08:13
Headroom + Ollama – Cut Your AI Agent’s Tokens by 90%
Fahd Mirza demonstrates Headroom, an open-source, Apache-licensed token compression proxy designed to sit between AI coding agents an...
Sort by: Newest Items
There are 135 items in this page
09:02
Needle: Finetune a 26M Tool-Calling Model Locally with Ollama
Needle is a 26-million-parameter encoder-decoder transformer with one job: given a natural language request and a list of available t...
13:29
Control What Your AI Agents Can Do: Archestra + Ollama Hands-On
Fahd Mirza walks through Orchestra (stylized as Archestra), an open-source platform built for running AI agents safely in production,...
20:41
Structuring the Unstructured – Cedric Clyburn, Red Hat
Cedric Clyburn, an open source engineer at Red Hat, makes the case that unstructured document processing is the single most important...
14:48
Turbocharge Your Agent’s Retrieval with TurboQuant – Shashi Jagtap, Superagentic AI
Shashi Jagtap, founder of SuperAgentic AI, presents at the AI Engineer conference on TurboQuant — a vector embedding compression algo...
45:48
Bypassing the Multimodal Tax: Hybrid RAG, SQL RRF & UI Telemetry – Abed Matini, Ogilvy
Abed Matini, senior backend developer at Ogilvy, presents a framework-free hybrid RAG system designed to sidestep two common producti...
08:51
OpenJarvis + Ollama: Local AI Agent That Tracks Every Watt
Fahd Mirza walks through the installation and hands-on testing of Open Jarvis, a newly released local-first personal AI framework dev...
29:54
“Learn AI” Is Bad Advice. Learn This Instead
Greg Isenberg, entrepreneur and co-founder of Late Checkout, argues that generic "learn AI" advice has become useless in 2026 — and r...
08:09
Ponytail + OpenClaw + Ollama: 20K Tokens to 2K Tokens – Don’t Overbuild
Fahd Mirza demonstrates Ponytail, an open-source skill for the OpenClaw AI assistant that enforces minimal code generation — framed a...
09:49
GLM 5.2 Failed… But Not At Everything
Creator Magic puts GLM 5.2 — a recently released open-weight Chinese model that benchmarks close to Claude Opus on several metrics —...