Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026

CowAgent by zhayujie (LinkAI)

A self-hosted assistant, formerly chatgpt-on-wechat, that plans tasks and runs tools, skills and browser automation with memory, a knowledge base and multi-agent teams, connecting to web, WeChat, Feishu, DingTalk, Telegram, Slack and other channels.

General-purpose AI agents Open-source personal AI assistant (formerly chatgpt-on-wechat)Open source · MITFree to start

Use it in: Slack, Teams, Telegram Web app CLI Desktop app Self-hosted Works with: Multi-agent

Price
Free (OSS)
free and open source
Popularity
#26 in General
Gid Score 27 / 100 · #185 of 255 ranked AI agents
Trend
Gaining stars
about +19 GitHub stars a day
Development
Updated recently
latest 2.2.2, 22d ago
Community
48K GitHub stars
public signals

Usage data: latest readings Nov 20 to Nov 21, 2026, last checked Nov 21, 06:29 UTC. Date of each number

What CowAgent does

CowAgent is an open-source personal AI assistant (formerly chatgpt-on-wechat) from zhayujie, first released in August 2022. You use it through messaging apps, a web app, a command-line tool, a desktop app and self-hosted. Its documentation covers subagents or parallel agents. It can run models from Anthropic, OpenAI, Google, DeepSeek, Qwen and Moonshot (Kimi). It is free and open source (MIT); you pay only for the models it calls.

Key facts

Makerzhayujie (LinkAI)
TypeOpen-source personal AI assistant (formerly chatgpt-on-wechat)
First releasedAugust 2022
LicenseMIT
InterfacesMessaging apps, Web app, CLI, Desktop app, Self-hosted
Main languagePython
Open issues and PRs40
Docker Hub pulls268,493

Pricing

Free MIT-licensed self-hosted software; a hosted version and enterprise services are sold through LinkAI.

Source: official pricing page, checked Oct 6, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (MIT)
  • Where you use itMessaging apps, Web app, CLI, Desktop app, Self-hosted
  • Model providersanthropic, openai, google, deepseek, qwen, moonshot
  • Subagents / multi-agent?Yes
  • Feature comparisonAll agents
  • Closest alternativeOpenClaw · all alternatives

What's new in CowAgent: October 2026

Full monthly summary

October brought major improvements to artifact management and introduced a new public-facing pages feature. CowAgent now makes it easier to organize Agent outputs and share interactive chat experiences with visitors.

  • Artifacts automatically collect all documents, images, and videos your Agents create in one searchable timeline.
  • Create standalone pages with embedded chat windows to share Agent capabilities on your website.
  • Customize menu groups, order, names, and visibility across Web and desktop clients.
  • Each Agent page can have its own theme, references, access controls, and customization.

2 releases this month · summarised from the official release notes · all months

Get started with CowAgent

Dockerdocker pull zhayujie/chatgpt-on-wechat

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Compare CowAgent with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
8
OpenClawOpenClaw Foundation (nonprofit); created by Peter Steinberger
70 2.8M down 8.7% down 27.1% 395K+123/day 2026.11.62d ago Free (OSS)
11 67 676K down 14.9% up 59.0% 285K+622/day — Free
14
Hermes AgentNous Research
63 56.8K down 26.1% — 265K+297/day 0.23.3yesterday Free (OSS)
42
ManusButterfly Effect Pte. Ltd. (Manus AI), Singapore
50 — — — — — $20/mo
58
Cloudflare OSCloudflare
46 — — — 11.8K+9/day — Free (OSS)
63
Muse NewMeta
452/4 — — — — — Free

Ratings from people who use CowAgent

No ratings yet. Used CowAgent? Rate it and say what it is good and bad at.

