Cherry Studio
Cherry Studio is an all-in-one AI assistant and cross-platform desktop client that brings hundreds of AI models into one unified workspace for Windows, macOS, and Linux. It connects to major model providers and lets users switch between different AI services without juggling separate apps, browser tabs, or fragmented workflows. It is designed as a powerful local AI productivity hub, supporting everyday chat, writing, translation, research, coding help, document understanding, image understanding, and multimodal AI workflows from a single interface. Users can configure model providers, manage assistants, organize conversations, and work with different models depending on the task, making Cherry Studio useful for both casual AI use and more advanced experimentation. Its assistant system allows users to create, subscribe to, and manage role-based assistants with specialized prompts for scenarios such as product management, community operations, technical support, strategy, etc.
Learn more
FastGPT
FastGPT is a free, open source AI knowledge base platform that offers out-of-the-box data processing, model invocation, retrieval-augmented generation retrieval, and visual AI workflows, enabling users to easily build complex large language model applications. It allows the creation of domain-specific AI assistants by training models with imported documents or Q&A pairs, supporting various formats such as Word, PDF, Excel, Markdown, and web links. The platform automates data preprocessing tasks, including text preprocessing, vectorization, and QA segmentation, enhancing efficiency. FastGPT supports AI workflow orchestration through a visual drag-and-drop interface, facilitating the design of complex workflows that integrate tasks like database queries and inventory checks. It also offers seamless API integration with existing GPT applications and platforms like Discord, Slack, and Telegram using OpenAI-aligned APIs.
Learn more
DocsGPT
DocsGPT is an open-source platform for private AI agents, assistants and enterprise search over an organisation's own documents, built by Arc53. It runs where the data is allowed to be: Arc53's EU cloud, a dedicated managed instance, the organisation's own servers, or fully air-gapped with no outbound traffic.
Teams connect files and services (PDF, DOCX, XLSX, scanned documents with OCR, Google Drive, SharePoint, Confluence, GitHub, S3) and get answers cited to the source passage. Agents call tools and APIs with per-action approval, a visual builder turns document jobs into workflows, and agents can produce DOCX, XLSX, PPTX and PDF files.
Any model works: OpenAI, Anthropic, Google and others in the cloud, or local models through Ollama or vLLM. Governance covers OIDC SSO, SCIM 2.0, role-based access, guardrails, usage quotas and an exportable, append-only audit log. MIT licence, 18,000+ GitHub stars.
Learn more
Jan
Jan is an open-source personal AI assistant designed to run locally on your device, giving you full control over your data and privacy. It allows users to interact with AI models without relying on cloud-based services or incurring API costs. The platform supports a wide range of models, including popular options from OpenAI, Anthropic, Google, Meta, and others. Jan provides a clean, user-friendly interface that makes it easy to chat, research, and complete tasks efficiently. It also includes real-time web search capabilities to enhance responses with up-to-date information. Users can customize their experience by selecting different models and integrating external providers. Jan is lightweight and optimized for performance, enabling smooth operation even on personal machines. It empowers users to build a private, flexible AI environment tailored to their needs.
Learn more