Benjamin Taylor
45bfd28dcc
Two ways the filter reached places it should not, both found in review.
Intelligence: `IntelligenceAgent` posts `{...input}` to the managed runtime, so
the filtered list went on the wire, while the Intelligence connect path builds
its own input through `delegate.connectAgent` and stayed unfiltered. Run and
connect disagreeing is bad on its own, but the deciding point is that the
managed runtime is the store of record for the thread — the threads drawer and
the Slack transcript read from it — so a client-side truncation there has a
blast radius nobody asked for. Every reporter on #1482 is self-hosted. The
filter is now skipped in Intelligence mode, which also removes the asymmetry.
Suggestions: `SuggestionEngine` clones the provider agent for the fallback path
and gives the clone a fresh thread id, so no backend store can fill in what the
filter withheld — the seeded messages ARE the context. A trimming filter rode
the clone and silently degraded suggestions to context-free prompts, and only on
runtimes without the `suggestions` capability, so the behavior differed by
runtime version. The engine now clears the filter on that clone.
Also widens the try/catch to cover the repair, so a filter that returns an array
with a non-message entry degrades like one that throws rather than blowing up on
`message.role`. And corrects two JSDoc claims: the registry stamps every
`ProxiedCopilotRuntimeAgent` including one from `registerProxiedAgent` (which
files under `localAgents`), not only runtime-discovered ones; and the public
`messageFilter` setter is registry-owned, replaced on the next sweep.
Testing: 27 tests passing, up from 24. The suggestion test drives the real
`SuggestionEngine` fallback path and asserts the outbound body still carries the
seeded context — it fails with "expected 1 to be greater than 1" when the guard
is removed, which is exactly the silent degradation it protects against. New
tests also cover the Intelligence exemption and the bad-entry fallback. Full
core suite 846 passing with the same 20 pre-existing failures; suggestions
suites (72 tests) still green; tsc clean against the normalized baseline; oxlint
clean on all five files.
My first pass at the Intelligence JSDoc claimed the opposite of this and was
wrong in both directions before landing here.
Refs #1482
CopilotKit
Build agent-native applications — on any framework, on any surface.
Generative UI, shared state, and human-in-the-loop workflows for React, Angular, Vue, React Native — and in Slack and Microsoft Teams.
What is CopilotKit?
CopilotKit is a best-in-class SDK for building full-stack agentic applications, Generative UI, and chat applications.
What started as a React library is now the horizontal layer between your agents and your users: the same agent can power your web app, your mobile app, and your team's Slack or Microsoft Teams workspace.
We are the company behind the AG-UI Protocol — adopted by Google, LangChain, AWS, Microsoft, Mastra, PydanticAI, and more!
Quick Start
Up and running in under five minutes. All you need is an LLM key (OpenAI, Anthropic, Gemini, etc.).
npx copilotkit@latest create
Agent Skills
CopilotKit ships agent skills that teach your coding agent (Claude Code, Codex, Cursor, Gemini, and others) how to set up, build with, integrate, debug, and upgrade CopilotKit.
Install them into any project directory:
npx copilotkit@latest skills install
Run it again any time to refresh to the latest skills.
Bring Your App to Life
https://github.com/user-attachments/assets/72b7b4f3-b6e7-460c-a932-5746fe3c8db3
Features:
- Chat UI – A fully customizable chat interface that supports message streaming, tool calls, and agent responses.
- Backend Tool Rendering – Enables agents to call backend tools that return UI components rendered directly in the client.
- Generative UI – Allows agents to generate and update UI components dynamically at runtime based on user intent and agent state.
- Shared State – A synchronized state layer that both agents and UI components can read from and write to in real time.
- Human-in-the-Loop – Lets agents pause execution to request user input, confirmation, or edits before continuing.
- Self-Learning (early access) – Agents that continuously improve from user feedback via in-context reinforcement learning (CLHF).
