CopilotKit launches CLiF: turning real user work into agent skills, evals and fine-tuning data
techNmak · x · 2026-10-14
CopilotKit released CLiF (Continual Learning from Full-Stack Trajectories) in early access. Built on the AG-UI protocol — an open bidirectional protocol between agents and user-facing apps adopted by Google, Microsoft and AWS — CLiF captures both what agents and users did, converting real product usage into skills, evals and fine-tuning data. The team argues evals are today's most expensive problem, and notes CLiF is fully self-hostable with exportable outputs.
Related event: CopilotKit Launches CLiF to Turn Real User Actions into Agent Training Data(2 posts)→
More from coding & agent
- Mine Bittensor Subnet 92 by pointing Claude Code at one link — airesearch12 · 2026-10-15
- Future agents will keep refactoring memory, building RL environments, and distilling to old checkpoints — manosaie · 2026-10-15
- Coinbase for Agents goes live on Composio, connecting agents to 1,500+ apps — MurrLincoln · 2026-10-15
- WebMCP demo shows agents joining apps in real-time, dragging canvas nodes live — DavidWells · 2026-10-15
- Codex team explains app RAM growth: subprocesses and agent tasks fold into the app — Dimillian · 2026-10-15
- Complete guide to harness engineering: a bad harness let Claude rm -rf a dev machine — aakashgupta · 2026-10-15