github.com/DarkNoah/aime-chat @v0.3.39

<img src="https://img.shields.io/badge/version-0.3.37-blue.svg" alt="Version">
<img src="https://img.shields.io/badge/platform-macOS%20|%20Windows%20|%20Linux-lightgrey.svg" alt="Platform">
<img src="https://img.shields.io/badge/license-MIT-green.svg" alt="License">







<a href="https://darknoah.github.io/aime-chat/">Official Website</a> • <a href="https://github.com/DarkNoah/aime-chat/raw/v0.3.39/README_CN.md">中文</a>

---

✨ Features

• 🦾 Harness Engineering - A complete agent harness around the model (Agent = Model + Harness): orchestration loop, tools, context & memory, sub-agents, guardrails, and observability turn a stateless model into a reliable, long-running agent
• 🤖 Multiple AI Provider Support - Integrated with mainstream AI providers including OpenAI, DeepSeek, Google, Zhipu AI, MiniMax, Ollama, LMStudio, ModelScope, and more
• 💬 Intelligent Conversations - Powerful AI Agent system based on Mastra framework, supporting streaming responses and tool calling
• 🤝 Open CoWork Capability - AI is not just for chatting, it can perform actual operations like file editing, code execution, web searching, and more
• 📚 Knowledge Base Management - Built-in vector database with support for document retrieval, knowledge Q&A, and long-term cultivation memory
• 🧠 Cultivation Memory - A scheduled Cultivation Agent extracts preferences, habits, project context, and important facts from chat history into a structured memory wiki
• ⏰ Cron Automation - Run scheduled AI tasks with project context, selectable agents/tools, and either reusable or per-run chat threads
• 🛠️ Tool Integration - Support for MCP (Model Context Protocol) client with extensible tool capabilities
• 🎙️ Audio Processing - Built-in Speech-to-Text (STT) and Text-to-Speech (TTS) powered by Qwen3-TTS models
• 🔍 Skill System - Search, import, and manage AI skills from Git repositories or the online skill marketplace
• 🧑‍💻 Assistant Personalities - Built-in assistant personalities can be selected instantly and customized through the current personality format
• 🖥️ Background Bash Sessions - Track long-running shell processes from the current chat or the whole project, with direct stop controls in the UI
• 📡 Channel Integration - Connect AI capabilities to messaging platforms like WeChat and Telegram
• 🔐 Secrets Management - Centralized secret key management for tools and services, securely stored locally
• 🎨 Modern UI - Built with shadcn/ui component library, supports light/dark theme switching
• 🌍 Internationalization - Built-in Chinese and English interfaces
• 🔒 Local First - Data stored locally for privacy protection
• ⚡ High Performance - Built on Electron for cross-platform native experience

🚀 Quick Start

Prerequisites

• Node.js >= 22.x
• npm >= 10.x
• pnpm >= 10.x

Install Dependencies

pnpm install

Development Mode

Start the development server:

• Click on "Electron Main" in VSCode's debug panel to start debugging

The application will start in development mode with hot reload support.

Build Application

Package desktop application:

pnpm package

Packaged applications will be generated in the release/build directory.

macOS Installation Notes

Due to the app not being signed with an Apple Developer certificate, macOS Gatekeeper may prevent the app from running. If you see "App is damaged" or "Cannot be opened" error, please run the following command in Terminal:

# After mounting the DMG and copying to Applications
xattr -cr /Applications/aime-chat.app

Or right-click the app → hold Option key → click "Open".

📦 Project Structure

aime-chat/
├── assets/              # Static assets
│   ├── icon.png        # Application icon
│   ├── models.json     # AI model configurations
│   └── model-logos/    # Provider logos
├── src/
│   ├── main/           # Electron main process
│   │   ├── providers/  # AI provider implementations
│   │   ├── mastra/     # Mastra Agent and tools
│   │   ├── knowledge-base/ # Knowledge base management
│   │   ├── tools/      # Tool system
│   │   └── db/         # Database
│   ├── renderer/       # React renderer process
│   │   ├── components/ # UI components
│   │   ├── pages/      # Page components
│   │   ├── hooks/      # React Hooks
│   │   └── styles/     # Style files
│   ├── types/          # TypeScript type definitions
│   ├── entities/       # Data entities
│   └── i18n/           # Internationalization config
└── release/            # Build artifacts

🎯 Core Features

Harness Engineering

A raw LLM is just a stateless function — it becomes a dependable agent only when wrapped in a harness. Following the Agent = Model + Harness formula that the industry formalized in 2026, AIME Chat is built as a complete harness around the model, not just a chat box in front of it.

The harness layers AIME Chat provides:

Layer	What it does	In AIME Chat
Orchestration Loop	Drives the prompt → response → tool call → observation → next step cycle until a task is done	Mastra-based Agent runtime with streaming and multi-step tool calling
Guides	Feed-forward constraints that steer behavior	Agent instructions, assistant personalities, and the Skill system
Tool Interfaces	Scoped access to the outside world with clear schemas	Bash, Read/Write/Edit, Grep/Glob, Code Execution, Web, Vision, OCR, and MCP tools
Context & Memory	Assembling and persisting the right information across turns and sessions	Knowledge base, cultivation memory wiki, and session/working memory
Orchestration & Sub-agents	Delegating and coordinating specialized agents	Sub-agent configuration and multi-agent workflows
State & Long-running Tasks	Durable state so work survives across runs	Background Bash sessions, Goal-driven execution, and Cron automation
Guardrails & Permissions	Enforcing what the agent is allowed to do	Per-agent tool permissions, action approval, and centralized Secrets management
Observability	Tracing behavior for debugging and trust	Detailed runtime logging with direct log access from the About page

In short, AIME Chat focuses on engineering everything around the model so that any provider — cloud or local — can be turned into a reliable, goal-directed agent.

