Your Autonomous AI Agent

VexNet is an AI agent that reads, writes, searches, browses, and builds other agents. Runs locally with Ollama. Chat via CLI or Telegram. No cloud required.

curl -fsSL https://vexnet.ai/install.sh | bash

Installs Python (if needed), Ollama, AI models, and VexNet. Takes 2-5 minutes.

irm https://vexnet.ai/install.ps1 | iex

Run in PowerShell as Administrator. Installs Ollama, AI models, and VexNet.

# Requires Python 3.12+ and Ollama already installed
pip install vexnet

Manual install. You'll need to set up Ollama separately (see setup guide below).

What Vex Can Do

Read, Write & Edit Code

Explore codebases, write new files, make precise edits. Understands project structure and conventions.

Run Commands

Execute shell commands, run tests, build projects. Graduated security controls so you stay in charge.

Search the Web

Web search, fetch pages, and full browser control via headless Chromium for complex research tasks.

Build Sub-Agents

Dynamically creates specialist agents for complex tasks. A scraper agent, a docs agent, a test agent — on demand.

Telegram Integration

Chat with Vex from your phone. Group monitoring with intelligent interjections. Persistent conversation memory.

Runs 100% Local

Uses Ollama for local AI. Your data never leaves your machine. No API keys needed to get started.

Personality & Memory

Vex has a unique personality that evolves over time. Remembers users, learns preferences, and grows curious about you.

Security First

4-level autonomy system, secret redaction, prompt injection detection, workspace sandboxing, and full audit logs.

Setup Guide

1

Install Ollama

Ollama runs AI models locally on your machine. The installer handles this automatically, but if you need to install manually:

  • macOS/Linux: curl -fsSL https://ollama.com/install.sh | sh
  • Windows: Download from ollama.com/download
2

Pull AI Models

VexNet needs a language model and an embedding model:

ollama pull glm4:latest
ollama pull nomic-embed-text:latest

You can use any Ollama model. Popular alternatives: llama3.2, mistral, qwen2.5. Update the model name in your config file after installing.

3

Install VexNet

Use the one-line installer above, or install with pip:

pip install vexnet
4

Start Chatting

Open a terminal and run:

vex

That's it! Vex will launch an interactive session. Type a task and watch it work.

5

Telegram Bot (Optional)

Chat with Vex from your phone:

  • Open Telegram and message @BotFather
  • Send /newbot and follow the prompts to create your bot
  • Copy the bot token
  • Set the token: export TELEGRAM_BOT_TOKEN=your_token_here
  • Start: vex --telegram
  • Message your bot on Telegram!
6

Configuration

VexNet looks for config in ./vex.toml or ~/.vex/config.toml. Key settings:

  • LLM provider: Switch between ollama, anthropic, or openai
  • Model: Any Ollama model or cloud API model
  • Autonomy level: 0 (ask everything) to 3 (full auto)
  • Telegram: Bot token, allowed users, group settings