Auto Added by WPeMatico
MiniMax has open-sourced MCode Stack, the workflows and agent skills its team uses to build MiniMax Code. The MiniMax MCode Stack agent skills went public on October 28, 2026 under the MIT license. It is not a prompt collection. Each piece is a SKILL.md skill or checklist that installs directly into MiniMax Code. For developers,
MiniMax Open-Sources MCode Stack: 15 Agent Skills Its Coding Team Uses Daily Read More »
The vLLM Semantic Router team has released d3-ultra, a 27B multimodal decision model under Apache-2.0. The d3-ultra decision model does not generate text. It reads an input once and returns a probability for every answer to every question. For developers, that means routing, classification, visual grounding and video checks from 1 open-weight call. TL;DR Size:
vLLM Semantic Router Releases d3-ultra: A 27B Open Multimodal Decision Model Read More »
OpenAI has released GPT-6.1 Terra, a fast model for visual reasoning, computer use and writing. It replaces GPT-5.6 Terra and is live in the API as gpt-6.1-terra. Standard pricing is $1 per million input tokens and $5 per million output tokens. For teams automating screens, forms and documents at volume, GPT-6.1 Terra changes the cost
OpenAI Launches GPT-6.1 Terra, Halving GPT-6.1 Sol’s API Price for Agent Work Read More »
Nace AI has released Drex for Search, which brings its Drex decision models to document search. Drex for Search is a retrieval layer that helps people and agents find evidence. Coding agents such as Claude Code, Codex, Cursor and OpenCode call it through CLI, SDKs, MCP or REST. In Nace’s evaluation, it scores 92.05% on
Tsinghua University and CUHK researchers open-sourced AKV, a serving system for KV cache engineering in LLM agents. Instead of summarizing old history, agents drop selected KV cache entries and keep reusing the rest. Across 3 models and 4 agent benchmarks, average cost falls 27.7%. Average task score rises 1.7 points. The code is Apache-2.0 licensed
Tsinghua AI Open-Sources AKV, a Cache Engineering Server for LLM Agents on SGLang Read More »
Stanford and UC Berkeley researchers released TokenGate, a module for long-context prefill. TokenGate learned token pruning lets an existing LLM skim its input. Only the tokens that matter get full processing. The research team reports 1.4x to 11.3x faster time-to-first-token (TTFT) with no accuracy loss. Peak prefill memory drops 1.5x to 3.4x. Code and checkpoints
Anthropic has launched OSS Scanner, a free, opt-in vulnerability scanner for critical open-source projects. The Anthropic OSS Scanner runs the company’s strongest models, including Claude Mythos, against enrolled codebases. Reports go straight to maintainers without human review. That trade delivers faster findings, but shifts triage work onto project teams. 11 days after the October 8
Anthropic Launches OSS Scanner, a Free AI Vulnerability Scanner Read More »
Cognition has released the Devin Vulnerability Fixes plugin, a free, open-source set of agent skills. It targets three critical remote code execution (RCE) advisories. They cover PHP2Shell, the Node.js October 21, 2026 security release and a CVSS 10.0 self-managed GitLab bug. The skills run in Devin and in any coding agent that reads SKILL.md files.
In this article, we will discuss newly trending open sourced Anthropic’s sandbox-runtime (srt), the OS-level sandbox behind Claude Code’s sandboxed bash tool. The Anthropic sandbox-runtime limits which files a process can touch and which hosts it can reach. It does this without spinning up a container. It is also not tied to Claude Code. Your
Meet Anthropic’s sandbox-runtime: OS-Level Sandboxing for AI Agents, No Containers Read More »
NVIDIA has just released Nemotron 3.5 Bolt E4B 4GB, an open small language model for fast conversational agents. It targets voice assistants, game NPCs and robot interfaces running locally on RTX, Jetson and Spark hardware. The model is post-trained from Google’s Gemma 4 E4B using reinforcement learning only. For developers, this is agent behavior in
