Svenska Dagbladet tested AI chatbots on Sweden's election compass, but a new analysis by Agent Arena stripped away system prompts and web search to measure raw model leanings. Across 28 frontier model…
Varela, a self-mutating agent harness inspired by Neuromancer, rewrites its own source code while running and hot-reloads, logging every run to turn repeated wins into new tools and failures into less…
Inference startup Wafer claims it achieved 80% of Nvidia B200 performance on AMD MI355X GPUs running GLM-5.2, with 2.6x cheaper hardware, by optimizing the software stack. The benchmark, published by …
Anthropic's Claude Sonnet 5 offers a 1-million-token context window at standard pricing with no long-context tax, but the cost of filling it remains significant. Whole-repo Q&A with caching costs abou…
Anthropic launched Claude Sonnet 5, its most agentic mid-tier model, now available in Kilo Code via OpenRouter and direct API. The model achieves 63.2% on SWE-bench Pro and edges past Opus 4.8 on know…
CorvinLabs released CorvinOS, a self-hosted agentic operating system that enforces EU AI Act and GDPR compliance in code, not documentation. The open-source platform connects multiple LLMs to seven me…
Developer Ian Wootten replaced his Claude subscription with open-source models accessed via OpenRouter and the OpenCode harness, citing cost, flexibility, and a desire to avoid vendor lock-in. He buil…
A developer built five free AI tools that replace $200/month in SaaS subscriptions, including a content writer, email writer, social media caption generator, code assistant, and file converter. The to…
MiniMax released M3, a 428-billion-parameter open-weight model, on June 7, achieving 59.0% on SWE-Bench Pro—slightly outperforming GPT-5.5's 58.6%—at $0.30 per million input tokens, making it 16 times…
A developer built an auditable cost-modeling pipeline using exact-rational math to compare LLM provider prices for agent workloads. The analysis found DeepSeek V3.2 on OpenRouter is the best value at …
Hytham H built Phinq, an agent governance system, after a cronjob failure exposed the inadequacy of per-tool hooks. The system uses a proxy that intercepts LLM API calls to enforce deterministic rules…
Anthropic is preparing to release Claude Sonnet 5, codenamed "Fennec," on OpenRouter, according to reports. The model, which was rumored for a February 2026 launch that did not materialize, is now nea…
A developer built a free customer support AI agent for NextJS websites using Hexabot, OpenRouter, and Railway. The agent uses RAG to ingest website content and answer questions, deployed with a free P…
A safety evaluation of Google's Gemini 3.1 Pro Preview found that the same alias routed to two different served systems, producing harmful compliance rates of 57% and 12% on identical requests. The mo…
Kilo Code offers a free AI coding setup using Auto Free for chat, Mistral's free Codestral API key for autocomplete, and a free model for background tasks, eliminating costs for personal projects. For…
ChatbotX, an open-source omnichannel AI marketing platform, launches as an alternative to ManyChat and Chatfuel, supporting platforms like WhatsApp, Facebook, Instagram, and TikTok. Built with Node.js…
A developer warns that HTTP 200 responses from LLM gateways do not guarantee correct output, as gateways like LiteLLM, Portkey, and OpenRouter only check transport-level success. The developer propose…
Meituan launched LongCat-2.0, a 1.6 trillion-parameter Mixture-of-Experts model with 48 billion active parameters per token, available via API for agentic coding and tool use. The model features a 1 m…
Meituan's LongCat team released LongCat-2.0, a 1.6 trillion-parameter mixture-of-experts AI model trained entirely on domestic AI ASICs, claiming it as China's largest model trained on home-grown hard…
A developer tracked OpenRouter's daily usage rankings for a month to see which AI models developers actually use in production. The top five models by token volume were all from Chinese labs or open-w…