Gneol

A runtime for .gneol files — describe your AI program in one plain-text file, deploy it with one command, and Gneol runs it. No external server to deploy. No database. Just one binary that contains the CLI, the model runtime, and the chat terminal.

Installation

One command puts the Gneol runtime on your machine. That's it — no separate service to install, no database to set up.

bash — install
$ curl -sSL https://raw.githubusercontent.com/Gneol/Gneol/main/install.sh | bash
 Gneol installed → /usr/local/bin/gneol

$ gneol --version
gneol 1.0.0
$ curl -sSL https://raw.githubusercontent.com/Gneol/Gneol/main/install.sh | bash
$ curl -sSL https://raw.githubusercontent.com/Gneol/Gneol/main/install.sh | bash -s -- --version v1.0.0
# Download from GitHub Releases:
#   https://github.com/Gneol/Gneol/releases
#
# macOS (arm64) → gneol-darwin-arm64.tar.gz
# Linux (x64)   → gneol-linux-x64.tar.gz

Write a Program

Everything in Gneol starts with a file.

A .gneol file describes your program.

Name it, give it a model. Add tools, subagents, schedules — the pieces your agent needs to work. It's plain text, so it reads like a spec, not a codebase.

Save it and you're ready to deploy.

hello.gneol
// an agent, in one file
program("Hello World")
  .model("fast-llm")

model("fast-llm")
  .provider("openrouter")
  .modelId("openai/gpt-4o-mini")
  .apiKey("OPENROUTER_API_KEY")

// add subagents, triggers, schedules later

Deploy & Run

One command turns your file into a live agent. Gneol handles the agentic loop — calling models, firing triggers, delegating to subagents — so you just talk to it.

bash — deploy
$ gneol deploy -f hello.gneol -i
 Deployed. Agent "Hello World" is live.

$ gneol
Hello World ❯ hi there
💬 Hello! I'm your Hello World agent — ask me anything.

Why Gneol?

Single Binary

CLI, LLM runtime, and terminal in one self-contained executable. Just download and run.

File-Driven Agents

Declare agents, models, triggers, tools, and MCP servers in a single .gneol file.

Automated Triggers

Time-based and event-based triggers fire your workflows automatically. The AI checks the conditions itself, so triggers only run when they should.

MCP & Custom Tools

Plug in tools from the Model Context Protocol (MCP) ecosystem, or write your own with the Gneol SDK.

Safe by Default

File access is permission-controlled per file. Changes are backed up automatically. Long-running tasks run in isolated subagents.

macOS & Linux

Precompiled binaries for macOS arm64 and Linux x64. One install command gets you going.

VS Code IntelliSense

Syntax highlighting, autocomplete, and inline docs for .gneol files — right in your editor.

Author .gneol files with confidence.

Install the official Gneol IntelliSense extension and get syntax highlighting, autocomplete, and documentation tooltips for every directive.

Install from Marketplace

bash — install
$ code --install-extension Gneol.gneol-intellisense
 Installed Gneol IntelliSense extension.

Stay in the loop

Watch the repo on GitHub to get notified about releases and updates. Found a bug or have a question? Email us.