{ "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": 58.7, "grade": "C", "agentReady": false, "rank": 671, "ranked": true, "rankOf": 1239, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 83, "payments": 60, "reliability": 84, "schema": 67, "security": 43, "transparency": 47 }, "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": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.7 } ], "editorialScores": { "ergonomics": 59, "maintenance": 83, "payments": 60, "reliability": 84, "schema": 67, "security": 43, "transparency": 62 }, "provenanceScore": 31, "checked": { "categories": { "ergonomics": "2026-10-12", "maintenance": "2026-10-12", "payments": "2026-10-12", "reliability": "2026-10-12", "schema": "2026-10-12", "security": "2026-10-12", "transparency": "2026-10-12" }, "last": "2026-10-12", "lastMoved": "2026-10-27", "oldest": "2026-10-12", "stale": false, "staleAfterDays": 90 } }, "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": 31 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cowagent.json", "live": { "slug": "cowagent", "versions": [ { "registry": "github", "name": "zhayujie/CowAgent", "version": "2.2.2", "released": "2026-10-30", "seenAt": "2026-10-30T14:06:42.172567293Z" } ], "githubStars": 47692, "securityTxt": { "url": "https://cowagent.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-30T15:39:33.738494769Z" }, "llmsTxt": { "url": "https://docs.cowagent.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-30T15:07:12.455980932Z" }, "domain": { "domain": "cowagent.ai", "registered": "2026-02-06", "source": "https://rdap.identitydigital.services/rdap/domain/cowagent.ai", "checkedAt": "2026-10-25T13:49:06.264453079Z" }, "pages": [ { "url": "https://docs.cowagent.ai/releases/overview", "kind": "changelog", "status": 200, "checkedAt": "2026-10-30T05:36:59.264972446Z", "changedAt": "2026-10-30T05:36:59.264972446Z", "fingerprint": "5ba7778e728e" } ], "github": { "repo": "zhayujie/cowagent", "checkedAt": "2026-10-26T08:20:10.101686627Z", "stars": 47600, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-25T02:44:27Z", "openIssues": 15, "openPRs": 29, "issuesOpened90d": 135, "issuesClosed90d": 138, "prsMerged90d": 593, "ci": { "branch": "master", "runs": 50, "success": 46, "failure": 4, "other": 0, "latest": "success", "latestAt": "2026-10-25T02:51:00Z" }, "advisories": [ { "ghsa": "GHSA-qwjc-xv6c-mqfx", "severity": "medium", "published": "2025-11-28T03:49:52Z" } ], "replies": { "sampled": 25, "unanswered": 2, "medianDays": 1.1 } }, "updatedAt": "2026-10-30T15:39:33.738494769Z" } }, "answer": "LearnHarness and CowAgent score within a point of each other on agent readiness, 59.3 (C) and 58.7 (C). CowAgent leads on reliability and maintenance \u0026 community.", "b": { "slug": "learnharness", "name": "LearnHarness", "vendor": "Amos Blomqvist", "vendorUrl": "https://learnharness.ai", "kind": "harness", "category": "personal-assistants", "summary": "LearnHarness is an open-source desktop app for macOS, Windows and Linux that tests what a learner already understands, plans a route to a goal, teaches step by step and keeps a local knowledge graph, using the learner's own model keys.", "url": "https://www.anchorterminal.com/tools/learnharness", "markdownUrl": "https://www.anchorterminal.com/tools/learnharness.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/learnharness.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/learnharness.json", "repo": "https://github.com/amosblomqvist/learnharness", "license": "AGPL-3.0-only", "transports": [], "packages": [], "auth": "none", "authNotes": "No LearnHarness account. The learner adds keys for model providers (OpenAI, Anthropic, Google, DeepSeek, OpenRouter and others), or one OpenAI-compatible endpoint, or signs in with ChatGPT, GitHub Copilot or Grok, or connects an installed Claude Code CLI. Deepgram (dictation) and Tavily or Brave (web search) take separate keys.", "pricing": "free", "pricingNotes": "Free under AGPL-3.0 with nothing to buy. Model usage is billed by the provider the learner configures, or counts against a ChatGPT, Copilot or Grok plan, and the app shows a live cost meter. The README says any future charge would be for convenience such as managed keys or hosting.