π“‚€ v1.0.0 Β· GPL-3.0 Β· macOS

An autonomous AI agent, powered by your local LLM.

Pine Chat is a macOS AI agent app that connects to a local model like LM Studio. Hand it a design document (.md) and hands-off mode will build the app for you, right up to the final build.

Open source (GPL-3.0-or-later) Β· Built by Yuki Orita

Features

Research, build, and stay connected β€” all in one agent.

More than a chat window: coding, research, and outside integrations run through a single local AI agent.

π“‚€

Auto-connects to your local AI

Connects automatically to LM Studio (port 1234) or any OpenAI-compatible API. A 20B-class model or larger is recommended.

π“…±

Web search via SearXNG

Privacy-respecting web search through SearXNG, which can also run as a background service on macOS.

𓃭

App design & autonomous build

Give it a design document (.md) and "hands-off" mode will implement the app all the way to the final build.

π“…”

Markdown RAG

Load .md files as a reference dictionary (RAG) so the agent can draw on project-specific knowledge.

π“€€

Agent integrations

Connects to Discord, Telegram, and your calendar to summarize activity and hold conversations for you.

β—†

Open source

Released under GPL-3.0-or-later. Source is freely available to read and modify on GitHub.

How it works

Get started in 3 steps

  1. Start a local LLM server

    Load a model and start a server in LM Studio (default port 1234).

  2. Install Pine Chat

    Download the latest .dmg from the GitHub Releases page and launch it.

  3. Start chatting

    It connects to your local AI automatically on launch. Create a project and start building, researching, or just chatting.

Requirements

  • β—† macOS 14.0 or later
  • β—† A local LLM server (e.g. LM Studio)
  • β—† Recommended: 20B-class model or larger
  • β—† Node.js / npm if running from source

Running from source

npm install then npm start, or run ./build.sh to build a .dmg.

Open the repository β†’