Run Hermes Agent and OpenClaw on the same WeChat account
# Add to your Claude Code skills
git clone https://github.com/AaronWong1999/hermesclawGuides for using ai agents skills like hermesclaw.
Last scanned: 5/16/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-16T06:23:22.710Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": false
}Run Hermes Agent, OpenClaw, and OpenCode on the same WeChat account. One command to install.
在同一个微信账号上同时多开 Hermes Agent、OpenClaw 和 OpenCode。一条命令安装。
Both Hermes Agent and OpenClaw now support WeChat natively — but you can't run both on the same account. Each gateway exclusively locks the iLink connection. If you start both, one gets 403 errors and drops messages. OpenCode adds a third AI brain via its ACP subprocess protocol.
HermesClaw solves this by becoming the sole iLink poller, then running two local proxy servers (for Hermes and OpenClaw) plus a direct ACP bridge (for OpenCode). Each gateway believes it's talking to the real iLink API.
The new OpenCode support also lets you Vibe Code via WeChat voice messages — just speak and OpenCode handles it, backed by four free models including MiniMax M2.5 Free. You can also use it alongside the other two agents to complement each other — fixing their issues, tracing bugs, or inspecting the local environment.
现在 Hermes 和 OpenClaw 都原生支持微信了——但你不能在同一个账号上双开。 每个 Gateway 会独占 iLink 连接。HermesClaw 解决这个问题：它作为唯一的 iLink 轮询者，运行两个本地代理，让两个 Gateway 各连各的。
新版还增加了 OpenCode 支持，现在你可以用微信语音直接进行 Vibe Coding 了，调用的就是 OpenCode 中包含 MiniMax M2.5 Free 在内的四个免费模型。你也可以用它和另外两个 Agent 互相补充使用，比如帮它们修问题、查 bug、看本机环境。
Special thanks to the Hermes Agent team at Nous Research for recognizing and recommending HermesClaw in the Community section of their official GitHub README.
特别感谢 Nous Research 的 Hermes Agent 团队，在其 GitHub 官方 README 的 Community 区收录并推荐 HermesClaw。
Official reference: Hermes Agent README - Community
| | Without HermesClaw | With HermesClaw |
|---|---|---|
| Hermes on WeChat | ✅ Works (native gateway) | ✅ Works |
| OpenClaw on WeChat | ✅ Works (clawbot) | ✅ Works |
| OpenCode on WeChat | ❌ No WeChat support | ✅ via ACP bridge |
| Both on same account | ❌ Token conflict / 403 | ✅ /both mode |
| All three on same account | ❌ Impossible | ✅ /three mode |
| Voice messages | ✅ Each handles natively | ✅ Transcription forwarded |
| Images / video / files | ✅ Each handles natively | ✅ Raw iLink msg forwarded |
| Switching agents | — | /hermes, /openclaw, /opencode, /both, /three |
┌────────── iLink API ──────────┐
│ ilinkai.weixin.qq.com │
└──────────┬────────────────────┘
│
(sole poller / token owner)
│
┌──────────▼────────────────────┐
│ HermesClaw v3 │
│ routes by /hermes /openclaw │
│ /opencode /three │
│ queues raw iLink messages │
├────────┬──────────┬────────────┤
│ │ │
Proxy A Proxy B ACP Bridge
(:19999) (:19998) (subprocess)
openclaw hermes opencode acp
│ │ │
▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────┐
│ openclaw │ │ hermes │ │ opencode │
│ gateway │ │ gateway │ │ process │
└────┬─────┘ └────┬─────┘ └────┬─────┘
│ │ │
sendmessage sendmessage send_text_ilink
└─────┬──────┘ │
│ (proxy forwards) │
└──────────────────►┘
to iLink
HermesClaw is a thin Python proxy (~500 lines). It does not process media, call agent APIs, or touch agent memory. It just queues and forwards raw iLink protocol messages. Each gateway handles its own media decryption, markdown formatting, and AI interaction natively.
