context-mode is a free MCP plugin that intercepts tool output before it hits your context window, cutting token usage by 98% and surviving session compaction across 17 AI coding platforms.
Qwen releases a language model trained to simulate agent environments, not just act in them — beating GPT-5.4 and Claude Opus 4.8 on a new 7-domain benchmark
Moonshot AI's Kimi K2.7 Code lands on AWS Marketplace with EDP billing support, giving enterprise AWS teams a frontier-grade open-weight coding model without a new vendor contract
Seeed Studio's reBot Arm B601 ships full hardware blueprints, a screw-level BOM, and a complete AI software stack for under $1,200 — making research-grade embodied AI accessible to anyone with a workbench.
Handy is a free, MIT-licensed, fully offline speech-to-text desktop app built in Rust that pastes transcriptions directly into any text field — no cloud, no account, no cost.
Microsoft Agent Framework 1.0 hits GA, unifying AutoGen and Semantic Kernel into a single open-source SDK for production-grade AI agents in Python and .NET
GitHub Copilot's desktop app now lets you plug in your own API keys for OpenAI, Anthropic, Ollama, and more — routing inference through your own infrastructure per session.
Together AI's ParallelKernelBench reveals frontier LLMs solve under a third of 87 real multi-GPU kernel tasks, but occasionally beat every public implementation
PydanticAI v2 ships a new 'capability' primitive that bundles tools, hooks, instructions, and model settings into one composable unit, plus a leaner core and the new Pydantic AI Harness library.