agenvoy

A local AI agent that can build, test, and reuse its own tools

Agenvoy runs on your machine, handles multi-step work, searches local files, schedules recurring tasks,
and exposes its tool library to other agents through MCP.

English · 繁體中文

Why Agenvoy

• Build missing tools instead of stopping
• Share one sandboxed tool library across Agenvoy, Claude Code, Codex, and more
• Run local workflows with scheduling, memory, and file search
• Use it as both an agent app and an MCP server

What you can do with it

Ask for live answers 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.	Turn one sentence into automation 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.
Ask your local files questions Find all invoices from last year Which document mentions Prompt guide? The agent searches your local files and answers directly.	Finish multi-step work Summarize today's GitHub commits and generate a progress report The agent breaks down the task, calls tools, combines results, and replies.

Works with the agents you already use

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

Claude Code creates a weather tool (1)	Codex reuses it and creates a crypto tool (2)	Agenvoy tests both tools (3)

Who it's for

Agenvoy is for developers, technical operators, and AI-heavy workflows that need more than chat:

• People who want local execution with guardrails
• Teams that want reusable tools across agents
• Users who need automation, file search, and scheduled reporting in one place

---

Core capabilities

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
File search	Answers from your local files
Sub-Agent	Multi-agent collaboration
MCP client	Connect to external MCP services
MCP server	Expose sandboxed tools to any MCP-compatible agent
Tool Market	Share and install tools
Transcription	Audio and video to text
Self-improvement	Auto-fixes after execution failures

---

Web Dashboard

Open web.agenvoy.com in your browser to reach the dashboard once the daemon is running on your machine.

▶ Watch the Web Dashboard walkthrough

One-line install

On MacBook, also run sudo pmset -c sleep 0 to prevent sleep from interrupting schedules.

curl -fsSL https://agenvoy.com/scripts/install.sh | bash

---

Developer Recommendations

A cost-effective model setup to get started:

• Apply for a free NVIDIA NIM API token, then use it for:
  • gpt-oss-20b as the dispatcher model
  • gpt-oss-120b as the fallback and summary model
• Use a subscription plan as your primary model:
  • OpenAI ChatGPT Plus ($20/mo)
  • SuperGrok ($30/mo)

---

How it compares

	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

---

Docs

Full documentation at agenvoy.com/docs

• Getting Started
• Sessions & Agents
• Providers
• Built-in Tools
• MCP Server
• MCP Client
• Memory System
• Skill System
• Sandbox
• Architecture

License

This project is licensed under the Apache License 2.0.

Community Contributors

Contributor

Just open an issue to share an idea.

---

©️ 2026 邱敬幃 Pardn Chiu