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the website, the skill or the source files read (checked 2026-10-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4204, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://github.com/amosblomqvist/learnharness/blob/main/docs/development.md", "capabilities": [ "assistant.memory", "assistant.self-hosted", "memory.graph", "memory.read", "web.search" ], "tags": [ "open-source", "local", "free", "no-card", "agpl", "desktop-app", "macos", "windows", "linux", "agent-skill", "typescript", "new" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 59.3, "grade": "C", "agentReady": false, "rank": 648, "ranked": true, "rankOf": 1239, "categoryRank": 9, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 71, "payments": 60, "reliability": 56, "schema": 63, "security": 52, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-30" }, "negative": 0, "verdict": "The in-app agent reads files but cannot change them or run commands, and a bundled skill gives other agents a documented read-only view of sessions and the knowledge graph. The project is 14 days old at 0.4.0, its file reads reach the whole home directory without approval, and it has no security policy.", "bestFor": "A tutor for one learner that keeps a local record of sessions and a graph of propositions and reasoning chains.", "strengths": [ "AGPL-3.0 source, with installers for macOS (signed and notarised), Windows and Linux on GitHub Releases", "A bundled agent skill with Python readers that print sessions and graph data as text or JSON and write nothing", "The in-app agent has no shell, write or send tool, and Claude Code runs with its built-in tools switched off", "The desktop server binds 127.0.0.1 and requires a per-launch 64-character secret header", "Nine releases from 17 to 29 October 2026, with CI running typecheck, tests, lint and three-OS builds on main" ], "weaknesses": [ "The read, ls, find and grep tools resolve against the home directory with no allow list, and their output goes to the model provider", "Provider keys and ChatGPT sign-in credentials are stored as plaintext JSON at mode 0600, not in the OS keychain", "No SECURITY.md, security.txt, privacy policy or terms. learnharness.ai answers 404 for each", "0.x software created on 16 October 2026, with 265 open issues and pull requests and none of the 39 newest pull requests merged", "No outside agent can start or drive a lesson. The local HTTP API is for the app's own window" ], "agentNotes": [ "Use the bundled skill (`skills/learnharness/SKILL.md`) to read a learner's record. It needs Python 3.10 or later and writes nothing", "Pass `--format json` before the subcommand, for example `python3 -B scripts/graph.py --format json propositions`", "Treat stored answer keys and teacher prose as model-authored. A proposition in the graph is not evidence the learner understood it", "Do not read `auth.json`, which sits one folder above the data folder and holds provider keys in plain text", "Close the app or re-read when a stable snapshot matters. The readers do not lock files while the app writes" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.3 } ], "editorialScores": { "ergonomics": 60, "maintenance": 71, "payments": 60, "reliability": 56, "schema": 63, "security": 52, "transparency": 64 }, "provenanceScore": 56, "checked": { "categories": { "ergonomics": "2026-10-30", "maintenance": "2026-10-30", "payments": "2026-10-30", "reliability": "2026-10-30", "schema": "2026-10-30", "security": "2026-10-30", "transparency": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 } }, "letme": { "capability": "https://letme.dev/assistant.memory", "tool": "https://letme.dev/learnharness" }, "area": "frameworks", "provenance": { "legalEntity": "No legal entity found. Copyright Amos Blomqvist", "domain": "learnharness.ai", "domainRegistered": "2026-10-09", "endpointOnVendorDomain": null, "terms": "https://raw.githubusercontent.com/amosblomqvist/learnharness/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "https://github.com/amosblomqvist/learnharness/releases", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "The footer of learnharness.ai reads © 2026 Amos Blomqvist, and `package.json` names Amos Blomqvist as author. No company is named.", "learnharness.ai/privacy, /terms, /llms.txt and /.well-known/security.txt return 404, and the repository has no SECURITY.md, so the AGPL-3.0 licence stands in for terms.", "RDAP (Identity Digital) gives learnharness.ai a registration date of 2026-10-09.", "The app runs on the learner's machine. Its only vendor-side service seen is the website, which a release workflow updates. Updates come from GitHub Releases.", "There is no CHANGELOG file. Each GitHub release carries its notes." ], "score": 56 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/learnharness.json" }, "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "zhayujie", "b": "Amos Blomqvist", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "AGPL-3.0-only", "name": "Licence" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-09-30", "b": "2026-10-29", "name": "Last release" }, { "a": "no document linked", "b": "no date given", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "not found in the text", "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": "4.2k stars", "name": "Popularity" } ], "faq": [ { "answer": "LearnHarness and CowAgent score within a point of each other on agent readiness, 59.3 (C) and 58.7 (C). CowAgent leads on reliability and maintenance \u0026 community.", "question": "Which is better for AI agents, CowAgent or LearnHarness?" }, { "answer": "Yes. CowAgent is open source (MIT). LearnHarness is open source (AGPL-3.0-only).", "question": "Are CowAgent and LearnHarness open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 84 against 56", "Maintenance \u0026 community, 83 against 71" ], "also": null, "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, 52 against 43", "Transparency \u0026 trust, 60 against 47" ], "also": [ "No key needed to call it", "No incidents deducted, where CowAgent loses 5 points for them" ], "goodFor": "A tutor for one learner that keeps a local record of sessions and a graph of propositions and reasoning chains.", "slug": "learnharness", "watchFor": "The read, ls, find and grep tools resolve against the home directory with no allow list, and their output goes to the model provider" } ], "job": { "capability": "assistant.memory", "name": "Assistants that remember you" }, "others": [ { "json": "https://www.anchorterminal.com/compare/asaply-vs-cowagent.json", "title": "asaply vs CowAgent", "url": "https://www.anchorterminal.com/compare/asaply-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/asmi-vs-cowagent.json", "title": "Asmi vs CowAgent", "url": "https://www.anchorterminal.com/compare/asmi-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/boba-vs-cowagent.json", "title": "Boba vs CowAgent", "url": "https://www.anchorterminal.com/compare/boba-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/brea-vs-cowagent.json", "title": "Brea vs CowAgent", "url": "https://www.anchorterminal.com/compare/brea-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-del.json", "title": "CowAgent vs Del", "url": "https://www.anchorterminal.com/compare/cowagent-vs-del" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-hirealpha.json", "title": "CowAgent vs HireAlpha", "url": "https://www.anchorterminal.com/compare/cowagent-vs-hirealpha" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-openinstinct.json", "title": "CowAgent vs OpenInstinct", "url": "https://www.anchorterminal.com/compare/cowagent-vs-openinstinct" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-orbits.json", "title": "CowAgent vs Orbits", "url": "https://www.anchorterminal.com/compare/cowagent-vs-orbits" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-orchid-ai.json", "title": "CowAgent vs Orchid", "url": "https://www.anchorterminal.com/compare/cowagent-vs-orchid-ai" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-szn.json", "title": "CowAgent vs szn", "url": "https://www.anchorterminal.com/compare/cowagent-vs-szn" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-tab-bot.json", "title": "CowAgent vs Tab", "url": "https://www.anchorterminal.com/compare/cowagent-vs-tab-bot" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-zapia.json", "title": "CowAgent vs Zapia", "url": "https://www.anchorterminal.com/compare/cowagent-vs-zapia" }, { "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/boski-vs-cowagent.json", "title": "Boski vs CowAgent", "url": "https://www.anchorterminal.com/compare/boski-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/caddy-app-vs-cowagent.json", "title": "Caddy vs CowAgent", "url": "https://www.anchorterminal.com/compare/caddy-app-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/claude-duet-vs-cowagent.json", "title": "Claude Duet vs CowAgent", "url": "https://www.anchorterminal.com/compare/claude-duet-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-folk-nozomio.json", "title": "CowAgent vs folk", "url": "https://www.anchorterminal.com/compare/cowagent-vs-folk-nozomio" }, { "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-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-lobby-os.json", "title": "CowAgent vs Lobby", "url": "https://www.anchorterminal.com/compare/cowagent-vs-lobby-os" }, { "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-openduet.json", "title": "CowAgent vs OpenDuet", "url": "https://www.anchorterminal.com/compare/cowagent-vs-openduet" }, { "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-tasker-ai.json", "title": "CowAgent vs Tasker AI", "url": "https://www.anchorterminal.com/compare/cowagent-vs-tasker-ai" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-town.json", "title": "CowAgent vs Town", "url": "https://www.anchorterminal.com/compare/cowagent-vs-town" }, { "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/asaply-vs-learnharness.json", "title": "asaply vs