weclaw-wechat-ai-bridge

Connect WeChat to AI agents (Claude, Codex, Gemini, Kimi, etc.) using the WeClaw bridge in Go.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "weclaw-wechat-ai-bridge" with this command: npx skills add aradotso/trending-skills/aradotso-trending-skills-weclaw-wechat-ai-bridge

WeClaw — WeChat AI Agent Bridge

Skill by ara.so — Daily 2026 Skills collection.

WeClaw connects WeChat to AI agents (Claude, Codex, Gemini, Kimi, OpenClaw, etc.) via a Go-based bridge. It handles QR-code login, message routing, media conversion, and agent lifecycle. Supports three agent modes: ACP (JSON-RPC subprocess, fastest), CLI (new process per message), and HTTP (OpenAI-compatible REST).


Installation

# One-line installer
curl -sSL https://raw.githubusercontent.com/fastclaw-ai/weclaw/main/install.sh | sh

# Via Go toolchain
go install github.com/fastclaw-ai/weclaw@latest

# Via Docker
docker run -it -v ~/.weclaw:/root/.weclaw ghcr.io/fastclaw-ai/weclaw start

First-Run Flow

weclaw start        # Shows QR code → scan with WeChat → auto-detects agents → saves config
weclaw login        # Add/re-authenticate a WeChat account
weclaw status       # Show running state and active agent
weclaw stop         # Stop the background daemon
weclaw start -f     # Foreground mode (debug/verbose)

Logs: ~/.weclaw/weclaw.log
Config: ~/.weclaw/config.json


Configuration

{
  "default_agent": "claude",
  "agents": {
    "claude": {
      "type": "acp",
      "command": "/usr/local/bin/claude-agent-acp",
      "model": "sonnet"
    },
    "codex": {
      "type": "acp",
      "command": "/usr/local/bin/codex-acp"
    },
    "claude-cli": {
      "type": "cli",
      "command": "/usr/local/bin/claude",
      "args": ["--dangerously-skip-permissions"]
    },
    "codex-cli": {
      "type": "cli",
      "command": "/usr/local/bin/codex",
      "args": ["--skip-git-repo-check"]
    },
    "openclaw": {
      "type": "http",
      "endpoint": "https://api.example.com/v1/chat/completions",
      "api_key": "$OPENCLAW_GATEWAY_TOKEN",
      "model": "openclaw:main"
    }
  }
}

Environment Variables

VariablePurpose
WECLAW_DEFAULT_AGENTOverride default agent at runtime
WECLAW_API_ADDRChange local HTTP API address (default 127.0.0.1:18011)
OPENCLAW_GATEWAY_URLHTTP agent endpoint
OPENCLAW_GATEWAY_TOKENHTTP agent API token

Agent Modes

ModeProcess modelBest for
acpLong-running subprocess, JSON-RPC over stdioClaude, Codex, Kimi, Gemini — fastest, session reuse
cliNew process per message, --resume for sessionsclaude -p, codex exec
httpOpenAI-compatible /v1/chat/completionsAny REST-accessible model

Auto-detection prefers acp over cli when both binaries exist.


Chat Commands (send as WeChat messages)

CommandAction
helloSend to default agent
/codex write a sort functionRoute to named agent
/cc explain this codeUse alias (/cc → claude)
/claudeSwitch default agent to Claude (persisted)
/statusShow active agent info
/helpList available commands

Built-in Aliases

AliasAgent
/ccclaude
/cxcodex
/cscursor
/kmkimi
/gmgemini
/ocdopencode
/ocopenclaw

Proactive Messaging — CLI

# Send plain text
weclaw send --to "user_id@im.wechat" --text "Hello from WeClaw"

# Send an image
weclaw send --to "user_id@im.wechat" --media "https://example.com/photo.png"

# Send text + media together
weclaw send --to "user_id@im.wechat" \
  --text "Check this out" \
  --media "https://example.com/photo.png"

# Send a file
weclaw send --to "user_id@im.wechat" --media "https://example.com/report.pdf"

Proactive Messaging — HTTP API

The local API listens on 127.0.0.1:18011 while weclaw start is running.

# Send text
curl -X POST http://127.0.0.1:18011/api/send \
  -H "Content-Type: application/json" \
  -d '{"to": "user_id@im.wechat", "text": "Hello from WeClaw"}'

# Send image
curl -X POST http://127.0.0.1:18011/api/send \
  -H "Content-Type: application/json" \
  -d '{"to": "user_id@im.wechat", "media_url": "https://example.com/photo.png"}'

# Send text + media
curl -X POST http://127.0.0.1:18011/api/send \
  -H "Content-Type: application/json" \
  -d '{"to": "user_id@im.wechat", "text": "See this", "media_url": "https://example.com/photo.png"}'

Supported media types: png, jpg, gif, webp, mp4, mov, pdf, doc, zip.

Change listen address:

WECLAW_API_ADDR=0.0.0.0:18011 weclaw start

Go Integration Example

Call the WeClaw HTTP API from a Go service to send notifications:

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"net/http"
	"os"
)

type SendRequest struct {
	To       string `json:"to"`
	Text     string `json:"text,omitempty"`
	MediaURL string `json:"media_url,omitempty"`
}

type SendResponse struct {
	OK      bool   `json:"ok"`
	Message string `json:"message,omitempty"`
}

func sendToWeChat(to, text, mediaURL string) error {
	apiAddr := os.Getenv("WECLAW_API_ADDR")
	if apiAddr == "" {
		apiAddr = "127.0.0.1:18011"
	}

	req := SendRequest{To: to, Text: text, MediaURL: mediaURL}
	body, err := json.Marshal(req)
	if err != nil {
		return fmt.Errorf("marshal: %w", err)
	}

	resp, err := http.Post(
		fmt.Sprintf("http://%s/api/send", apiAddr),
		"application/json",
		bytes.NewReader(body),
	)
	if err != nil {
		return fmt.Errorf("post: %w", err)
	}
	defer resp.Body.Close()

	var result SendResponse
	if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
		return fmt.Errorf("decode: %w", err)
	}
	if !result.OK {
		return fmt.Errorf("weclaw error: %s", result.Message)
	}
	return nil
}

func main() {
	recipient := os.Getenv("WECHAT_RECIPIENT_ID") // e.g. "user_id@im.wechat"
	if err := sendToWeChat(recipient, "Build succeeded ✅", ""); err != nil {
		fmt.Fprintf(os.Stderr, "failed: %v\n", err)
		os.Exit(1)
	}
	fmt.Println("Message sent.")
}

Docker Setup

# Build image
docker build -t weclaw .

# Step 1: Interactive login (scan QR code)
docker run -it -v ~/.weclaw:/root/.weclaw weclaw login

# Step 2: Run daemon with HTTP agent
docker run -d --name weclaw \
  -v ~/.weclaw:/root/.weclaw \
  -e OPENCLAW_GATEWAY_URL=https://api.example.com \
  -e OPENCLAW_GATEWAY_TOKEN="$OPENCLAW_GATEWAY_TOKEN" \
  weclaw

# Expose the local API externally (bind carefully — no auth by default)
docker run -d --name weclaw \
  -v ~/.weclaw:/root/.weclaw \
  -e WECLAW_API_ADDR=0.0.0.0:18011 \
  -p 18011:18011 \
  -e OPENCLAW_GATEWAY_TOKEN="$OPENCLAW_GATEWAY_TOKEN" \
  weclaw

docker logs -f weclaw

ACP/CLI agents require the agent binary inside the container. Mount the binary or build a custom image. HTTP agents work out of the box.


System Service (Auto-start)

macOS (launchd):

cp service/com.fastclaw.weclaw.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.fastclaw.weclaw.plist

Linux (systemd):

sudo cp service/weclaw.service /etc/systemd/system/
sudo systemctl enable --now weclaw
journalctl -u weclaw -f

Development

make dev                        # Hot reload
go build -o weclaw .            # Build binary
./weclaw start -f               # Run in foreground

Releasing:

git tag v0.1.0
git push origin v0.1.0
# GitHub Actions builds darwin/linux × amd64/arm64 and uploads release artifacts

Common Patterns

Pattern: Per-user agent routing

Send /claude or /codex as a WeChat message to switch the default agent. The choice persists in ~/.weclaw/config.json across restarts.

Pattern: CI/CD build notifications

After a build, call weclaw send or POST to the HTTP API to push results to a WeChat contact or group.

Pattern: Media from agent

If an agent reply contains ![alt](https://...), WeClaw auto-downloads, AES-128-ECB encrypts, uploads to WeChat CDN, and delivers as a native image message — no extra config needed.

Pattern: Disable permission prompts for headless use

{
  "claude": { "type": "cli", "command": "/usr/local/bin/claude",
               "args": ["--dangerously-skip-permissions"] },
  "codex":  { "type": "cli", "command": "/usr/local/bin/codex",
               "args": ["--skip-git-repo-check"] }
}

ACP agents handle permissions automatically and do not need these flags.


Troubleshooting

SymptomFix
QR code not appearingRun weclaw login explicitly; ensure terminal supports UTF-8
Agent not auto-detectedCheck binary is on $PATH; run weclaw status
connection refused on HTTP APIConfirm weclaw start is running; check WECLAW_API_ADDR
Agent permission prompts block responsesAdd --dangerously-skip-permissions (Claude) or --skip-git-repo-check (Codex) to args; or use ACP mode
Docker — no agent binaryMount binary: -v /usr/local/bin/claude:/usr/local/bin/claude; or use HTTP mode
Markdown not renderingWeClaw strips markdown automatically for WeChat plain-text display; this is expected
Logstail -f ~/.weclaw/weclaw.log or docker logs -f weclaw

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

everything-claude-code-harness

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

paperclip-ai-orchestration

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

freecodecamp-curriculum

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

opencli-web-automation

No summary provided by upstream source.

Repository SourceNeeds Review