#109109th of 142 in Agent frameworks and SDKs
deep-chat
Embeddable web component that adds a chat UI to any website
- Stars
- 3.7k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Aug 2026
- Language
- TypeScript
3,542 on 22 Apr 20263,747 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Deep Chat is a front-end web component (<deep-chat>, installed via npm) that you embed in a page and point at your own backend or at one of 20+ AI APIs such as OpenAI and Claude. It handles file upload, webcam and microphone capture, speech-to-text, text-to-speech and Markdown rendering. It has examples for React, Vue, Svelte, Angular, Solid, Next and Nuxt, and can run a model in the browser through a separate web-llm module.
Who it is for: Web developers embedding a chat interface into their own site or app
Strengths
- One custom element works across React, Vue, Svelte, Angular, Solid and plain JS
- directConnection covers 20+ AI APIs, including OpenAI, Claude, Open WebUI, LiteLLM and Dify
- Built-in camera, microphone, speech-to-text, text-to-speech and file upload
- Server templates provided for Express, Nest, Flask, Spring, Go, SvelteKit and Next
Weaknesses
- Front-end component only; no user accounts or server-side chat history included
- directConnection exposes the API key in the browser; README says prototyping only
- Custom backends must match Deep Chat's request and response format, or use interceptors
- In-browser model needs the separate deep-chat-web-llm module
What it needs
- GPU optional
- Needs npm
- Models: OpenAI, Claude, Open WebUI, LiteLLM, Dify
What changed
- 2.5.1 ↗ (opens in a new tab)Breaking
“The OpenAI Assistants and Azure OpenAI Assistants APIs in directConnection have been removed due to the deprecation of the official OpenAI Assistants API service. Please see here for more information.”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Agent frameworks and SDKs
See all 142| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 96 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 92 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 92 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitReact and Angular SDK for adding agent chat and generative UI to apps | 90 out of 100 |