# CopilotKit launches CLiF for agent learning from user actions

Digest AI · Agents & Tools · published 2026-10-15T14:19:27Z

Canonical: https://digestai.news/story/copilotkit-launches-clif-for-agent-learning-from-user-actions

## Summary

CopilotKit released **CLiF**, a platform for continual learning from full-stack agent trajectories, in early access. The tool captures both agent actions and user interactions in a product, combining them into a single timeline via **AG-UI**, an open protocol the company developed. This data is then processed into **skills, production-based evals, fine-tuning datasets, and raw exports**, all versioned and human-reviewed before deployment.

The core idea is that most agent failures stem from missing the *actual* workflows users follow—often undocumented shortcuts or fixes—while traditional tracing only logs agent mistakes. CLiF addresses this by analyzing recurring patterns in user behavior (e.g., post-sprint issue adjustments) and turning them into reusable skills. It supports **self-hosting** on Kubernetes, AWS, or on-premises, with compatibility across frameworks like **LangChain, Mastra, and Google ADK**. Early adopters can also generate **eval candidates** and **fine-tuning data** from real usage, reducing reliance on manual test cases.

CopilotKit, which maintains the open-source **CopilotKit framework** (38,000+ GitHub stars), positions CLiF as a solution to common agent deployment challenges: **eval bottlenecks, context bloat, cost inefficiency, and fragmented tooling**. The platform is designed for teams shipping agents at scale, whether internal or via **MCP servers** for external agents like **Claude**.

## Key points

- CLiF combines agent traces and user actions into a single timeline via AG-UI, capturing full-stack workflows for learning
- Outputs include skills, production-based evals, fine-tuning datasets, and raw trajectory exports—all human-reviewed and versioned
- Self-hostable on Kubernetes/AWS or cloud-managed, with support for frameworks like LangChain, Mastra, and Google ADK

## Why it matters

CLiF bridges the gap between agent observability and real-world user behavior, potentially accelerating agent deployment by automating skill discovery from production data. Its self-hosted, framework-agnostic design could reduce costs and improve reliability for teams struggling with evals, context bloat, or fragmented agent stacks.

## Sources

1. [CopilotKit Releases CLiF: A Continual Learning Platform That Turns Agent Traces and User Actions into Skills, Evals, and Fine-Tuning Data](https://marktechpost.com/2026/10/15/copilotkit-releases-clif-a-continual-learning-platform-that-turns-agent-traces-and-user-actions-into-skills-evals-and-fine-tuning-data) (MarkTechPost, 2026-10-15)

## Cite

Digest AI, "CopilotKit launches CLiF for agent learning from user actions", 15 October 2026, https://digestai.news/story/copilotkit-launches-clif-for-agent-learning-from-user-actions

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/copilotkit-launches-clif-for-agent-learning-from-user-actions.json