<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Sessions on Nitin Kumar Singh</title><link>https://nitinksingh.com/tags/sessions/</link><description>Recent content in Sessions on Nitin Kumar Singh</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Nitin Kumar Singh. All rights reserved.</copyright><lastBuildDate>Sun, 12 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://nitinksingh.com/tags/sessions/index.xml" rel="self" type="application/rss+xml"/><item><title>MAF v1 — Sessions (Python + .NET)</title><link>https://nitinksingh.com/posts/maf-v1-04-sessions/</link><pubDate>Sun, 12 Apr 2026 00:00:00 +0000</pubDate><guid>https://nitinksingh.com/posts/maf-v1-04-sessions/</guid><description>Serialize an AgentSession to JSON, persist it, reload in a fresh process, and have the agent pick up exactly where it left off.</description></item><item><title>MAF v1 — Streaming and Multi-turn (Python + .NET)</title><link>https://nitinksingh.com/posts/maf-v1-03-streaming-and-multiturn/</link><pubDate>Sun, 12 Apr 2026 00:00:00 +0000</pubDate><guid>https://nitinksingh.com/posts/maf-v1-03-streaming-and-multiturn/</guid><description>Stream tokens as they arrive and reuse a session across turns so the LLM sees the full conversation. ~60 lines of code per language.</description></item></channel></rss>