instinct.md)\n- [Gemini Spark vs IronClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-ironclaw.md)\n- [Gemini Spark vs Leon](https://www.anchorterminal.com/compare/gemini-spark-vs-leon.md)\n- [Gemini Spark vs Lindy](https://www.anchorterminal.com/compare/gemini-spark-vs-lindy.md)\n- [Gemini Spark vs nanobot](https://www.anchorterminal.com/compare/gemini-spark-vs-nanobot.md)\n- [Gemini Spark vs NanoClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-nanoclaw.md)\n- [Gemini Spark vs Dots](https://www.anchorterminal.com/compare/gemini-spark-vs-openai-dots.md)\n- [Gemini Spark vs OpenClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-openclaw.md)\n- [Gemini Spark vs PicoClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-picoclaw.md)\n- [Gemini Spark vs Poke](https://www.anchorterminal.com/compare/gemini-spark-vs-poke.md)\n- [Gemini Spark vs QwenPaw](https://www.anchorterminal.com/compare/gemini-spark-vs-qwenpaw.md)\n- [Gemini Spark vs ZeroClaw](https://www.anchorterminal.com/compare/gemini-spark-vs-zeroclaw.md)\n- [Gemini Spark vs Zo Computer](https://www.anchorterminal.com/compare/gemini-spark-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 Gemini Spark", "url": "" } ], "description": "CowAgent scores 58.5 (C) to Gemini Spark's 24.5 (F) for assistant proactive. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "CowAgent C 58.5", "Gemini Spark F 24.5", "scores" ], "h1": "CowAgent vs Gemini Spark", "image": "https://www.anchorterminal.com/assets/og/compare-cowagent-vs-gemini-spark.png", "path": "/compare/cowagent-vs-gemini-spark", "published": "2026-10-01", "section": "tools", "title": "CowAgent vs Gemini Spark for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/cowagent-vs-gemini-spark" }, "tokens": { "markdown": 2700, "slim": 680 }, "version": 1 }