Open Source · Apache 2.0

A Personal AI Agent
& MCP Server on Your Machine

Say what you need in one sentence — the agent builds the tool, tests it, and reuses it.
Every tool is sandboxed and shared with Claude Code, Codex, and any MCP agent.

curl -fsSL https://agenvoy.com/scripts/install.sh | bash
agen
What's the weather in Taipei?
 
⏵ Search Tools(weather)
⏵ Plug Tool(Script fetch_weather)
 
⏺ Currently 28°C in Taipei, partly cloudy with 72% humidity.
  Wind from the northeast at 12 km/h.
 
  ⏜ 3.2s · claude-sonnet-4-6 · ↑2.1K · ↓340
 
Report TSMC stock price every morning at 8am on Telegram
 
⏵ Plug Tool(Script fetch_yahoo_finance)
⏵ Add Schedule(0 8 * * *)
 
⏺ Done. Scheduled daily at 08:00 — results push to Telegram.
  ⏜ 5.8s · claude-sonnet-4-6 · ↑3.4K · ↓520
Web Dashboard

Drive Your Agent From the Browser

Manage sessions, tools, schedules, and memory from a browser. Open web.agenvoy.com once the daemon is running on your machine — it connects to your local agent, nothing leaves your device.

Features

Everything You Need in One Binary

Auto-built tools and a built-in MCP server at the core — plus multi-model routing, scheduling, and memory, all in a single Go binary.

Auto Tool Generation

Ask for anything. If no tool exists, the agent builds one — writes the script, tests it in a sandbox, and registers it. Next time, it's already there.

MCP Server & Client

Server mode shares every sandboxed tool with Claude Code, Codex, and any MCP client — which can auto-build new tools too. Client mode calls external MCP services.

Multi-Model Dispatch

10 LLM providers behind one interface. The dispatcher routes each task to the best model automatically.

Scheduler

Cron jobs and one-shot tasks with skill binding. Daemon fires them, hot-reloads on change, auto-disables on failure.

3-Tier Memory

Context window, semantic vector search, full-text SQLite archive. Cross-session error memory with 90-day TTL.

Sandboxed Execution

Every command and script runs inside an OS-native sandbox — bubblewrap on Linux, sandbox-exec on macOS.

Skill System

Loadable markdown instruction packs with YAML frontmatter. Slash-command activation, natural language trigger, or cron-bound.

Self-Improvement

When a skill fails, the agent rewrites it, git-commits the fix, and retries. Rollback available via git_rollback tool.

RAG Integration

Optional KuraDB child process for external document search. Keyword + semantic dual-track over your personal knowledge base.

How It Works

Capability Gap → Auto-Build

When no tool fits a request, the agent builds one in real-time — finds an API, writes the script, tests it, and saves it for reuse. No code required.

Step 1

Detect Gap

User asks for live data. No matching tool found.

Step 2

Find API

Search public APIs, fetch docs, pick the best match.

Step 3

Write & Test

Generate script + schema. Run test_tool to verify.

Step 4

Call & Share

Execute the new tool. Auto-persisted for all agents.

MCP

Share Tools Across All Your Agents

One config line gives Claude Code, Codex, and any MCP agent your entire sandboxed tool library — and they can auto-build new tools that everyone instantly shares.

Server

Expose Your Tools

Any MCP-compatible agent connects via stdio and gets access to all tools — built-in, script, API, and extension.

// claude_desktop_config.json
{
  "mcpServers": {
    "agenvoy": {
      "command": "agen"
    }
  }
}
Claude Code Codex OpenCode Cursor
Client

Call External Services

Connect third-party MCP servers via stdio or HTTP/SSE. Tools auto-registered and available to the agent immediately.

// ~/.config/agenvoy/mcp.json
{
  "github": {
    "command": "npx",
    "args": ["@modelcontextprotocol/server-github"]
  }
}
stdio HTTP/SSE Hot Reload
Integrations

Talk to Your Agent Anywhere

Same agent, same tools, same memory — accessible from terminal, chat apps, HTTP, or other AI agents.

TUI

Interactive terminal with slash commands and session switching

Telegram

OTP-authenticated bot with HTML output and voice

Discord

Guild-verified bot with markdown and button confirms

REST API

OpenAI-compatible chat completions endpoint

MCP Server

Expose tools to Claude Code, Codex, and more

Providers

10 LLM Providers, One Interface

Unified Agent.Send() interface. Dispatcher auto-routes tasks to the best model.

Anthropic
Claude 4.x
OpenAI
GPT · o-series
Codex
ChatGPT OAuth
Gemini
2.x · 3.x
Copilot
GitHub OAuth
Nvidia
NIM API
xAI Grok
Grok 4 · 3
DeepSeek
Chat · Reasoner
OpenRouter
200+ models
Compat
Ollama · vLLM
Tools

60+ Built-in Tools, Infinitely Extensible

From file ops to web search, from RAG queries to image generation. Missing a tool? The agent builds it.

File & Search

Read, write, patch, list, glob, and search local files with policy guards.

read_filewrite_filepatch_file list_filesglob_filessearch_files

Web & HTTP

Fetch pages with readability, search the web, browse news, HTTP requests.

fetch_pagesearch_websearch_google_news send_http_requestdownload_file

Orchestration

Spawn subagents, delegate to external CLIs, run cross-reviews, plan.

invoke_subagentinvoke_external_agent generate_planrun_commandrun_skill

Memory & RAG

Search history, persist error resolutions, query external docs via KuraDB.

search_chat_historyremember_error search_error_historylist_ragsearch_rag

Media & Interactive

Transcribe audio/video, generate images, interactive prompts, secrets.

transcribe_mediagenerate_image ask_userstore_secretcalculate

Extensibility

Auto-generate tools from natural language. Drop scripts, API descriptors, or connect MCP.

script_*api_*ext_* mcp__*write_tooltest_tool
Get Started

Up and Running in 60 Seconds

One command to install, one command to start. Add a provider and you're ready.

1

Install

Single binary. macOS and Linux.

curl -fsSL https://agenvoy.com/scripts/install.sh | bash
2

Add Provider

Connect any of 10 LLM providers.

agen model add
3

Create Session

Name it. Persists across restarts.

agen session new my-agent
4

Launch

TUI opens. Daemon auto-starts.

agen

Start Building with Agenvoy

One binary. One install. Infinite tools.

中文