01
Install the bridge
Run the shell installer, Go install command, or Docker image. WeClaw is meant to sit beside the agent binaries you already operate.
Built for real WeChat operator workflows
WeChat AI Agent Bridge
Turn WeChat into the operator surface for Claude, Codex, Gemini, and more.
WeClaw installs locally, opens a QR login on first run, auto-detects ACP, CLI, and HTTP integrations, and routes real chat threads through the agent stack you already trust.
WeChat ClaudeWeChat CodexQR LoginACP / CLI / HTTPMedia + Files
3 transports
ACP, CLI, HTTP
7 integrations
Claude to OpenClaw
1 thread surface
Reply, route, send
Operator Flow
Install. Authenticate. Operate.
Ready
One-line install
first run prompts WeChat QR login
01curl -sSL https://raw.githubusercontent.com/fastclaw-ai/weclaw/main/install.sh | shPrefers ACP when a persistent agent bridge is available.
Falls back to CLI or OpenAI-compatible HTTP when ACP is unavailable.
Cleans markdown into WeChat-safe text and uploads media as messages.
Sends outbound text, images, and files from CLI or local HTTP.
Compatibility
Keep the agent stack you already trust.
Use WeChat as the thread surface without replacing the tools, models, or launch path you already run locally.
ClaudeCodexGeminiKimiCursorOpenCodeOpenClaw
Workflow
From install command to first routed reply in three steps.
Evaluation friction is predictable: show the install path, the authentication step, and the first operator action before asking people to trust the feature list.
02
Authenticate and inspect the stack
On first run, scan the WeChat QR code. WeClaw checks ACP, CLI, and HTTP availability, then writes the active local config.
03
Route the first live thread
Use slash commands, aliases, default-agent switching, and outbound sends to keep the conversation inside WeChat instead of learning another operator UI.
Why WeClaw
The bridge stays narrow. The operator loop stays intact.
WeClaw does a small number of hard things well: message routing, transport selection, media cleanup, outbound sends, and explicit configuration.
Routing
Route each request to the right agent
Keep a default agent for normal traffic, override a single prompt with `/codex` or `/claude`, and switch thread defaults without leaving WeChat.
- Slash commands route a single request, like `/codex` or `/claude`.
- Aliases such as `/cc` and `/cx` keep typing short inside the chat box.
- Default agent selection is persisted to config and survives restarts.
Transport
Prefer persistent ACP when it exists
When ACP is available, WeClaw keeps a persistent JSON-RPC bridge alive so agent processes and session state stay warm.
- ACP is the fastest mode because it avoids a fresh process per message.
- Mode selection is automatic when ACP and CLI are both present.
- Claude, Codex, Gemini, Kimi, Cursor, OpenCode, and OpenClaw fit this model.
Fallback
Drop to CLI or HTTP without losing the flow
If ACP is not available, WeClaw still routes messages through CLI invocation or an OpenAI-compatible HTTP chat endpoint.
- CLI mode can resume compatible sessions using agent-specific flags.
- HTTP mode covers OpenClaw-style endpoints when local binaries are not the right fit.
- Transport choice stays explicit in the config file instead of hiding behind magic.
Media
Send back messages people can actually read
WeClaw flattens agent markdown into WeChat-safe text, turns image URLs into uploads, and keeps files as files instead of broken links.
- Markdown is converted to plain text for better chat readability.
- Image URLs from agent replies can be downloaded and sent as actual image messages.
- Common media types include images, videos, and arbitrary files.
Outbound
Push text or media without waiting
Operators can send text or media even when the user has not just messaged, either from the CLI or from a local HTTP endpoint.
- `weclaw send` pushes outbound text, image, or file payloads from the terminal.
- The local HTTP API runs on `127.0.0.1:18011` while WeClaw is active.
- Outbound flow works for message-driven automations and handoffs.
Operations
Keep the bridge explicit and inspectable
Config lives in `~/.weclaw/config.json`, default-agent selection is explicit, and environment overrides stay visible where they matter.
- Environment overrides handle default agent and OpenClaw gateway values.
- CLI permission flags are documented for operators who need them.
- Background mode, logs, launchd, and systemd keep deployment practical.
Quick Start
The first successful reply should happen fast.
The shortest path matters more than feature volume. The home page should make the first run obvious.
Install the bridge
InstallUse the shell script for the fastest evaluation path, or choose Go or Docker if that better matches your workstation.
install
01curl -sSL https://raw.githubusercontent.com/fastclaw-ai/weclaw/main/install.sh | shScan the QR code once
LoginRun `weclaw start`, authenticate with WeChat, and let the bridge write the local config it will reuse later.
start
01weclaw startSend the first routed prompt
RouteTalk to the default agent, send a one-off request to a named model, or inspect bridge status without leaving the thread.
chat commands
01/codex write a sorting function02/cc explain this diff03/statusCommand Routing
Route one request or change the default without losing the thread.
Stay in the WeChat message box: send to the default agent, switch defaults, or force a one-off route with a slash command.
hello
Send a message to the current default agent without prefixing an explicit route.
/codex write a sorting function
Route one request to Codex without changing the default agent for the rest of the thread.
/cc explain this diff
Use the Claude alias when you want a shorter, chat-friendly route inside the message box.
/claude
Switch the default agent to Claude and persist that choice in local config.
Media
Return usable messages, not raw markdown
WeClaw cleans agent output for WeChat, turns image URLs into actual uploads, and keeps operators out of copy-paste cleanup.
Outbound
Send on demand from CLI or HTTP
Use `weclaw send` or the local endpoint when an automation or handoff needs to push text, images, or files before the next inbound message.
FAQ Preview
Handle setup questions before they block the install.
Most evaluation friction is predictable: supported agents, first-run behavior, config location, and outbound sending.
Prospective users usually need four facts before they install: what WeClaw is, which stacks it supports, where config lives, and how outbound sends work. The FAQ answers those directly.
Read the full FAQWeClaw is a WeChat AI agent bridge. It connects WeChat message threads to tools such as Claude, Codex, Gemini, Kimi, Cursor, OpenCode, and OpenClaw.
Get Started
Install the bridge, scan once, and run WeChat as part of your agent workflow.
The upstream repository currently labels the project for personal-learning usage. Review the README, license, and your own operational requirements before moving beyond evaluation.