RadarTopicsBuildersWeeklyReads
Open Source Radar
ThinkInAIXYZ/

deepchat

GitHubWebsite

DeepChat is an open-source, local-first AI agent desktop client with MCP, Skills, ACP, and remote control integrations. It supports multiple model providers, offline capabilities, and a Tape.systems workflow for recoverable sessions.

6.2kstars
708forks
7issues
Apache-2.0license
2025since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 5, 2026

What it is

DeepChat is an open-source, local-first AI agent desktop client with support for MCP, Skills, ACP, and remote control integrations for messaging apps.

How it works

The project presents a desktop application that connects to multiple model providers (e.g., Deepseek, Moonshot, OpenAI, Gemini, Ollama, etc.), supports Skills installation and enabling per conversation, ACP agent integration, and remote control via various messaging platforms. It emphasizes session recovery and traceability via a Tape.systems-inspired approach for long-running agent sessions.

Getting started

  • Quick Start guidance is provided in the README under Skills and ACP sections:
    • Install/enable ACP via Settings → ACP Agents
    • Install or import Skills via Settings → Skills
  • It supports multiple cloud/local model providers and a built-in MCP runtime, with a Node.js runtime for npx/node-style services.

Recent releases

  • v1.1.0-beta.11 (2026-07-31): Tolerated invalid MCP tool output schemas without rejecting otherwise usable tools
  • v1.1.0-beta.10 (2026-07-31): Improved alert confirmations and notification feedback; Added MCP v2 ecosystem support and a built-in McDonald’s server
  • v1.1.0-beta.9 (2026-07-29): Added Directives to Agent Memory; immediate and draft instruction handling
  • v1.1.0-beta.8 (2026-07-26): Added fully offline OCR for image attachments (Light-OCR)
  • v1.1.0-beta.7 (2026-07-25): Fixed auto-update failures with quoted Date in updater metadata

Traction

  • Stars: 6191

Behind the repo

  • The repository is an open-source project under Apache-2.0 and mentions support for MCP, ACP, and multiple model providers; no explicit startup/company link is provided in the FACTS block.

Caveats

  • License: Apache-2.0
  • Created: 2025-02-14
  • Last push: 2026-08-04
  • Open issues: 7
  • Language: TypeScript
  • Topics include agent, ai-sdk, chatgpt, openai-client, Ollama, Electron, MCP, ACP, and more
Agent skills inside · 16
All skills →
docxComprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasksContent & MarketingscriptspptxPresentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasksContent & Marketingscriptsskill-creatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.AI & Agentsscriptsdeepchat-data-importHelp developers build third-party tools that import, inspect, migrate, or analyze DeepChat data. Use when Codex needs to work with DeepChat provider configuration, model configuration, MCP/app settings, sessions, messages, legacy chat data, `agent.db`, `chat.db`, SQLCipher encrypted SQLite, Electron safeStorage wrapped passwords, Tauri importers, or native macOS/Windows/Linux data access.Data & Analyticscomputer-useDrive native desktop apps through DeepChat's built-in Computer Use tools. Use when the user asks to operate, inspect, automate, or perform a GUI task in a real desktop application.Workflow & Productivitycua-driverDrive a native macOS app via the cua-driver MCP server or CLI — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to /Applications in Finder", "click the Save button in Numbers").Backend & API
SharePost on XLinkedIn
All trending reposRevenue-verified startups →