Loading image...Kiro

Product

  • About Kiro
  • Agents
  • IDE
  • CLI
  • Web
  • Mobile
  • Crew
  • Pricing
  • Downloads

For

  • Enterprise
  • Startups
  • Students

Community

  • Overview
  • Ambassadors
  • Case studies
  • Discord
  • Events
  • Powers
  • Shop
  • Showcase

Resources

  • Docs
  • Blog
  • Changelog
  • FAQs
  • Videos
  • Report a bug
  • Suggest an idea
  • Billing support

Social

Site TermsLicenseResponsible AI PolicyLegalPrivacy PolicyCookie Preferences
Kiro
  • Agents
  • Enterprise
  • Pricing
  • Docs
SIGN INDOWNLOADS
Kiro

Get Started

InstallationAuthenticationYour first project

Models

OverviewAvailable modelsReasoning effortAWS GovCloud (US) models

Features

How Kiro worksLocal command sandboxACP integrations
Specs
Steering
Hooks
MCP
Permissions
Custom agents
Workflows
Agent Skills
Powers
Cloud sessionsMemoryCompactionKiroignoreCheckpoints and rewind
Built-in tools
Configuration scopes

IDE 1.x

What's new in 1.0
Setup & First Run
Editor
Chat
Experimental
Troubleshooting0.x reference

CLI

What's new in V3
Setup & First Run
Terminal UI
Chat
Fullscreen modeVoice modeHeadless modeACPAuto complete
Experimental
2.x reference

Crew

Quick startInstallationRunning 24/7
Chat
Agent Capabilities
Features
Interfaces
Slack
Discord
Telegram
Teams
Webex
WeCom
WeChat (Weixin)
CLI reference
Apps
System & storageConfigurationSecurityTroubleshooting

Web

Setup & First RunIdentity Center
Connect your repositories
Working with the agent
Autonomous modeScheduleConfiguration Sync
Sandbox

Mobile - Preview

Overview

Commands and Reference

CLI commandsSlash commandsBuilt-in toolsExit codesSettings

Billing

OverviewManaging your subscriptionUpgrading your planDowngrading your planCancelling your planPurchasing add-on creditsManaging your paymentsManaging usage notificationsManaging your taxesContacting billing supportDeleting your accountRelated questions

Enterprise

ConceptsOnboarding quickstart
Connecting your identity provider
Deployment optionsSubscribe your teamManage subscriptions
Governance
Monitor and track
SettingsManaged updatesTLS inspection compatibilityBillingIAMSupported regions
AWS GovCloud (US)

Privacy and Security

OverviewData protectionCode referencesCompliance validationInfrastructure securityIAM permissionsFirewalls, proxies, and data perimetersVPC endpoints (AWS PrivateLink)

Guides

OverviewRunning Kiro in the cloud
Language support
Learn by playing

Migration

Migrating from Q DeveloperMigrating from VSCodeUpgrading from Q CLI
  1. Docs
  2. Crew
  3. Interfaces
  4. WeCom
View as Markdown

WeCom

View as Markdown

Crew connects to WeCom (企业微信) through its AI-bot API over an outbound WebSocket. Create the bot in your WeCom admin console, drop in two values, and you're chatting. Replies stream back live.

Info

This is WeCom (企业微信), the work edition. For personal WeChat (微信), see WeChat (Weixin).

Setup

From the dashboard (recommended)

  1. In the WeCom admin console, open 应用管理 → AI 智能体 and create a bot. Note the Bot ID and Secret from its settings page.
  2. Open Settings → Messaging Channels → WeCom in the dashboard
  3. Paste the Bot ID and Secret
  4. Add the userids you want to allow (every WeCom member has a userid / 账号)
  5. Click Save — the gateway restarts and connects

Look for WeCom WS connected and subscribed in the status badge. Message the bot in WeCom.

From the CLI

bash
# Save credentials to ~/.kiro/crew/.env echo "WECOM_BOT_ID=your-bot-id" >> ~/.kiro/crew/.env echo "WECOM_SECRET=your-bot-secret" >> ~/.kiro/crew/.env

In ~/.kiro/crew/config.json:

json
{ "wecom": { "enabled": true, "allowed_users": [{ "userid": "zhangsan", "name": "Zhang San" }] } }

Then: kirocrew restart

Message the bot in WeCom. If it stays quiet, confirm your userid is allowed.

Who can reach it

  • Owner (KIROCREW_OWNER_ID) plus anyone in allowed_users
  • Whole-company access: set "allow_all_users": true to skip individual listing — this is an explicit opt-in (an empty list never means "everyone")
  • The WeCom AI bot carries direct messages only — one conversation per userid
  • Anyone else is silently dropped and recorded in the audit log

Send and receive files

Images, regular files, and voice notes sent to the bot reach the agent. WeCom supplies voice-note transcripts, while attached audio files are downloaded and transcribed locally. Inbound limits are 10 MB per image, 20 MB per file, and 10 items per message.

Files the agent sends through file_send or a dashboard upload arrive as native WeCom media. PNG and JPEG files arrive as pictures, MP4 and WebM files as videos, and other formats as downloads. Outbound pictures and voice notes are limited to 2 MB; files and videos are limited to 20 MB. A larger picture is delivered as a file instead of being dropped.

An image merely mentioned inline in a reply is not uploaded. Use file_send when the image itself should arrive.

Commands

CommandEffect
/new (or 新对话, 清空)Start a fresh conversation
/compactCompress context

Behavior notes

  • The bot replies to messages — it can't start a conversation on its own
  • No buttons — OPTIONS prompts arrive as plain text; just reply normally
  • Only two values needed: Bot ID and Secret. No corp ID, agent ID, callback URL, or AES key

Configuration

KeyDefaultPurpose
wecom.enabledfalseTurns the channel on
wecom.allowed_users[]{ "userid", "name" } entries (empty = owner only)
wecom.allow_all_usersfalseAllow all organization members
wecom.soft_threshold_pct80Suggest /compact past this
wecom.hard_threshold_pct95Hard cutoff
wecom.ws_urlwss://openws.work.weixin.qq.comWeCom AI-bot endpoint

Credentials in ~/.kiro/crew/.env: WECOM_BOT_ID and WECOM_SECRET.

Troubleshooting

ProblemFix
No replySender's userid isn't allowed or enabled is false
No channel started in logsA credential is unset
Connects then goes quietBot may have been removed from the WeCom console — re-add and restart

Next

  • WeChat (Weixin) — personal WeChat via iLink
  • Telegram — similar outbound model
  • Interfaces overview — all surfaces at a glance
Page updated: October 12, 2026
Webex
WeChat (Weixin)