
Manifest
UI blocks for building ChatGPT-style and MCP apps

Manifest is an open-source UI block library designed to help developers build ChatGPT-style applications and MCP apps with interfaces that feel native to AI assistants. It provides production-ready, composable components built on top of shadcn/ui that you can customize and extend.
Key Features
- Production-ready UI blocks tailored to conversational and agentic app layouts
- Built on top of shadcn/ui for easy adoption within modern React codebases
- Installable blocks via CLI for quick integration into existing projects
- Customizable and extensible components intended to be adapted per product
- Designed for apps that render inside AI assistant contexts (for example, ChatGPT-style UIs)
Use Cases
- Building ChatGPT-style internal tools that combine chat with structured UI blocks
- Creating MCP apps with reusable interface patterns and consistent design
- Rapid prototyping of agentic app frontends using prebuilt, customizable components
Limitations and Considerations
- This project is a UI/component library, not a complete backend or full application framework
- Requires an existing shadcn/ui setup and a compatible React/TypeScript frontend stack
Manifest helps teams ship assistant-native app interfaces faster by providing a focused set of reusable UI building blocks. It is best suited for developers who want a structured, production-oriented component toolkit for conversational and agentic products.
Categories:
Tags:
Tech Stack:
Similar Services

Open WebUI
Extensible, offline-capable web interface for LLM interactions
Feature-rich, self-hosted AI interface that integrates Ollama and OpenAI-compatible APIs, offers RAG, vector DB support, image tools, RBAC and observability.


AnythingLLM
All-in-one AI chat app with RAG, agents, and multi-model support
AnythingLLM is an all-in-one desktop and Docker app for chatting with documents using RAG, running AI agents, and connecting to local or hosted LLMs and vector databases.

LibreChat
Self-hosted multi-provider AI chat UI with agents and tools
LibreChat is a self-hosted AI chat platform that supports multiple LLM providers, custom endpoints, agents/tools, file and image chat, conversation search, and presets.


Khoj
Open-source personal AI for chat, semantic search and agents
Self-hostable personal AI 'second brain' for chat, semantic search, custom agents, automations and integration with local or cloud LLMs.

Netron
Visualizer for neural network and machine learning models
Netron is a model graph viewer for inspecting neural network and ML formats such as ONNX, TensorFlow Lite, PyTorch, Keras, Core ML, and more.
Perplexica
Privacy-focused AI answering engine with web search and citations
Self-hosted AI answering engine that combines web search with local or hosted LLMs to generate cited answers, with search history and file uploads.



