Full-text search across 71143 articles. Combine with topic and date filters; results sorted by relevance.
QuAIA (Quality Assurance with Intelligent Agents), an open-source multi-agent system released under AGPL-3.0, coordinates specialized AI agents across the full test process — requirements review, test design, UI test exe…
Microsoft released .NET 11, an STS release with two years of support under the .NET support policy, adding C# 15 union types and closed hierarchies, a Native AOT CLI host, a warm MSBuild server, ASP.NET Core asynchronous…
Thinking Machines introduced Inkling 2 Small, a Mixture-of-Experts model with 594B total parameters and 17B active, scoring 31 on the Artificial Analysis Intelligence Index and initially available through Tinker with clo…
JetBrains released CLion 2026.3, adding JetBrains Air, a new agentic development layer that runs and verifies multi-agent workflows inside the IDE and works with Claude Agent, Codex, Gemini, GitHub Copilot, Junie, OpenCo…
Ricursive Intelligence released Ripple-65B Preview on November 4, 2026, a 65-billion-parameter dense Transformer pretrained from scratch on 12 trillion tokens with a context window of up to 1M tokens, published under Apa…
Twilio published best-practice guidance for building application-level provider failover into Voice AI agents running on Twilio Conversation Relay, which uses a third-party transcription (ASR/STT) provider and a text-to-…
Legora, the Stockholm-founded legal AI startup led by CTO Jacob Lauritzen, passed $100 million in ARR in April, less than 18 months after launch, and now serves more than 1,800 customers after raising $550 million in Mar…
JetBrains' Junie Eco Mode cut average model cost per task by 48% on internal benchmark A and 57% on benchmark B while average resolve rates changed by less than one percentage point, the company reported. Eco Mode has th…
A new open-source tool called rust-deobf recovers obfuscated strings from stripped Rust malware binaries without executing them, recovering 8 of 8 planted indicators in under 10 seconds on a benchmark sample where `strin…
EarthLink Network ran an open-source AI autonomous scanner, Strix, driven by a cheap model and scoped to four authentication routes on a non-production copy of its promptflow service, finding three real weaknesses in the…
Flockbay detailed how AI agents can automatically playtest Godot games by running builds headless, injecting timed input events, capturing viewports and reading the live scene tree, stdout and the debugger to find and fi…
MindooDB developer Karsten Lehmann reported on 27 October 2026 that the team gave twelve apps in its Haven workspace — including Word, Excel and PowerPoint editors, a mind map and task app, a field map, a CRM, contacts, …
Two developers built RecallDesk, a weekly recall-monitoring tool for resale shops that cross-checks CPSC recall notices against a store's inventory and eBay listings. In a study of 151 CPSC recalls from July to October, …
Veda, described as the first agentic hobby operating system, has published a contribution guide asking developers to help build the project. The guide, released under GPL-3.0-only by copyright holder Vahid Mohammadi, req…
Drupal creator Dries Buytaert exposed his 20-year-old custom photo album module's operations as AI-callable tools using the contributed Tool module's Tool API, which generates JSON Schema from PHP attributes on plain PHP…
Agnostic-ai released v0.85.0, which makes an agent's `can` or `tools` list write an exact `permission` map on OpenCode and Kilo so every unlisted tool is denied, and changes rule ordering so a broad `deny` or `ask` now w…
FlashInfer at commit 518f4c7f0 now includes dedicated block-scaled GEMM kernels for NVIDIA's Rubin architecture (sm_107a), documenting four hardware changes from Blackwell: a wider Tensor Core K (K = 128 for FP4 and K = …
A developer has released theAuth, an open-source authentication library for AI agents and humans, and published a guide showing how to cap agent spending and require human approval for risky actions. The guide builds thr…
A developer built "Should I Go Out?", an open-source web app that runs Google's Gemma 3 4B locally via Ollama and uses a four-step Mastra agent workflow to suggest a single outdoor plan — a park or landmark, a round-trip…
Grenat, a new compiled programming language for building AI agent systems, treats prompts, tools, supervised actor agents, budgets and durable workflows as first-class language constructs, with an effect system that turn…