Uploaded June 2026 | Updated September 2026, 2 weeks ago
Are you struggling to patch software vulnerabilities before they impact your business? Lightwell introduces specialized AI agents paired with human expertise to triage and fix code issues.
Scanning for software vulnerabilities is only half the battle. Responsible remediation across complex dependencies without disrupting your environment is significantly harder. Lightwell is a joint venture between Red Hat and IBM designed to change how the industry views security in open source. In this video, discover how written skills and specialized artificial intelligence (AI) agents scale code correction down to minutes or hours instead of days or weeks. Learn how this clearinghouse model delivers upstream care with real human verification, letting you run packages seamlessly without forced dependency upgrades.
Timestamps:
00:00 The evolution of agentic workflows in software engineering
00:19 Introducing Lightwell from Red Hat and IBM
00:41 Remediation with specialized written skills and AI agents
01:10 Keeping human verification at the core of upstream care
01:24 Maintaining customer dependencies without forced upgrades
Resources:
🔒 Explore enterprise open source security solutions → redhat.com/en/topics/security
✨ Learn more about Lightwell → redhat.com/en/lightwell
Hashtags: #Lightwell #OpenSource #Security #RedHat #IBM #AIAgents #DevSecOps #AppSec
Are you struggling to patch software vulnerabilities before they impact your business? Lightwell introduces specialized AI agents paired with human expertise to triage and fix code issues.
Scanning for software vulnerabilities is only half the battle. Responsible remediation across complex dependencies without disrupting your environment is significantly harder. Lightwell is a joint venture between Red Hat and IBM designed to change how the industry views security in open source. In this video, discover how written skills and specialized artificial intelligence (AI) agents scale code correction down to minutes or hours instead of days or weeks. Learn how this clearinghouse model delivers upstream care with real human verification, letting you run packages seamlessly without forced dependency upgrades.
Timestamps:
00:00 The evolution of agentic workflows in software engineering
00:19 Introducing Lightwell from Red Hat and IBM
00:41 Remediation with specialized written skills and AI agents
01:10 Keeping human verification at the core of upstream care
01:24 Maintaining customer dependencies without forced upgrades
Resources:
🔒 Explore enterprise open source security solutions → redhat.com/en/topics/security
✨ Learn more about Lightwell → redhat.com/en/lightwell
Hashtags: #Lightwell #OpenSource #Security #RedHat #IBM #AIAgents #DevSecOps #AppSec
![[vLLM Office Hours #56] - GuideLLM v0.7: Benchmarking Reasoning and Agentic Traces - August 20, 2026](https://i.ytimg.com/vi/dQAByb7N5QQ/mqdefault.jpg "[vLLM Office Hours #56] - GuideLLM v0.7: Benchmarking Reasoning and Agentic Traces - August 20, 2026
Welcome to vLLM office hours! These bi-weekly sessions are your chance to stay current with the vLLM ecosystem, ask questions, and hear directly from contributors and power users.
This weeks special topic: GuideLLM v0.7.0: Benchmarking Reasoning, Tool Calling, and Agentic Traces.
vLLM project update from core maintainer Michael Goin, covering the v0.27 release plus day-zero support for Qwen3.8, decode context parallelism, and adaptive verification for speculative decoding.
Lightning topic 1: Running Codex and Claude Code CLIs with vLLM and open models, with Francisco Javier Arceo (Red Hat AI) and Tun Jian Tan (Embedded LLM). A look at the Agentic API project, which keeps stateful logic outside vLLM so the inference engine stays stateless, plus a live demo of server-side web search.
Lightning topic 2: Speculators update from maintainer Rahul Tuli, covering the v0.6.0 and v0.7.0 releases, new algorithms including P-EAGLE and DSpark, MTP fine-tuning, and a config-file-first training CLI.
Then our special topic, with Samuel Monson and Jared OConnell (Red Hat AI): what performance benchmarking actually measures, how GuideLLM simulates realistic request patterns, and how the tool is evolving to handle multi-turn conversations, tool calling, sub-agents, and trace replay.
Slides: https://docs.google.com/presentation/d/1GdxjSmHvwM-X6sylRrbHo9-0UYQOSpJMNvhxqFUXZSY
Want to join the discussion live on Google Meet? Get a calendar invite by filling out this form: https://red.ht/office-hours
Timestamps:
00:00 Intro
03:06 Whats new in the vLLM community over the past two weeks
12:02 vLLM v0.27 release
15:50 Lightning topic: Codex and Claude Code CLIs with vLLM
22:40 Lightning topic: Speculators update
33:33 GuideLLM v0.7.0 deep dive
50:45 Q&A")
