#66th of 20 in Agent frameworks and SDKs
copilotkit
SDK for adding agent chat, generative UI and shared state to apps
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 38k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
29,297 on 25 Mar 202638,013 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
CopilotKit is hiring: 1 open role
Overview
CopilotKit is a TypeScript SDK that connects agents to user-facing front ends over the AG-UI protocol. It provides a chat UI, generative UI, shared agent state, human-in-the-loop approvals and a useAgent hook for React, Angular, Vue and React Native, plus a Channels SDK for Slack and Microsoft Teams. Persistent threads, memories and automatic learning are in a separate product, CopilotKit Intelligence.
Who it is for: Frontend and full-stack developers adding agents to React, Angular or Vue apps
Strengths
- Covers React, Angular, Vue and React Native, with Slack and Teams via Channels SDK
- Agents can pause for user confirmation or edits (human-in-the-loop)
- Shared state is readable and writable by both agent and UI through useAgent
- MIT-licensed source; AG-UI protocol is adopted by several agent frameworks
Weaknesses
- Rich threads, user memories and automatic learning belong to the Intelligence product, not the MIT repo
- Vue docs say quickstart is coming soon; Angular is source-only
- Discord, WhatsApp and Telegram managed connections are not yet available
- Does not run models; needs your own agent backend and LLM provider
What it needs
- no GPU
- Needs Agent backend (AG-UI compatible), LLM provider
Also in Agent frameworks and SDKs
See all 20| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 90 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 86 out of 100 |
| #5 | crewaiPython framework for multi-agent workflows with role-based Crews and event-driven Flows | 80 out of 100 |