LearnHarness", "url": "https://www.anchorterminal.com/compare/asaply-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/asmi-vs-learnharness.json", "title": "Asmi vs LearnHarness", "url": "https://www.anchorterminal.com/compare/asmi-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/atticus-vs-cowagent.json", "title": "Atticus vs CowAgent", "url": "https://www.anchorterminal.com/compare/atticus-vs-cowagent" }, { "json": "https://www.anchorterminal.com/compare/atticus-vs-learnharness.json", "title": "Atticus vs LearnHarness", "url": "https://www.anchorterminal.com/compare/atticus-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/boba-vs-learnharness.json", "title": "Boba vs LearnHarness", "url": "https://www.anchorterminal.com/compare/boba-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/boski-vs-learnharness.json", "title": "Boski vs LearnHarness", "url": "https://www.anchorterminal.com/compare/boski-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/brea-vs-learnharness.json", "title": "Brea vs LearnHarness", "url": "https://www.anchorterminal.com/compare/brea-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/caddy-app-vs-learnharness.json", "title": "Caddy vs LearnHarness", "url": "https://www.anchorterminal.com/compare/caddy-app-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/claude-duet-vs-learnharness.json", "title": "Claude Duet vs LearnHarness", "url": "https://www.anchorterminal.com/compare/claude-duet-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-deeptutor.json", "title": "CowAgent vs DeepTutor", "url": "https://www.anchorterminal.com/compare/cowagent-vs-deeptutor" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-hark-pro.json", "title": "CowAgent vs Hark Pro", "url": "https://www.anchorterminal.com/compare/cowagent-vs-hark-pro" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-talorys.json", "title": "CowAgent vs Talorys", "url": "https://www.anchorterminal.com/compare/cowagent-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/deeptutor-vs-learnharness.json", "title": "DeepTutor vs LearnHarness", "url": "https://www.anchorterminal.com/compare/deeptutor-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/del-vs-learnharness.json", "title": "Del vs LearnHarness", "url": "https://www.anchorterminal.com/compare/del-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/folk-nozomio-vs-learnharness.json", "title": "folk vs LearnHarness", "url": "https://www.anchorterminal.com/compare/folk-nozomio-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/gaia-vs-learnharness.json", "title": "GAIA vs LearnHarness", "url": "https://www.anchorterminal.com/compare/gaia-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/gemini-spark-vs-learnharness.json", "title": "Gemini Spark vs LearnHarness", "url": "https://www.anchorterminal.com/compare/gemini-spark-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/grok-bot-vs-learnharness.json", "title": "Grok Bot vs LearnHarness", "url": "https://www.anchorterminal.com/compare/grok-bot-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/hark-pro-vs-learnharness.json", "title": "Hark Pro vs LearnHarness", "url": "https://www.anchorterminal.com/compare/hark-pro-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/haven-vs-learnharness.json", "title": "Haven vs LearnHarness", "url": "https://www.anchorterminal.com/compare/haven-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/hermes-agent-vs-learnharness.json", "title": "Hermes Agent vs LearnHarness", "url": "https://www.anchorterminal.com/compare/hermes-agent-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/hirealpha-vs-learnharness.json", "title": "HireAlpha vs LearnHarness", "url": "https://www.anchorterminal.com/compare/hirealpha-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/instinct-vs-learnharness.json", "title": "Instinct vs LearnHarness", "url": "https://www.anchorterminal.com/compare/instinct-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/ironclaw-vs-learnharness.json", "title": "IronClaw vs LearnHarness", "url": "https://www.anchorterminal.com/compare/ironclaw-vs-learnharness" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-leon.json", "title": "LearnHarness vs Leon", "url": "https://www.anchorterminal.com/compare/learnharness-vs-leon" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-lindy.json", "title": "LearnHarness vs Lindy", "url": "https://www.anchorterminal.com/compare/learnharness-vs-lindy" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-lobby-os.json", "title": "LearnHarness vs Lobby", "url": "https://www.anchorterminal.com/compare/learnharness-vs-lobby-os" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-nanobot.json", "title": "LearnHarness vs