OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Gitagent

Gitagent is an AI agent framework with a CLI and TypeScript SDK. It defines agent configuration, identity, behavioral rules, memory, tools, skills and hooks as files in a Git repository, and provides workflows for running agents against local directories or GitHub repositories.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Gitagent — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Gitagent when you want agent configuration and memory to be reviewable and versioned through Git, or need a CLI or in-process SDK to apply an agent to code tasks.

Who it is for

  • Developers who want to build and configure agents using Git-managed files.
  • Teams that want agent rules, capabilities and memory history maintained in a repository.
  • TypeScript developers embedding agent queries in an application.

Documented uses

  • Create an agent configuration and identity in a project directory.
  • Ask an agent to explain or summarize code and suggest improvements.
  • Use an agent to make a requested change to a GitHub repository and push work to a session branch.
  • Stream agent responses and events from a TypeScript application.
Before you choose

Requirements & limits

The repository identifies the project as MIT-licensed open-source software. The documented core installation uses npm; the installer requests API key setup. GitHub repository mode requires a token supplied by flag or environment variable.

  • Agent configuration is split across named files and directories, making changes trackable through Git history and diffs.
  • The CLI supports both a local directory mode and a GitHub repository mode with session branches.
  • The TypeScript SDK exposes an in-process query interface that streams agent events.
  • Voice mode and the web UI are distributed separately from the slim CLI and SDK.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run an agent on a local project directory

Ask Gitagent to explain a project and suggest improvements.

Before you start

  • Gitagent installed
  • Node.js 18 or later, npm and Git
  • An OpenAI API key

Steps

  1. Set OPENAI_API_KEY in the environment.

  2. Run gitagent --dir ~/my-project "Explain this project and suggest improvements".

Expected outcome

Gitagent scaffolds `agent.yaml`, `SOUL.md` and `memory/` on first run and starts the agent.

Guide limitations

  • The documented example uses OpenAI; the README also describes a model override option.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
open-gitagent/gitagent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction