Open Source
Microsoft's Orchard Framework Boosts Agentic AI Research
Microsoft Researchhigh confidence
Why it matters
- →Orchard democratizes access to advanced AI research tools, reducing reliance on proprietary systems.
- →It enables seamless integration of research and real-world application by supporting training within deployment harnesses.
- →The framework's flexibility allows for diverse agentic AI applications, from software engineering to personal assistants.
Microsoft Research has launched Orchard, an open-source framework aimed at enhancing agentic AI research. Orchard provides a scalable environment for training and evaluating AI agents across multiple domains, including software engineering and web navigation. The framework allows for training within real deployment harnesses, facilitating a seamless transition from research to application. This initiative addresses the challenge of proprietary infrastructure in AI research, offering accessible tools and data to the broader community.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More in Open Source
© Lev SelectorOpen Sourcemodels
Bonsai 2 and Needle: Tiny Local AI Models
New tiny local models Bonsai 2 and Needle (8-29 MB) demonstrate that small, offline-capable AI can make fast, useful decisions.
Lev Selector
Open Sourceother
llama.cpp b11153 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing first-class ROCm 10.0 support to both Linux and Windows. AMD GPU users no longer need workarounds, effectively closing a long-standing parity gap with NVIDIA's CUDA ecosystem. Equally notable is the new Linux arm64 build targeting Snapdragon chips, which unlocks local AI on high-performance mobile hardware via CPU, Adreno GPU, and Hexagon NPU acceleration. While KleidiAI on Apple Silicon has been disabled in this specific binary, the broader platform expansion signals that llama.cpp is aggressively standardizing how models run across every major silicon architecture.