GitHub (open-webui/open-webui) · Oct 26, 2026 · 2:20 AM

Open WebUI 0.12.4 loads skills on demand, speaks MCP 2026-07-28 and ships unlisted security fixes

Released Oct 25, an opt-in ENABLE_SKILL_LAZY_LOADING setting lists selected skills for the model to load only when needed instead of sending every skill's instructions each message, and MCP connections now work with stateless 2026-07-28 servers. It also carries security fixes the team will detail after CVE assignment, so update soon, and note that saved tool-server and Open Terminal connections now stop working unless an admin turns on ENABLE_DIRECT_INTEGRATIONS.

Read at github.com

More news

View all

Kimi Code 2.3.2 stops launching subagents and agent swarms unless you ask for them

Released Oct 25, Moonshot's coding CLI now handles tasks itself by default, so request delegation in your message, AGENTS.md, a skill, or an enabled multi agent mode. AgentSwarm only starts once you turn on swarm mode, which means swarms are no longer available in kimi p or ACP clients such as Zed (changelog)…

GitHub (MoonshotAI/kimi-code) 21 minutes ago

Ollama 0.40.11 adds d3, local decision models that classify, answer yes/no or score options

Released Oct 24, d3 brings vLLM Semantic Router's 2B to 27B decision models to Ollama: pass text, structured state or an image and get a classification, yes/no answer or probability scored options, e.g. ollama run d3 "..." ask "Is this a billing issue?" . It's a cheap local gate for routing or approving an agent's next step…

GitHub (ollama/ollama) 2 hours ago

JetBrains open-sources ThinkRail, an agentic IDE that gives each coding agent its own git worktree

The Apache 2.0 InnovationHub project wraps the pi coding agent in Monaco tabs, terminals and diffs, runs parallel agents in separate worktrees, and keeps project intent in a graph of SPEC.md files the agent reads and updates. It's an experimental incubator project; install with the one line script in the repo and run thinkrail (TechNewsReel)…

GitHub (JetBrains/thinkrail) 3 hours ago

Corgi, an agent and terminal multiplexer for Claude Code, Codex and Pi, lands on Show HN

Corgi runs multiple coding agent sessions side by side with a live activity feed, a jump to next unread agent shortcut, a unified launcher with session search and usage tracking, and image paste that works over SSH. The solo developer says multi machine remoting is next; Windows works via WSL2…

Hacker News (Show HN) 4 hours ago

Nanbeige4.3-33B is an Apache-2.0 open model for agentic coding with a 512K context

The 33B dense model from BOSS Zhipin's Nanbeige lab self reports 80.9 on Terminal Bench 2.1 and 65.5 on DeepSWE versus 73.0 and 42.5 for Qwen3.8 27B, though Qwen still edges it on SWE Bench Pro (61.7 to 60.3). It runs on vLLM or SGLang with Qwen3 tool call parsing, and the scores are the lab's own, so test it on your repos before swapping your local coding agent (MarkTechPost)…

Hugging Face (Nanbeige) 5 hours ago

Spotted something we missed? Start a thread.