nanobot", "url": "https://www.anchorterminal.com/compare/learnharness-vs-nanobot" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-nanoclaw.json", "title": "LearnHarness vs NanoClaw", "url": "https://www.anchorterminal.com/compare/learnharness-vs-nanoclaw" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-natura.json", "title": "LearnHarness vs Natura tinyNature", "url": "https://www.anchorterminal.com/compare/learnharness-vs-natura" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-openai-dots.json", "title": "LearnHarness vs Dots", "url": "https://www.anchorterminal.com/compare/learnharness-vs-openai-dots" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-openclaw.json", "title": "LearnHarness vs OpenClaw", "url": "https://www.anchorterminal.com/compare/learnharness-vs-openclaw" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-openduet.json", "title": "LearnHarness vs OpenDuet", "url": "https://www.anchorterminal.com/compare/learnharness-vs-openduet" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-openinstinct.json", "title": "LearnHarness vs OpenInstinct", "url": "https://www.anchorterminal.com/compare/learnharness-vs-openinstinct" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-orbits.json", "title": "LearnHarness vs Orbits", "url": "https://www.anchorterminal.com/compare/learnharness-vs-orbits" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-orchid-ai.json", "title": "LearnHarness vs Orchid", "url": "https://www.anchorterminal.com/compare/learnharness-vs-orchid-ai" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-pally.json", "title": "LearnHarness vs Pally", "url": "https://www.anchorterminal.com/compare/learnharness-vs-pally" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-picoclaw.json", "title": "LearnHarness vs PicoClaw", "url": "https://www.anchorterminal.com/compare/learnharness-vs-picoclaw" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-poke.json", "title": "LearnHarness vs Poke", "url": "https://www.anchorterminal.com/compare/learnharness-vs-poke" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-qwenpaw.json", "title": "LearnHarness vs QwenPaw", "url": "https://www.anchorterminal.com/compare/learnharness-vs-qwenpaw" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-szn.json", "title": "LearnHarness vs szn", "url": "https://www.anchorterminal.com/compare/learnharness-vs-szn" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-tab-bot.json", "title": "LearnHarness vs Tab", "url": "https://www.anchorterminal.com/compare/learnharness-vs-tab-bot" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-talorys.json", "title": "LearnHarness vs Talorys", "url": "https://www.anchorterminal.com/compare/learnharness-vs-talorys" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-tasker-ai.json", "title": "LearnHarness vs Tasker AI", "url": "https://www.anchorterminal.com/compare/learnharness-vs-tasker-ai" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-tomo.json", "title": "LearnHarness vs Tomo", "url": "https://www.anchorterminal.com/compare/learnharness-vs-tomo" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-town.json", "title": "LearnHarness vs Town", "url": "https://www.anchorterminal.com/compare/learnharness-vs-town" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-wajo.json", "title": "LearnHarness vs Wajo (Fo)", "url": "https://www.anchorterminal.com/compare/learnharness-vs-wajo" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-zapia.json", "title": "LearnHarness vs Zapia", "url": "https://www.anchorterminal.com/compare/learnharness-vs-zapia" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-zeroclaw.json", "title": "LearnHarness vs ZeroClaw", "url": "https://www.anchorterminal.com/compare/learnharness-vs-zeroclaw" }, { "json": "https://www.anchorterminal.com/compare/learnharness-vs-zo-computer.json", "title": "LearnHarness vs Zo Computer", "url": "https://www.anchorterminal.com/compare/learnharness-vs-zo-computer" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-natura.json", "title": "CowAgent vs Natura tinyNature", "url": "https://www.anchorterminal.com/compare/cowagent-vs-natura" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-pally.json", "title": "CowAgent vs Pally", "url": "https://www.anchorterminal.com/compare/cowagent-vs-pally" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-tomo.json", "title": "CowAgent vs Tomo", "url": "https://www.anchorterminal.com/compare/cowagent-vs-tomo" }, { "json": "https://www.anchorterminal.com/compare/cowagent-vs-wajo.json", "title": "CowAgent vs Wajo (Fo)", "url": "https://www.anchorterminal.com/compare/cowagent-vs-wajo" }, { "json": "https://www.anchorterminal.com/compare/astrbot-vs-learnharness.json", "title": "AstrBot vs LearnHarness", "url": "https://www.anchorterminal.com/compare/astrbot-vs-learnharness" } ], "scores": [ { "by": 28, "cowagent": 84, "edge": "cowagent", "key": "reliability", "learnharness": 56, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 4, "cowagent": 67, "edge": "cowagent", "key": "schema", "learnharness": 63, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 1, "cowagent": 59, "edge": "learnharness", "key": "ergonomics", "learnharness": 60, "name": "Agent ergonomics", "weight": 13 }, { "by": 9, "cowagent": 43, "edge": "learnharness", "key": "security", "learnharness": 52, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "cowagent": 60, "edge": "", "key": "payments", "learnharness": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 12, "cowagent": 83, "edge": "cowagent", "key": "maintenance", "learnharness": 71, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 13, "cowagent": 47, "edge": "learnharness", "key": "transparency", "learnharness": 60, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "LearnHarness and CowAgent score within a point of each other on agent readiness, 59.3 (C) and 58.7 (C). CowAgent leads on reliability and maintenance \u0026 community. Both do assistants that remember you.", "tutorials": [], "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.", "learnharness": "The in-app agent reads files but cannot change them or run commands, and a bundled skill gives other agents a documented read-only view of sessions and the knowledge graph. The project is 14 days old at 0.4.0, its file reads reach the whole home directory without approval, and it has no security policy." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cowagent-vs-learnharness", "json": "https://www.anchorterminal.com/compare/cowagent-vs-learnharness.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cowagent-vs-learnharness.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cowagent-vs-learnharness.min.md" }, "markdown": "LearnHarness and CowAgent score within a point of each other on agent readiness, 59.3 (C) and 58.7 (C). CowAgent leads on reliability and maintenance \u0026 community. Both do assistants that remember you.\n\n- CowAgent: grade C, 58.7/100, rank #671 of 1239. Markdown https://www.anchorterminal.com/tools/cowagent.md · JSON https://www.anchorterminal.com/api/v1/tools/cowagent.json\n- LearnHarness: grade C, 59.3/100, rank #648 of 1239. Markdown https://www.anchorterminal.com/tools/learnharness.md · JSON https://www.anchorterminal.com/api/v1/tools/learnharness.json\n- Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 1196 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 56\n- Maintenance \u0026 community, 83 against 71\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### LearnHarness (C)\n\nGood for: A tutor for one learner that keeps a local record of sessions and a graph of propositions and reasoning chains.\n\nAhead on:\n- Security \u0026 auth, 52 against 43\n- Transparency \u0026 trust, 60 against 47\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where CowAgent loses 5 points for them\n\nWatch for: The read, ls, find and grep tools resolve against the home directory with no allow list, and their output goes to the model provider\n\n\n## Score by category\n\n| Category | Weight | CowAgent | LearnHarness | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 84 | 56 | CowAgent +28 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 67 | 63 | CowAgent +4 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 60 | LearnHarness +1 |\n| Security \u0026 auth | 14% (17.5 this run) | 43 | 52 | LearnHarness +9 |\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 | 71 | CowAgent +12 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 47 | 60 | LearnHarness +13 |\n| Negative events | ≤15 | -5 | 0 | |\n| **Total** | | **58.7 · C** | **59.3 · C** | |\n\n## Facts side by side\n\n| Fact | CowAgent | LearnHarness |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | zhayujie | Amos Blomqvist |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | |\n| Auth | OAuth or key | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | AGPL-3.0-only |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | no |\n| Last release | 2026-09-30 | 2026-10-29 |\n| Terms last updated | no document linked | no date given |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | not found in the text |\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 | 4.2k 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**LearnHarness.** The in-app agent reads files but cannot change them or run commands, and a bundled skill gives other agents a documented read-only view of sessions and the knowledge graph. The project is 14 days old at 0.4.0, its file reads reach the whole home directory without approval, and it has no security policy.