
weclaw-wechat-ai-bridge
Connect WeChat to AI agents (Claude, Codex, Gemini, Kimi, etc.) using the WeClaw bridge in Go.
- Installs
- 954
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/trending-skills --skill weclaw-wechat-ai-bridge- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads weclaw-wechat-ai-bridge automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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
| Variable | Purpose |
|---|---|
WECLAW_DEFAULT_AGENT | Override default agent at runtime |
WECLAW_API_ADDR | Change local HTTP API address (default 127.0.0.1:18011) |
OPENCLAW_GATEWAY_URL | HTTP agent endpoint |
OPENCLAW_GATEWAY_TOKEN | HTTP agent API token |
Agent Modes
| Mode | Process model | Best for |
|---|---|---|
acp | Long-running subprocess, JSON-RPC over stdio | Claude, Codex, Kimi, Gemini — fastest, session reuse |
cli | New process per message, --resume for sessions | claude -p, codex exec |
http | OpenAI-compatible /v1/chat/completions | Any REST-accessible model |
Auto-detection prefers acp over cli when both binaries exist.
Chat Commands (send as WeChat messages)
| Command | Action |
|---|---|
hello | Send to default agent |
/codex write a sort function | Route to named agent |
/cc explain this code | Use alias (/cc → claude) |
/claude | Switch default agent to Claude (persisted) |
/status | Show active agent info |
/help | List available commands |
Built-in Aliases
| Alias | Agent |
|---|---|
/cc | claude |
/cx | codex |
/cs | cursor |
/km | kimi |
/gm | gemini |
/ocd | opencode |
/oc | openclaw |
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 , 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
| Symptom | Fix |
|---|---|
| QR code not appearing | Run weclaw login explicitly; ensure terminal supports UTF-8 |
| Agent not auto-detected | Check binary is on $PATH; run weclaw status |
connection refused on HTTP API | Confirm weclaw start is running; check WECLAW_API_ADDR |
| Agent permission prompts block responses | Add --dangerously-skip-permissions (Claude) or --skip-git-repo-check (Codex) to args; or use ACP mode |
| Docker — no agent binary | Mount binary: -v /usr/local/bin/claude:/usr/local/bin/claude; or use HTTP mode |
| Markdown not rendering | WeClaw strips markdown automatically for WeChat plain-text display; this is expected |
| Logs | tail -f ~/.weclaw/weclaw.log or docker logs -f weclaw |
FAQ
What does the weclaw-wechat-ai-bridge skill do?
Connect WeChat to AI agents (Claude, Codex, Gemini, Kimi, etc.) using the WeClaw bridge in Go.
How do I install weclaw-wechat-ai-bridge?
Run npx skills add https://github.com/reason-machines/trending-skills --skill weclaw-wechat-ai-bridge in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/weclaw-wechat-ai-bridge/ (personal) or .claude/skills/weclaw-wechat-ai-bridge/ (project).
Which AI agents can use weclaw-wechat-ai-bridge?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is weclaw-wechat-ai-bridge safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains weclaw-wechat-ai-bridge?
It is published by reason-machines in reason-machines/trending-skills. It has 954 recorded installs.
More from reason-machines/trending-skills
openclaw-control-center
reason-machines/trending-skills
Local-first, security-first control center for OpenClaw agents — visibility dashboard with readonly defaults, token attribution, collaboration tracing, and safe write operations.
inkos-multi-agent-novel-writing
reason-machines/trending-skills
Multi-agent CLI system for autonomous novel writing, auditing, and revision with human review gates
claude-hud-statusline
reason-machines/trending-skills
A Claude Code plugin that displays a real-time HUD showing context usage, active tools, running agents, and todo progress in your terminal statusline.
understand-anything-knowledge-graph
reason-machines/trending-skills
Turn any codebase into an interactive knowledge graph using Claude Code skills — explore, search, and ask questions about any project visually.
agency-agents-ai-specialists
reason-machines/trending-skills
A collection of specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, and other AI coding tools — covering engineering, design, marketing, sales, and more.
agent-browser-automation
reason-machines/trending-skills
Headless browser automation CLI for AI agents using native Rust binary with Chrome DevTools Protocol
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available