AI Provider Configuration

Support for configuring multiple AI providers, each with independent settings:

• API Key
• API Endpoint
• Available model list
• Enable/Disable status

Supported providers include:

Provider	Type	Description
OpenAI	Cloud	GPT series models
DeepSeek	Cloud	DeepSeek series models
Google	Cloud	Gemini series models
Zhipu AI	Cloud	GLM series models
MiniMax	Cloud	MiniMax series models
Ollama	Local	Run open-source models locally
LMStudio	Local	Local model management tool
ModelScope	Cloud	ModelScope community models
SerpAPI	Cloud	Google Search API service

Knowledge Base Features

• 📄 Document upload and parsing
• 🔍 Vector storage and retrieval
• 💡 Intelligent Q&A based on knowledge base
• 🧠 Cultivation memory that maintains a global memory wiki from chat history
• 📊 Knowledge base management interface

Cultivation Memory

AIME Chat includes a global memory knowledge base maintained by the built-in Cultivation Agent. When the Cultivation Daily cron task is enabled, it reads newly updated user conversations, filters out automation-generated threads, deduplicates against existing memories, and writes useful long-term information into Markdown pages such as preferences.md, habits.md, and project notes.

This helps future conversations automatically inherit stable preferences, working habits, important people/entities, and ongoing project context without pasting old chat logs into every prompt.

Tool System

Rich built-in tools that AI Agents can call autonomously:

Category	Tools	Description
File System	Bash, Read, Write, Edit, Grep, Glob	File read/write, search, edit operations
Code Execution	CodeExecution	Execute Python and Node.js code
Web Tools	Web Fetch, Web Search	Web scraping and search (with AI content summarization)
Image Processing	GenerateImage, EditImage, RMBG	Image generation, editing, and background removal
Vision Analysis	Vision	LLM-powered image recognition and analysis (with OCR integration)
OCR Recognition	PaddleOCR	Document and image text recognition (supports PDF/images)
Audio Processing	SpeechToText, TextToSpeech	Speech-to-text and text-to-speech (powered by Qwen3-TTS)
Database	LibSQL	Database query and management
Translation	Translation	Multi-language text translation
Task Management	TaskCreate, TaskGet, TaskList, TaskUpdate	Structured task creation, query, and status management
Information Extraction	Extract	Extract structured information from documents
Knowledge Base	KnowledgeBase	Knowledge base retrieval and intelligent Q&A

• 🧵 Background Bash Tracking - Long-running Bash sessions are visible from task/context surfaces, including project-wide sessions when a chat is bound to a project
• 🔌 MCP Protocol Support - Extensible third-party tools
• ⚙️ Tool Configuration UI - Visual tool management and configuration
• 🔍 Skill Marketplace - Search and import skills from Git repositories or online marketplace (skills.sh)

Channel Integration

Connect AI capabilities to external messaging platforms:

Channel	Description
WeChat	Connect to WeChat for AI-powered conversations
Telegram	Integrate with Telegram bots for AI interaction

Secrets Management

Centralized management of secret keys and credentials used by tools and services:

• 🔑 Unified interface for managing API keys and tokens
• 🔒 Secure local storage with encryption
• 🔗 Automatic injection into tools that require authentication

🛠️ Tech Stack

Frontend

• Framework: React 19 + TypeScript
• UI Library: shadcn/ui (based on Radix UI)
• Styling: Tailwind CSS
• Routing: React Router
• State Management: React Context + Hooks
• Internationalization: i18next
• Markdown: react-markdown + remark-gfm
• Code Highlighting: shiki

Backend (Main Process)

• Runtime: Electron
• AI Framework: Mastra
• Database: TypeORM + better-sqlite3
• Vector Storage: @mastra/fastembed
• AI SDK: Vercel AI SDK

Build Tools

• Bundler: Webpack 5
• Compiler: TypeScript + ts-loader
• Hot Reload: webpack-dev-server
• App Packaging: electron-builder

Project Initialization

git clone https://github.com/DarkNoah/aime-chat.git
cd ./aime-chat
pnpm install

# Since pnpm disables postinstall scripts by default, if you encounter missing binary packages or similar issues, run:
pnpm approve-builds

⚙️ Configuration

Optional Runtime Libraries

AIME Chat supports optional runtime libraries that can be installed from the Settings page:

Runtime	Description
UV / Python	Python runtime used by code execution, OCR, and other local processing tools
Node.js / Bun	JavaScript runtimes used by Node.js code execution and MCP-related workflows
PaddleOCR	OCR recognition engine based on PaddlePaddle, supports document structure analysis and text extraction from PDF/images
Qwen Audio	Audio processing engine based on Qwen3-TTS, supports speech recognition (ASR) and text-to-speech (TTS)

These runtimes are installed under the application data directory. Runtime install attempts write detailed success and failure information to the application log, and the About page provides a direct entry for opening the log file.

Data Storage

Application data is stored by default in the system user directory:

• macOS: ~/Library/Application Support/aime-chat
• Windows: %APPDATA%/aime-chat
• Linux: ~/.config/aime-chat

🤝 Contributing

Issues and Pull Requests are welcome!

1. Fork this repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Code Standards

• Use ESLint and Prettier to maintain consistent code style
• Follow TypeScript type specifications

📄 License

This project is licensed under the MIT License.

👨‍💻 Author

Noah - Email: 781172480@qq.com

🙏 Acknowledgments

• Electron
• React
• Mastra
• Vercel AI SDK
• shadcn/ui
• Radix UI

🔗 Related Links

• Official Website
• Issue Tracker
• Changelog

---

_{Built with ❤️ by Noah}