Multi AI Agent Bridge — chat to AI agents (Claude, Codex, Gemini, Kimi, Cursor, Copilot and more).
Multi AI Agent Bridge — chat to AI agents (Gemini, Codex, Gemini, Kimi, Gemini, Gemini and more).
# Start (runs as background daemon; auto-login if no account saved)
agent-bridge start --provider weixin
On first start, AgentBridge will:
~/.agent-bridge/config.json
Use agent-bridge login --provider weixin to add additional WeChat accounts.
Projects:
| Project | Description |
|---|---|
AgentBridge.CLI | CLI entry point (agent-bridge executable) — commands, daemon management |
AgentBridge.Core | Core agent abstraction — ACP/CLI agent drivers, config, markdown conversion |
AgentBridge.Weixin | WeChat provider — ILink long-poll client, message handling, CDN upload, HTTP API |
Agent integration modes:
| Mode | How it works | Supported agents |
|---|---|---|
| ACP | Long-lived subprocess communicating via stdio JSON-RPC 2.0. Fastest — reuses process and session. | Gemini, Codex, Kimi, Gemini, Gemini, OpenCode, OpenClaw |
| CLI | Spawns a new process per message. Supports --resume for session continuity. | Gemini (gemini -p), Codex (codex exec), Gemini |
When both ACP and CLI variants are installed, ACP is automatically preferred.
agent-bridge <command> --provider <provider> [options]
| Command | Description |
|---|---|
login | Add a WeChat account via QR code scan |
start | Start the agent bridge (background daemon by default) |
stop | Stop the background daemon |
restart | Restart the background daemon |
status | Check if the daemon is running |
start options| Option | Description |
|---|---|
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.
Workflows from the Neura Market marketplace related to this Gemini resource