Open-source security labs for tool-using agents, MCP servers and retrieval pipelines.

GitHub's architectural redesign separates compute from storage as agent workloads grow.

Installed skill discovery, MCP Apps and backups to external storage.

Action-grounded causal traces for pretrained robot policies.

Open-source long-context inference engine with pluggable KV-cache strategies.

Cloudflare Artifacts and Workers enable programmable agent-era repositories.

Google's open-source Genkit framework reaches its first stable Dart and Flutter release.

Open-source local LLM server with priority scheduling and crash-resumable sessions.

JetBrains' open coding model trained with large-scale sandboxed reinforcement learning.

Google's study of dependency-update effort and complexity.

An agentic OS layer with skill security and shared CLI.

Early Rubin vLLM inference benchmarks, kernels and MoE locality.

Prime Intellect's technical report on an agent-orchestrated Rust rewrite.

Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

I spent most of my career in managed-runtime languages like Java and Python, so coming to Rust presented a few new land mines for me. I'm now about six months into primarily writing code in Rust, or more accurately, causing code to be authored in Rust, and I