\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### LearnHarness\n\n1. Use the bundled skill (`skills/learnharness/SKILL.md`) to read a learner's record. It needs Python 3.10 or later and writes nothing\n2. Pass `--format json` before the subcommand, for example `python3 -B scripts/graph.py --format json propositions`\n3. Treat stored answer keys and teacher prose as model-authored. A proposition in the graph is not evidence the learner understood it\n4. Do not read `auth.json`, which sits one folder above the data folder and holds provider keys in plain text\n5. Close the app or re-read when a stable snapshot matters. The readers do not lock files while the app writes\n\n## Questions\n\n### Which is better for AI agents, CowAgent or LearnHarness?\n\nLearnHarness and CowAgent score within a point of each other on agent readiness, 59.3 (C) and 58.7 (C). CowAgent leads on reliability and maintenance \u0026 community.\n\n### Are CowAgent and LearnHarness open source?\n\nYes. CowAgent is open source (MIT). LearnHarness is open source (AGPL-3.0-only).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cowagent-vs-learnharness.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cowagent-vs-learnharness.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cowagent\", \"b\": \"learnharness\"}`. From a terminal: `anchor compare cowagent learnharness`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cowagent.json and https://www.anchorterminal.com/api/v1/tools/learnharness.json\n\n## Other comparisons with CowAgent or LearnHarness\n\n- [asaply vs CowAgent](https://www.anchorterminal.com/compare/asaply-vs-cowagent.md)\n- [Asmi vs CowAgent](https://www.anchorterminal.com/compare/asmi-vs-cowagent.md)\n- [Boba vs CowAgent](https://www.anchorterminal.com/compare/boba-vs-cowagent.md)\n- [Brea vs CowAgent](https://www.anchorterminal.com/compare/brea-vs-cowagent.md)\n- [CowAgent vs Del](https://www.anchorterminal.com/compare/cowagent-vs-del.md)\n- [CowAgent vs HireAlpha](https://www.anchorterminal.com/compare/cowagent-vs-hirealpha.md)\n- [CowAgent vs OpenInstinct](https://www.anchorterminal.com/compare/cowagent-vs-openinstinct.md)\n- [CowAgent vs Orbits](https://www.anchorterminal.com/compare/cowagent-vs-orbits.md)\n- [CowAgent vs Orchid](https://www.anchorterminal.com/compare/cowagent-vs-orchid-ai.md)\n- [CowAgent vs szn](https://www.anchorterminal.com/compare/cowagent-vs-szn.md)\n- [CowAgent vs Tab](https://www.anchorterminal.com/compare/cowagent-vs-tab-bot.md)\n- [CowAgent vs Zapia](https://www.anchorterminal.com/compare/cowagent-vs-zapia.md)\n- [AstrBot vs CowAgent](https://www.anchorterminal.com/compare/astrbot-vs-cowagent.md)\n- [Boski vs CowAgent](https://www.anchorterminal.com/compare/boski-vs-cowagent.md)\n- [Caddy vs CowAgent](https://www.anchorterminal.com/compare/caddy-app-vs-cowagent.md)\n- [Claude Duet vs CowAgent](https://www.anchorterminal.com/compare/claude-duet-vs-cowagent.md)\n- [CowAgent vs folk](https://www.anchorterminal.com/compare/cowagent-vs-folk-nozomio.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 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 Lobby](https://www.anchorterminal.com/compare/cowagent-vs-lobby-os.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 OpenDuet](https://www.anchorterminal.com/compare/cowagent-vs-openduet.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 Tasker AI](https://www.anchorterminal.com/compare/cowagent-vs-tasker-ai.md)\n- [CowAgent vs Town](https://www.anchorterminal.com/compare/cowagent-vs-town.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- [asaply vs LearnHarness](https://www.anchorterminal.com/compare/asaply-vs-learnharness.md)\n- [Asmi vs LearnHarness](https://www.anchorterminal.com/compare/asmi-vs-learnharness.md)\n- [Atticus vs CowAgent](https://www.anchorterminal.com/compare/atticus-vs-cowagent.md)\n- [Atticus vs LearnHarness](https://www.anchorterminal.com/compare/atticus-vs-learnharness.md)\n- [Boba vs LearnHarness](https://www.anchorterminal.com/compare/boba-vs-learnharness.md)\n- [Boski vs LearnHarness](https://www.anchorterminal.com/compare/boski-vs-learnharness.md)\n- [Brea vs LearnHarness](https://www.anchorterminal.com/compare/brea-vs-learnharness.md)\n- [Caddy vs LearnHarness](https://www.anchorterminal.com/compare/caddy-app-vs-learnharness.md)\n- [Claude Duet vs LearnHarness](https://www.anchorterminal.com/compare/claude-duet-vs-learnharness.md)\n- [CowAgent vs DeepTutor](https://www.anchorterminal.com/compare/cowagent-vs-deeptutor.md)\n- [CowAgent vs Hark Pro](https://www.anchorterminal.com/compare/cowagent-vs-hark-pro.md)\n- [CowAgent vs Talorys](https://www.anchorterminal.com/compare/cowagent-vs-talorys.md)\n- [DeepTutor vs LearnHarness](https://www.anchorterminal.com/compare/deeptutor-vs-learnharness.md)\n- [Del vs