Get an audit

Head to head · Assistant proactive · October 2026 research run

CowAgent vs Dots

CowAgent scores 58.5 (C) on agent readiness against Dots's 28.3 (F), and leads in 6 of 7 scored categories. Dots leads on security & auth. Both do assistant proactive.

Best AI personal assistants that act for one person · All 190 assistants comparisons

CowAgentzhayujie · Agent harness C58.5/100#591 of 986 DotsOpenAI · Platform F28.3/100#973 of 986

Which one, for what

CowAgent C

Best 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.

Ahead on

  • Reliability, 84 against 3
  • Schema & documentation, 67 against 41
  • Agent ergonomics, 59 against 22
  • Payments & pricing, 60 against 10
  • Maintenance & community, 83 against 38
  • Transparency & trust, 45 against 31

Also in its favour

  • Free to start without a card
  • Open source

Watch 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

Dots F

Best for A ChatGPT Pro or Enterprise user who wants ongoing work tracked across mail, documents, code and Slack with approval before sends.

Ahead on

  • Security & auth, 58 against 43

Also in its favour

  • No incidents deducted, where CowAgent loses 5 points for them

Watch for

Beta. The admin setting is labelled Use dots (Beta), access is rolling out gradually, and Teams access is an invite-only alpha

Score by category

CategoryWeight this runCowAgentDotsEdge
Reliability16%20843CowAgent +81
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26741CowAgent +26
Agent ergonomics13%16.25922CowAgent +37
Security & auth14%17.54358Dots +15
Payments & pricing10%12.56010CowAgent +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88338CowAgent +45
Transparency & trust7%8.84531CowAgent +14
Negative events≤15-50
TotalC 58.5/100F 28.3/100

Facts side by side

FactCowAgentDots
KindAgent harnessPlatform
VendorzhayujieOpenAI
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthOAuth or keyOAuth or key
PricingFreePaid
x402nono
LicenceMITProprietary hosted service. The governing terms were not read
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-09-302026-10-09
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity47k starsnone

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.

Dots

Actions that affect accounts or share information pass an automatic review, and custom rules can require approval or a hand-off. Dots is a beta on Pro plans from $100 a month, and no status page, terms, privacy policy or way to delete individual saved notes was found in the pages we could read.

Before you call either

CowAgent

  1. Set agent_permission_mode to workspace-write or read-only before connecting any channel. Source and Docker installs default to full-access
  2. Keep the bot out of group chats that include other people. Any member who mentions it reaches the same tools as the owner
  3. Set web_password before changing web_host to 0.0.0.0. The password is empty by default
  4. 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
  5. Run it in a container for a hard boundary. The docs and the source both say the permission modes are not isolation

Dots

  1. Say what may be sent. Asking a dot to draft replies does not permit sending them, and an action outside a stated scope needs another decision
  2. Stop three things separately. Pause stops the main task only, delegated tasks stop in Activity and recurring tasks in Scheduled, and completed actions are not undone
  3. Connect each thing separately. A messaging channel grants no access to an inbox, an app or a computer
  4. Sign out of websites and disconnect apps yourself when removing access. Revoking dots access or disconnecting an app does not delete information already obtained
  5. Keep the connected computer online with the ChatGPT app open for local work. Only one personal computer can be connected at a time

Questions

Which is better for AI agents, CowAgent or Dots?

CowAgent scores 58.5 (C) on agent readiness against Dots's 28.3 (F), and leads in 6 of 7 scored categories. Dots leads on security & auth.

Are CowAgent and Dots open source?

CowAgent is open source (MIT). No open-source release is listed for Dots.

Other comparisons with CowAgent or Dots

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report