Klepai: a free desktop chat for the LLM servers you already run

Description and use

Klepai consolidates chat, history, and agent mode for locally hosted LLMs into a single desktop app.

Problem

Managing self-hosted LLMs was fragmented: separate terminals, web UIs, and scattered history.

Outcome

Klepai consolidates chat, history, and agent capabilities for self‑hosted LLMs into a single, local, open‑source desktop application.

Workflow

• 1. Download the platform‑specific build from GitHub Releases.
• 2. Install or point to an existing Ollama/OpenAI‑compatible server.
• 3. Add the server URL in Klepai Settings → Servers and wait for green status.
• 4. Select a model and start chatting.
• 5. (Optional) Switch to Agent mode, target a project folder, and approve tool permissions.

Evidence

I run language models on my own hardware, and the hard part was never running them. It was living with them.

Source

Klepai is a private, self-hosted LLM manager: a desktop chat app for macOS, Windows and Linux that connects to your own model servers over the LAN.

Source

One server list: every Ollama or OpenAI-compatible endpoint, live online status, every model listed

Source

Steps: first chat in five minutes ... 1. Grab a build for your platform from GitHub Releases ... 5. Optional: flip to Agent mode, aim it at a folder, approve tools as asked.

Source