BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//txlf2026//talk//HQWWGD
BEGIN:VTIMEZONE
TZID:US/Central
BEGIN:STANDARD
DTSTART:20251107T000000
TZNAME:CST
TZOFFSETFROM:-0600
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20270314T030000
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T020000
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Don't Mess With My Data: Local AI + MCP on Linux - Rajesh Alwar
DTSTART;TZID=US/Central:20261107T150000
DTEND;TZID=US/Central:20261107T155000
DTSTAMP:20260930T133611Z
UID:pretalx-txlf2026-HQWWGD@pretalx.com
DESCRIPTION:What if you could ask an AI "is my house good for solar panels
 ?" - and get a real answer\, without sending your address leaving your mac
 hine?\n\nIn this talk\, we'll build a fully local AI agent stack on Linux 
 that evaluates solar potential for any Texas property - no cloud APIs\, no
  OpenAI key\, no data leaving your network. We'll wire together Ollama run
 ning a local LLM\, a custom MCP (Model Context Protocol) server exposing t
 ools for geocoding and solar estimation\, the free NREL PVWatts government
  API\, and PostgreSQL for local storage. The result: an agent you can ask 
 "what would solar look like on my roof?" and get a real\, human-readable a
 nswer grounded in real data.\n\nWe'll cover:\n- Running a local LLM with O
 llama on Linux\n- Building an MCP server that exposes real-world tools to 
 any AI client\n- Turning raw government solar data into plain-English savi
 ngs estimates\n- Persisting and querying results in local PostgreSQL\n- Ru
 nning the whole stack as a systemd service - no always-on laptop required
 \n\nTexas gets 200+ sunny days a year and some of the most volatile electr
 icity prices in the country thanks to ERCOT. This is a practical talk abou
 t what local\, open source AI can actually do - on your hardware\, on your
  terms\, using a protocol you can reuse for your own tools tomorrow.\n\nAs
  the industry shifts from expensive frontier models toward cheaper\, optim
 ized inference this talk shows what's possible when you run capable AI age
 nts directly on hardware you own.
LOCATION:Lil Tex
URL:https://pretalx.com/txlf2026/talk/HQWWGD/
END:VEVENT
END:VCALENDAR