Your AI sessions shouldn’t start from zero every time.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Your AI sessions shouldn’t start from zero every time. Kipi is a Claude Code system for turning the knowledge around your work into context that follows you across AI sessions. It helps you answer questions with relevant project context by selecting the sources that fit the question, supplying verbatim excerpts to the model, and recording what was or was not read. Key features: • Context-aware retrieval – questions about people, projects, or work pull different relevant sources • Evidence receipts – supplied excerpts include file and line references, while each source is marked read, empty
Posted by Dan Kornas (99.3k followers) 2 h ago · 4 likes · 509 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Okay, my first complete benchmark of Jev with my new Decision v1 eval suite on… — @morganlinton
- 🚨重磅！DeepSeek 发布 DeepEP V2.5 版本！又把 MoE 通信库掏出来升级了！ — @NFT_Chen
- おうちのllama.cppベース ローカルJevの利用モデルでのスコア、こんな感じ。 — @kis
- NVIDIA just dropped a real-time conversational AI voice, free and open source… — @0x0SojalSec
- Turning a long video into useful clips is still too manual. This repo automates the… — @DanKornas
- GitHub 🤝 @Muse — @github
- This is an insanely cool release — @Shaughnessy119
- AI coding agents get more useful when their workflows are reusable. — @DanKornas
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 23k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 00:15 UTC. Full method.