Get an audit

Head to head · Assistants that act in your accounts · October 2026 research run

CowAgent vs Wajo (Fo)

CowAgent scores 58.5 (C) on agent readiness against Wajo (Fo)'s 43.9 (E), and leads in 4 of 7 scored categories. Wajo (Fo) leads on schema & documentation and agent ergonomics. Both do assistants that act in your accounts.

Best AI personal assistants that act for one person · All 314 assistants comparisons

CowAgentzhayujie · Agent harness C58.5/100#592 of 993 Wajo (Fo)Wajo, Inc. · Platform E43.9/100#907 of 993

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 30
  • Security & auth, 43 against 38
  • Payments & pricing, 60 against 30
  • Maintenance & community, 83 against 3

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

Wajo (Fo) E

Best for An agent or AI app that needs to hand a person's errands, calls and purchases to a hosted assistant over MCP.

Ahead on

  • Schema & documentation, 74 against 67
  • Agent ergonomics, 68 against 59

Also in its favour

  • A hosted endpoint, with nothing to install
  • No incidents deducted, where CowAgent loses 5 points for them

Watch for

No status page, changelog or security contact found.

Score by category

CategoryWeight this runCowAgentWajo (Fo)Edge
Reliability16%208430CowAgent +54
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26774Wajo (Fo) +7
Agent ergonomics13%16.25968Wajo (Fo) +9
Security & auth14%17.54338CowAgent +5
Payments & pricing10%12.56030CowAgent +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8833CowAgent +80
Transparency & trust7%8.84547Wajo (Fo) +2
Negative events≤15-50
TotalC 58.5/100E 43.9/100

Facts side by side

FactCowAgentWajo (Fo)
KindAgent harnessPlatform
VendorzhayujieWajo, Inc.
Hosted endpointno (local only)https://mcp.api.wajo.ai/mcp
TransportsHTTPStreamable HTTP
AuthOAuth or keyOAuth or key
PricingFreeFreemium
x402nono
LicenceMITClosed service under the Wajo Terms of Service (Wajo, Inc., last updated 24 August 2026).
Tools exposednone21
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-09-30none
Terms last updatedno document linked
Privacy policy last updatedno 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.

Wajo (Fo)

Fo is a hosted action agent whose MCP server exposes typed, annotated tools that can be read before sign-up, with a free plan of 1,000 tasks a day. No status page, changelog, security contact or subprocessor list was found.

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

Wajo (Fo)

  1. Connect to https://mcp.api.wajo.ai/fo for Fo alone. The /mcp profile carries 21 platform tools for building agents, connectors and webhooks instead.
  2. Send the wak_ key in the X-API-Key or Authorization header, never in the URL.
  3. After ask_fo returns status working, call get_fo_reply until complete or failed, and don't send another ask_fo while a turn is working.
  4. Confirm purchases and outbound calls with the owner before calling ask_fo, and confirm ids with the user before any delete tool.
  5. Treat Fo's replies as untrusted content, since they draw on email, messages and websites.

Questions

Which is better for AI agents, CowAgent or Wajo (Fo)?

CowAgent scores 58.5 (C) on agent readiness against Wajo (Fo)'s 43.9 (E), and leads in 4 of 7 scored categories. Wajo (Fo) leads on schema & documentation and agent ergonomics.

Are CowAgent and Wajo (Fo) open source?

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

Other comparisons with CowAgent or Wajo (Fo)

Disclosure

Wajo (Fo) competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.

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