Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.
</td> <td width="50%" valign="top">What's the weather in Taipei?
The agent finds current data, calls tools, and gives you the answer.
If a tool doesn't exist, it builds one.
</td> </tr> <tr> <td> </td> <td> </td> </tr> <tr> <td width="50%" valign="top">Report TSMC stock price every morning at 8am
The agent asks:
- Where to push results
- What format you want
- When to run
Then creates the schedule automatically.
</td> <td width="50%" valign="top">Find all invoices from last year
Which document mentions Prompt guide?
The agent searches your local files and answers directly.
</td> </tr> <tr> <td> </td> <td> </td> </tr> </table>Summarize today's GitHub commits and generate a progress report
The agent breaks down the task, calls tools, combines results, and replies.
<table> <tr> <td width="33%" valign="top">Agenvoy is also an MCP server.
Claude Code, Codex, OpenCode, and other AI agents can connect and:
- Use all your sandboxed tools
- Auto-build new tools when none exist
- Share every tool across all agents
One line of config. Instant shared tool library.
Tools created in the demo:fetch_weather·fetch_crypto_price
Agenvoy is for developers, technical operators, and AI-heavy workflows that need more than chat:
| Capability | Description |
|---|---|
| Auto tool generation | Builds and saves tools when they're missing |
| Self-scheduling | Create cron jobs with a single sentence |
| Long-term memory | Retains key info and context |
| Knowledge notes | Reads the notes you keep, before it answers |
| File search | Answers from your local files |
| Sub-Agent | Multi-agent collaboration |
| MCP client | Connect to external MCP services via official go-sdk (live tool refresh) |
| MCP server | Expose sandboxed tools to any MCP-compatible agent |
| Reasoning guides | On-demand rules via reasoning_guide(topic=...) |
| Tool Market | Share and install tools |
| Transcription | Audio and video to text |
| Self-improvement | Auto-fixes after execution failures |
Open web.agenvoy.com in your browser to reach the dashboard once the daemon is running on your machine.
<p align="center"> <a href="https://youtu.be/n8tHHSCwOjE"> <img src="https://img.youtube.com/vi/n8tHHSCwOjE/maxresdefault.jpg" alt="Agenvoy Web Dashboard demo" width="640"> </a> </p> <p align="center"> <a href="https://youtu.be/n8tHHSCwOjE">▶ Watch the Web Dashboard walkthrough</a> </p>On MacBook, also run
sudo pmset -c sleep 0to prevent sleep from interrupting schedules.
curl -fsSL https://agenvoy.com/scripts/install.sh | bashA cost-effective model setup to get started:
gpt-oss-20b as the dispatcher modelgpt-oss-120b as the fallback and summary model| Agenvoy | OpenClaw | Hermes-agent | |
|---|---|---|---|
| Install | One command, single binary | pnpm monorepo | pip + docker |
| Multi-model | Auto-picks | Manual switch | Manual switch |
| Chat UI | Buttons / menus / modals | Text only | Text only |
| Builds missing tools | ✅ | ❌ | ⚠️ Skill only |
| Shares tools across agents | ✅ | ❌ | ❌ |
| Works as MCP server | ✅ | ❌ | ❌ |
| Chat verification | 6-digit code | Manual approval | Manual approval |
| Cross-session push | ✅ | ❌ | ⚠️ Limited |
| File search | Semantic + keyword | Chat memory only | Chat memory only |
| Scheduled local workflows | ✅ | ❌ | ⚠️ Limited |
Full documentation at agenvoy.com/docs
This project is licensed under the Apache License 2.0.
Just open an issue to share an idea.
<a href="https://github.com/pardnchiu/agenvoy/graphs/contributors"> <img src="https://contrib.rocks/image?repo=pardnchiu/agenvoy&cache_bust=2026-05-12" alt="Agenvoy contributors" /> </a>©️ 2026 邱敬幃 Pardn Chiu