🧩 Works With Your Stack
One agent backend. Every frontend.
| Platform | Status | Get Started |
|---|---|---|
| ⚛️ React / Next.js | ✅ GA | Quickstart |
| 🅰️ Angular | ✅ Supported | Source Code & Quickstart |
| 💚 Vue | ✅ Supported | Source Code - Quickstart coming soon |
| 📱 React Native | ✅ Supported | Quickstart |
| 💬 Slack / Microsoft Teams | ✅ Supported | Channels · Quickstart |
| 🔜 Discord / WhatsApp / Telegram / Google Chat / iMessage / SMS | 🟡 Coming soon | Channels |
Your agent logic stays the same — AG-UI handles the wire protocol, CopilotKit handles the UI layer for each framework and channel.
💬 Channels: One Agent, Every Chat App
The Channels SDK takes the agent you already built and drops it into the chat apps your users live in — same tools, same shared state, same human-in-the-loop, no rewrite (Learn more).
- Slack – Agents as first-class Slack apps: threads, tool calls, and human-in-the-loop approvals right in the channel.
- Microsoft Teams – Bring agentic workflows to the enterprise, where your org already lives.
🧠 Self-Learning Agents
Improve your product by learning over time.
With Continuous Learning from Human Feedback (CLHF), part of CopilotKit Intelligence, agents improve with every interaction:
- In-context reinforcement learning – Agents automatically improve from user interactions, no model fine-tuning required.
- Automatic prompt augmentation – Agent behavior adapts based on recent interactions and outcomes.
- Per-user adaptation – Agents learn individual preferences and get better for each user over time.
- Threads & persistence – Full interaction history — generative UI, human-in-the-loop, shared state — captured across sessions.
Available via CopilotKit Cloud or self-hosted.
🔒 Early access: We're onboarding teams now.
https://github.com/user-attachments/assets/7372b27b-8def-40fb-a11d-1f6585f556ad
What this gives you:
- CopilotKit installed – Core packages are fully set up in your app
- Provider configured – Context, state, and hooks ready to use
- Agent <> UI connected – Agents can stream actions and render UI immediately
- Deployment-ready – Your app is ready to deploy
Complete getting started guide →
How it works:
CopilotKit connects your UI, agents, and tools into a single interaction loop.
This enables:
- Agents that ask users for input
- Tools that render UI
- Stateful workflows across steps and sessions
- One agent, deployed across web, mobile, and chat platforms
⭐️ useAgent Hook
The useAgent hook sits directly on AG-UI, giving you full programmatic control over the agent connection.
// Programmatically access and control your agents
const { agent } = useAgent({ agentId: "my_agent" });
// Render and update your agent's state
return <div>
<h1>{agent.state.city}</h1>
<button onClick={() => agent.setState({ city: "NYC" })}>
Set City
</button>
</div>
Check out the useAgent docs to learn more.
https://github.com/user-attachments/assets/67928406-8abc-49a1-a851-98018b52174f
Generative UI
Generative UI is a core CopilotKit pattern that allows agents to dynamically render UI as part of their workflow.
https://github.com/user-attachments/assets/3cfacac0-4ffd-457a-96f9-d7951e4ab7b6
Compare the Three Types
Explore:
Generative UI educational repo →
🖥️ AG-UI: The Agent–User Interaction Protocol
Connect agent workflows to user-facing apps, with deep partnerships and 1st-party integrations across the agentic stack—including LangChain, CrewAI, Mastra, PydanticAI, and more.
npx create-ag-ui-app my-agent-app
🤝 Community
Have questions or need help?
Join our Discord →Read the Docs →
Try CopilotKit Intelligence →
Stay up to date with our latest releases!
Follow us on LinkedIn →Follow us on X →
🙋🏽♂️ Contributing
Thanks for your interest in contributing to CopilotKit! 💜
We value all contributions, whether it's through code, documentation, creating demo apps, or just spreading the word.
Here are a few useful resources to help you get started:
-
For code contributions, CONTRIBUTING.md.
-
For documentation-related contributions, check out the documentation contributions guide.
-
Want to contribute but not sure how? Join our Discord and we'll help you out!
📄 License
This repository's source code is available under the MIT License.