What changed: recent CowAgent releases

5 stable releases in the last 90 days · Monthly summary · Full changelog

2.2.2
  • Standalone pages: each page gets its own link, visitors keep their chat history, and the name, icon, theme color, welcome message, and suggested questions are all customizable.
  • Embedded chat window: a single code snippet embeds the page in your website, with a chat button in the bottom-right corner.
  • Data isolation: the Agent serving visitors can only use the tools, skills, and references enabled for that page.
  • References: select your knowledge base, or one of its categories, as read-only references, each with a note on what it is for.
  • Access control: supports an access password, a daily question limit per visitor, and an expiry date.
  • Theme import: drag in a theme zip or folder to import it, with custom colors, a background wallpaper, and a new-chat icon. Themes are stored in ~/cow/system/themes/.
2.2.1
  • Automatic collection: documents, web pages, images, and videos your Agents create show up in Artifacts automatically, on one timeline across all Agents.
  • Preview and trace back: filter by type or Agent, search, preview in place, and jump back to the conversation that produced a file (Thanks @rudycelekli #3732).
  • Pin and manage: pin, rename, or remove artifacts; a file card in a conversation takes you straight to it in Artifacts. The Artifacts page is hidden by default and can be turned on in the menu editor.
  • Custom menu: customize the groups, order, names, icons, and visibility of menu entries in the Web console and desktop client, with one shared configuration.
  • Token usage: each reply shows the tokens actually used in that turn, including cache hits. Thanks @Harbor404
  • Mermaid diagrams: Mermaid code blocks can switch to a rendered diagram, with zoom and full screen. Thanks @akushonkamen
Earlier releases
2.2.0
  • Skill installation: install from Cow Skill Hub, GitHub, or ClawHub, or upload an archive, a SKILL.md, or a folder. Every skill is previewed first and only installed after you confirm.
  • MCP configuration: add, edit, and remove MCP servers in the UI, covering the stdio, SSE, and Streamable HTTP transports.
  • Tool retrieval diagnostics: see how MCP tools were ranked and why retrieval fell back during a conversation, making it easier to find out why a tool was not picked. Thanks @zhongjunqi7657
  • Task handoff as separate messages: when an Agent delegates a task to a team member, the member's reply streams as its own message under its own name and avatar, on both the Web console and the…
  • Team session management: clearing context now clears it for every participant in a team session; a group chat shows its members in the session list before the first message is sent.
  • Data isolation: skills, uploaded file previews, and website directories are now scoped per Agent.
2.1.9
  • Multi-Agent session selection: the in-session multi-Agent selector adds a lead-Agent marker that clearly separates the lead Agent from members, while simplifying the view in single-Agent setups.
  • Collaboration fix: fixed failures when delegating tasks from non-lead Agents in multi-Agent group chats, now correctly identifying member Agents.
  • Member Agent image rendering: fixed images generated by non-default Agents failing to render on the Web console and desktop client.
  • Group-chat entry: the desktop Team page adds a group-chat entry, so you can start a group session directly from an Agent team.
  • Desktop channel integration fix: fixed channels failing to start in the desktop client.
  • Channel stop fix: fixed a lost app_module lookup during the channel stop flow that caused disconnect errors (a regression introduced by #3141).
2.1.8
  • Team management: create and maintain Agents, configure name, responsibilities, default model, skills, and knowledge, and copy the setup from an existing Agent.
  • Resource isolation: each Agent has its own workspace, memory, and sessions; the knowledge base and skills can be shared or kept independent.
  • Group collaboration: add multiple Agents to one session and use @ to direct a message to a specific member, with each Agent using its own configured model.
  • Task delegation: a group chat has a lead Agent that can hand a task off to the member best suited for it based on their responsibilities, with support for multi-level delegation and configurable…
  • Multiple channel instances: an IM channel of the same type can now run multiple instances, each bound to a single Agent or an Agent team.
  • Manual task creation: create, edit, and run tasks directly on the tasks page, and select the channel instance and recipient.
2.1.7
  • Multiple workspaces: create or open any directory as a project workspace; the documents, web pages, and code the Agent produces are created and managed there.
  • Per-session workspace: each session is bound to its own project workspace, so tasks running side by side stay out of each other's way.
  • Per-session model: switch the model for a single session; new sessions start from the global default.
  • Grouped sessions: the session list is grouped by workspace, with pinning, reordering, renaming, and deleting.
  • Shared system resources: memory, skills, and the knowledge base still live in the system workspace (~/cow by default).
  • Three levels: read-only, workspace-write, and full-access, set independently for each session.

CowAgent prices over time

Token prices of Anthropic modelsnewest Anthropic model in each family, output price per 1M tokens
Anthropic OpusAnthropic SonnetAnthropic Haiku

CowAgent popularity and usage data

The GitHub repository has 48K stars, 647 of them added in the last 30 days. The latest stable release is 2.2.2, published Oct 30, 2026; there was 1 stable release in the past 30 days. It was mentioned in 1 Hacker News posts and comments over the last 30 days.

GitHub starsrunning total 48K
Hacker News mentionsposts and comments, rolling 7-day total 0 this week
Website rankTranco list; a lower rank means more traffic #2,378,382

Download the raw daily series: cowagent.csv

Gid Score breakdown

Adoption12
Community70
Attention0
Momentum51

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
GitHub starsNov 21, 2026Nov 21, 06:26 UTC
Docker pullsNov 21, 2026Nov 21, 06:27 UTC
Website rank (Tranco)Nov 20, 2026Nov 21, 06:29 UTC
Hacker News mentionsNov 20, 2026Nov 21, 06:27 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

CowAgent FAQ

How much does CowAgent cost?

Free MIT-licensed self-hosted software; a hosted version and enterprise services are sold through LinkAI.

Is CowAgent open source?

Yes. CowAgent is open source, released under the MIT license.

How popular is CowAgent?

The GitHub repository has 48K stars, 647 of them added in the last 30 days. The latest stable release is 2.2.2, published Oct 30, 2026; there was 1 stable release in the past 30 days. It was mentioned in 1 Hacker News posts and comments over the last 30 days.

What is the latest version of CowAgent?

The latest stable release we track is 2.2.2, published on Oct 30, 2026.

What are the alternatives to CowAgent?

The closest alternatives in the same category by Gid Score are OpenClaw, DeepSeek Harness, Hermes Agent, Manus.

For the makers of CowAgent badges, corrections

Add a live badge to your README or site:

AgentGid: #26 in General Gid Score: 27/100

[![AgentGid: #26 in General](https://agentgid.com/badges/cowagent-rank.svg)](https://agentgid.com/agents/cowagent/)
[![Gid Score: 27/100](https://agentgid.com/badges/cowagent-score.svg)](https://agentgid.com/agents/cowagent/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

GitHub: zhayujie/cowagent. Site rank: cowagent.ai on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: github.com, hub.docker.com.