[opensourcedex]

deepchat is a free, open source ai interaction & interfaces project written in TypeScript and released under Apache-2.0. It has 6,328 GitHub stars, 734 forks and 8 open issues, and was last pushed 14 hours ago. On this registry it ranks #43 of 76 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available. It gained 2 stars over the last 3 tracked days.

What is deepchat?

What it is

DeepChat is an open-source, local-first AI agent desktop client built with TypeScript under the Apache-2.0 license. It lives in the AI interaction and interfaces ecosystem, distributed as a cross-platform Electron application, and it gathers models, tools, Skills, agent runtimes, Tape, and long-running sessions into a single desktop app. Cloud APIs such as OpenAI, Gemini, and Anthropic work alongside locally deployed Ollama models, and any provider exposing an OpenAI, Gemini, or Anthropic API format can be connected.

The concrete problem it solves is fragmentation of agent work across separate chat clients, terminal runners, and bot frameworks. DeepChat's sessions and agent processes follow the Tape.systems philosophy: the process is kept, so context, tool calls, requests, and results stay recoverable, traceable, and inspectable. That matters when agent work becomes complex and token budgets must be inspected. Skills can be installed, imported, exported, and enabled per conversation for code review, documents, frontend work, and Office or PDF tasks. Native ACP integration runs ACP-compatible coding and task agents as first-class entries in the model selector, and remote control integrations extend the same agents into messaging workflows on Telegram, Feishu/Lark, QQBot, Discord, and WeChat iLink.

Key capabilities

  • Runs DeepChat agents, ACP agents, and remote-ready bots inside one local desktop app.
  • Preserves recoverable session history, request context, and token budget inspection under the Tape.systems philosophy.
  • Supports MCP for tool and context integration.
  • Supports installable, importable, exportable Skills that can be enabled per conversation.
  • Runs ACP-compatible coding and task agents as first-class entries in the model selector.
  • Connects to OpenAI, Gemini, Anthropic, and locally deployed Ollama models, plus any provider in those API formats.
  • Provides remote control integrations for Telegram, Feishu/Lark, QQBot, Discord, and WeChat iLink.

Who uses it and how

  • Developers running coding and task agents through ACP integration directly from the model selector.
  • Teams enabling reusable Skills per conversation for code review, document handling, frontend work, and Office or PDF tasks.
  • Users mixing cloud APIs with local Ollama models in a single desktop client.
  • Operators routing agent conversations into messaging platforms such as Telegram, Discord, Feishu/Lark, QQBot, and WeChat iLink.
  • Anyone needing to trace request context, tool calls, and results after a long-running agent session.

Getting started

The README quick start path is download and install, then configure models, then start conversations; the hosted page sits

project readme (upstream, from github) — read inline

DeepChat AI Assistant Icon

DeepChat - Open-Source Local-First AI Agent Desktop Client

DeepChat is an open-source, local-first AI agent desktop client with rich agent capabilities, designed around the Tape.systems philosophy, with support for MCP, Skills, ACP, and remote control integrations for messaging apps.

Stars Badge Forks Badge Pull Requests Badge Issues Badge License Badge Downloads Ask DeepWiki

ThinkInAIXYZ%2Fdeepchat | Trendshift

中文 / English / 日本語

❤️ Sponsor

Thanks to APIMart for sponsoring this project! APIMart is a low-cost API platform for AI image & video generation — GPT-Image-2 from $0.006/image, 160+ images per dollar. One async API covers both image and video: submit a task, get an ID, fetch results via polling or callback. Batch tens of thousands of images without timeouts, switch models without changing code. Pay-as-you-go with no monthly fee — sign up here to get started.
Thanks to OpenModel for sponsoring this project! OpenModel offers client-specific discounts of up to 90% for Codex and 60% for Claude Code across supported models, helping developers cut API costs without changing how they work. Just connect your OpenModel API key and keep using Codex or Claude Code as usual — supported clients are detected automatically and discounted routes are applied with no extra parameters or manual routing required. You can also configure fallback behavior per API key, choosing whether to continue at standard pricing or stop when a discounted route is temporarily unavailable. DeepChat users can register via this link.
PackyCode is a stable, high-performance API relay provider, offering relay services for Claude Code, Codex, Gemini, and more. With automatic failover, smart routing, and unlimited concurrency, it turns AI into a real productivity tool. Register via this link and get started!

📑 Table of Contents

🚀 Project Introduction

DeepChat is a powerful open-source, local-first AI agent desktop client that brings together models, tools, Skills, agent runtimes, Tape, and long-running sessions in one desktop app. Whether you're using cloud APIs like OpenAI, Gemini, Anthropic, or locally deployed Ollama models, DeepChat delivers a smooth user experience.

DeepChat's sessions and agent processes follow the Tape.systems philosophy: keep the process, so context, tool calls, requests, and results stay recoverable, traceable, and inspectable. It also provides strong MCP support, installable Skills, ACP agent integration, and remote control for Telegram, Feishu/Lark, QQBot, Discord, WeChat iLink, and other messaging workflows.

DeepChat Light Mode
DeepChat Dark Mode

💡 Why Choose DeepChat

Compared to other AI tools, DeepChat offers the following unique advantages:

🔥 Main Features

readme truncated — read the full docs on github

Frequently asked questions

Is deepchat free to use?

deepchat is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does deepchat do?

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

What is deepchat written in?

deepchat is primarily written in TypeScript. Its source is publicly available at https://github.com/ThinkInAIXYZ/deepchat, and it has 6,328 GitHub stars.