Latest

Open-source AI agent frameworks have quietly turned into infrastructure, and the proof isn't in anyone's marketing copy. It's in version numbers and shell commands. Microsoft Agent Framework landed at 1.0 GA advertising "graph-based workflows, multi-agent orchestration, and human-in-the-loop support" (Microsoft agent

The OpenAI Agents API entered public beta on September 10, 2026, per Tech Insider's tutorial. Quick answer for the scanners: no platform fee, beta live since September 10, 2026. And the only cost is the tokens plus tools your agents use. What shipped under that date matters more

TruLens's Agent GPA evaluator caught 267 of 281 human-annotated agent errors on TRAIL/GAIA, a 95% catch rate against 55% for a baseline trace judge. That 40-point gap is the entire argument for open-source LLM evaluation frameworks for autonomous agents. If you grade your agents on final output

Open-source multi-agent orchestration frameworks look like a safe category to shop in 2026. They aren't. The licenses are genuinely open, the companies behind them aren't neutral. And the AutoGen-plus-Semantic-Kernel consolidation into one MIT-licensed successor — Microsoft Agent Framework. Reshuffled this whole market from the top down. If

At Microsoft Build 2026, GitHub showed off a desktop Copilot app. Help Net Security describes it as "a desktop application built for working with AI coding agents" and a "dedicated workspace for directing several agents at once." That's the loudest signal yet that agentic

OpenAI's Evals repo sits at roughly 18.5k GitHub stars, and it has company. A 2026 comparison counted 11 new open-source eval frameworks that emerged in the past 12 months, stacked on top of established names like DeepEval and Ragas. Benchmarking LLM agents used to mean trusting a