chat-ollama

ChatOllama is an open source agentic app for running AI agents across local and hosted models.

What is chat-ollama?

ChatOllama is an open source agentic app for running AI agents across local and hosted models.

Overview of chat-ollama

What it is

ChatOllama is an open source agentic application for running AI agents across local and hosted models. It is built on Pi Durable and provides a SvelteKit web interface for persistent agent conversations, document knowledge bases, and tools. Data is stored locally in SQLite and files, with no separate database or vector service required.

Key features

  • Chat with your choice of model: connect AI providers or local models through OpenAI-compatible endpoints, including Ollama, and switch models within a conversation.
  • Persistent conversations: stream responses, inspect tool activity, and keep tasks running after closing the browser.
  • Document knowledge bases: upload PDF, Markdown, and plain-text documents, then ask questions with source citations.
  • Agent tools: use built-in file and shell tools, or connect local and remote tools through Model Context Protocol (MCP).
  • Reusable skills: install skills and choose which ones are available in each conversation.

Use cases

ChatOllama can be used for running AI agents that interact with local and hosted models, managing persistent conversations with tool activity inspection, building document knowledge bases from uploaded files, and integrating custom tools via MCP. It is suitable for users who want a self-hosted, agentic chat application with local data storage.

Getting started

Install Node.js 24 and pnpm 10.8.1, then clone the repository and build from the rewrite/ directory:shgit clone https://github.com/sugarforever/chat-ollama.gitcd chat-ollama/rewritepnpm installpnpm buildConfigure a chat endpoint and start the app. This example uses a running local Ollama server; replace your-chat-model with an installed model ID:shexport HOST='127.0.0.1'export ORIGIN='http://localhost:3000'export CHAT_BASE_URL='http://127.0.0.1:11434/v1'export CHAT_MODEL_ID='your-chat-model'# Export CHAT_API_KEY if your provider requires an API key.pnpm startOpen http://localhost:3000. You can add providers and change models in Settings. Configure a separate embedding endpoint and model there before indexing knowledge documents. pnpm start does not load .env automatically; export variables in your shell. Data is saved in rewrite/data by default. Set DATA_DIR to use another location. The app has no login, so the example binds it to your local computer.

License and pricing

The license is not stated in the provided metadata or README. The project is listed as open source with pricing type open_source.

這是什麼

ChatOllama 是一個開放原始碼的代理應用程式,用於在本地端與託管模型上執行 AI 代理。它基於 Pi Durable 建構,並提供 SvelteKit 網頁介面,支援持久性代理對話、文件知識庫與工具。資料儲存在本機的 SQLite 與檔案中,無需額外的資料庫或向量服務。

主要功能

  • 選擇模型聊天:透過 OpenAI 相容端點連接 AI 提供者或本地模型(包括 Ollama),並可在對話中切換模型。
  • 持久性對話:串流回應、檢視工具活動,並在關閉瀏覽器後繼續執行任務。
  • 文件知識庫:上傳 PDF、Markdown 與純文字文件,然後提問並取得來源引用。
  • 代理工具:使用內建的檔案與 Shell 工具,或透過 Model Context Protocol (MCP) 連接本地與遠端工具。
  • 可重複使用的技能:安裝技能,並在每個對話中選擇可用的技能。

使用情境

ChatOllama 可用於執行與本地及託管模型互動的 AI 代理、管理附帶工具活動檢視的持久性對話、從上傳檔案建立文件知識庫,以及透過 MCP 整合自訂工具。適合想要自架、具備代理功能且資料儲存在本機的聊天應用程式使用者。

快速開始

安裝 Node.js 24 與 pnpm 10.8.1,然後複製儲存庫並從 rewrite/ 目錄建置:shgit clone https://github.com/sugarforever/chat-ollama.gitcd chat-ollama/rewritepnpm installpnpm build設定聊天端點並啟動應用程式。以下範例使用執行中的本地 Ollama 伺服器;請將 your-chat-model 替換為已安裝的模型 ID:shexport HOST='127.0.0.1'export ORIGIN='http://localhost:3000'export CHAT_BASE_URL='http://127.0.0.1:11434/v1'export CHAT_MODEL_ID='your-chat-model'# 如果您的提供者需要 API 金鑰,請匯出 CHAT_API_KEY。pnpm start開啟 http://localhost:3000。您可以在設定中新增提供者與變更模型。在索引知識文件之前,請先在設定中設定獨立的嵌入端點與模型。pnpm start 不會自動載入 .env;請在 Shell 中匯出變數。資料預設儲存在 rewrite/data。設定 DATA_DIR 可使用其他位置。此應用程式沒有登入功能,因此範例將其綁定到您的本機電腦。

授權與價格

提供的元資料或 README 中未說明授權條款。該專案列為開放原始碼,定價類型為 open_source。

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/sugarforeverchat-ollama.svg)](https://yunodb.com/tools/sugarforeverchat-ollama?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/sugarforeverchat-ollama?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/sugarforeverchat-ollama.svg" alt="Featured on YunoDB" height="20"></a>