HermesClaw 只是一个轻量转发代理（~500 行），不处理媒体、不调 Agent API、不动记忆。每个 Gateway 原生处理自己的媒体解密和 AI 交互。
Before installing HermesClaw, you need at least one of:
openclaw-weixin) — installed and logged into WeChathermes gateway configuredBoth installed = full dual-open. One installed = single-agent mode with the option to add the other later.
安装 HermesClaw 前，需要至少安装以下其中一个：OpenClaw 的 clawbot，或者 Hermes 的微信 Gateway。
curl -fsSL https://raw.githubusercontent.com/AaronWong1999/hermesclaw/main/install.sh | bash
For non-interactive / automated installs (skips all confirmation prompts):
curl -fsSL https://raw.githubusercontent.com/AaronWong1999/hermesclaw/main/install.sh | HERMESCLAW_YES=1 bash
# or, when running the script directly:
bash install.sh -y
The installer will:
baseUrl → http://127.0.0.1:19999 (proxy A)WEIXIN_BASE_URL → http://127.0.0.1:19998 (proxy B)/opencode and /three)requests, python-dotenv)hermesclaw systemd serviceAfter install, restart your gateways and send /whoami in WeChat.
Drop this into any AI agent on the target machine:
Run: curl -fsSL https://raw.githubusercontent.com/AaronWong1999/hermesclaw/main/install.sh | bash
Then read README.md and install.sh from the installed HermesClaw directory.
Detect whether Hermes Agent, OpenClaw, their WeChat gateways, python3, pip3,
and systemd are present. At least one gateway must be configured. Extract
the iLink token from the first available gateway account file. Patch
openclaw-weixin baseUrl to http://127.0.0.1:19999 and Hermes WEIXIN_BASE_URL
to http://127.0.0.1:19998. Install dependencies and systemd service.
Also detect OpenCode CLI: run `command -v opencode` or check
~/.npm-global/bin/opencode. If not found, suggest installing with:
npm install -g opencode-ai
Set OPENCODE_CMD in .env to the detected path (or empty if not found).
OPENCODE_MODEL defaults to opencode/minimax-m2.5-free (free, no API key needed).
If Hermes Agent WeChat gateway is detected, the installer will offer to patch
weixin.py to disable newline-based message splitting (recommended). Accept
this patch so long replies are sent as single messages instead of being split
by paragraphs. The fix script is at fix_hermes_splitting.sh.
Restart gateways. Verify /whoami works in WeChat.
| Command | Action |
|---------|--------|
| /hermes | Route to Hermes only |
| /openclaw | Route to OpenClaw only |
| /opencode | Route to OpenCode only (via ACP bridge) |
| /both | Route to Hermes + OpenClaw (reply from both) |
| /three | Route to all three (reply from all) |
| /whoami | Show current route and status |
| anything else | Forward to the active agent(s) |
Default route is Hermes. In /both and /three modes, proxy replies are prefixed with [Hermes Agent] / [OpenClaw] / [OpenCode] for attribution.
OpenCode connects via its native ACP subprocess protocol — no proxy port needed. Install it first:
npm install -g opencode-ai
Then set OPENCODE_CMD in .env (the installer auto-detects it). Use /opencode or /three once OpenCode is installed.
hermesclaw.py # ~870 lines. Triple-proxy router + ACP bridge.
install.sh # Smart auto-detecting installer (-y for non-interactive).
fix_hermes_splitting.sh # Patch Hermes weixin.py (optional, recommended).
tests/ # 82 pytest tests (core, proxy, ACP, recovery).
README.md
LICENSE
docs/ # Screenshots and media.
HermesClaw forwards raw iLink protocol messages to each gateway. This means:
HermesClaw does not do AES decryption, CDN downloads, or media re-encoding. That's each gateway's job.
Stop and disable the hermesclaw systemd service. Restore openclaw-weixin
account .bak files. Remove WEIXIN_BASE_URL override fr
No comments yet. Be the first to share your thoughts!