LearnHarness](https://www.anchorterminal.com/compare/del-vs-learnharness.md)\n- [folk vs LearnHarness](https://www.anchorterminal.com/compare/folk-nozomio-vs-learnharness.md)\n- [GAIA vs LearnHarness](https://www.anchorterminal.com/compare/gaia-vs-learnharness.md)\n- [Gemini Spark vs LearnHarness](https://www.anchorterminal.com/compare/gemini-spark-vs-learnharness.md)\n- [Grok Bot vs LearnHarness](https://www.anchorterminal.com/compare/grok-bot-vs-learnharness.md)\n- [Hark Pro vs LearnHarness](https://www.anchorterminal.com/compare/hark-pro-vs-learnharness.md)\n- [Haven vs LearnHarness](https://www.anchorterminal.com/compare/haven-vs-learnharness.md)\n- [Hermes Agent vs LearnHarness](https://www.anchorterminal.com/compare/hermes-agent-vs-learnharness.md)\n- [HireAlpha vs LearnHarness](https://www.anchorterminal.com/compare/hirealpha-vs-learnharness.md)\n- [Instinct vs LearnHarness](https://www.anchorterminal.com/compare/instinct-vs-learnharness.md)\n- [IronClaw vs LearnHarness](https://www.anchorterminal.com/compare/ironclaw-vs-learnharness.md)\n- [LearnHarness vs Leon](https://www.anchorterminal.com/compare/learnharness-vs-leon.md)\n- [LearnHarness vs Lindy](https://www.anchorterminal.com/compare/learnharness-vs-lindy.md)\n- [LearnHarness vs Lobby](https://www.anchorterminal.com/compare/learnharness-vs-lobby-os.md)\n- [LearnHarness vs nanobot](https://www.anchorterminal.com/compare/learnharness-vs-nanobot.md)\n- [LearnHarness vs NanoClaw](https://www.anchorterminal.com/compare/learnharness-vs-nanoclaw.md)\n- [LearnHarness vs Natura tinyNature](https://www.anchorterminal.com/compare/learnharness-vs-natura.md)\n- [LearnHarness vs Dots](https://www.anchorterminal.com/compare/learnharness-vs-openai-dots.md)\n- [LearnHarness vs OpenClaw](https://www.anchorterminal.com/compare/learnharness-vs-openclaw.md)\n- [LearnHarness vs OpenDuet](https://www.anchorterminal.com/compare/learnharness-vs-openduet.md)\n- [LearnHarness vs OpenInstinct](https://www.anchorterminal.com/compare/learnharness-vs-openinstinct.md)\n- [LearnHarness vs Orbits](https://www.anchorterminal.com/compare/learnharness-vs-orbits.md)\n- [LearnHarness vs Orchid](https://www.anchorterminal.com/compare/learnharness-vs-orchid-ai.md)\n- [LearnHarness vs Pally](https://www.anchorterminal.com/compare/learnharness-vs-pally.md)\n- [LearnHarness vs PicoClaw](https://www.anchorterminal.com/compare/learnharness-vs-picoclaw.md)\n- [LearnHarness vs Poke](https://www.anchorterminal.com/compare/learnharness-vs-poke.md)\n- [LearnHarness vs QwenPaw](https://www.anchorterminal.com/compare/learnharness-vs-qwenpaw.md)\n- [LearnHarness vs szn](https://www.anchorterminal.com/compare/learnharness-vs-szn.md)\n- [LearnHarness vs Tab](https://www.anchorterminal.com/compare/learnharness-vs-tab-bot.md)\n- [LearnHarness vs Talorys](https://www.anchorterminal.com/compare/learnharness-vs-talorys.md)\n- [LearnHarness vs Tasker AI](https://www.anchorterminal.com/compare/learnharness-vs-tasker-ai.md)\n- [LearnHarness vs Tomo](https://www.anchorterminal.com/compare/learnharness-vs-tomo.md)\n- [LearnHarness vs Town](https://www.anchorterminal.com/compare/learnharness-vs-town.md)\n- [LearnHarness vs Wajo (Fo)](https://www.anchorterminal.com/compare/learnharness-vs-wajo.md)\n- [LearnHarness vs Zapia](https://www.anchorterminal.com/compare/learnharness-vs-zapia.md)\n- [LearnHarness vs ZeroClaw](https://www.anchorterminal.com/compare/learnharness-vs-zeroclaw.md)\n- [LearnHarness vs Zo Computer](https://www.anchorterminal.com/compare/learnharness-vs-zo-computer.md)\n- [CowAgent vs Natura tinyNature](https://www.anchorterminal.com/compare/cowagent-vs-natura.md)\n- [CowAgent vs Pally](https://www.anchorterminal.com/compare/cowagent-vs-pally.md)\n- [CowAgent vs Tomo](https://www.anchorterminal.com/compare/cowagent-vs-tomo.md)\n- [CowAgent vs Wajo (Fo)](https://www.anchorterminal.com/compare/cowagent-vs-wajo.md)\n- [AstrBot vs LearnHarness](https://www.anchorterminal.com/compare/astrbot-vs-learnharness.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-31", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "CowAgent vs LearnHarness", "url": "" } ], "description": "LearnHarness and CowAgent score within a point of each other for assistants that remember you, 59.3 and 58.7 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "CowAgent C 58.7", "LearnHarness C 59.3", "scores" ], "h1": "CowAgent vs LearnHarness", "image": "https://www.anchorterminal.com/assets/og/compare-cowagent-vs-learnharness.png", "path": "/compare/cowagent-vs-learnharness", "published": "2026-10-01", "section": "tools", "title": "CowAgent vs LearnHarness for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/compare/cowagent-vs-learnharness" }, "tokens": { "markdown": 3950, "slim": 630 }, "version": 1 }