Developers gain access to Mojo's GPU-optimized compiler for AI/ML workloads with Python-inspired syntax.
Mojo programming language releases compiler and toolchain as open source under Apache 2 license after promising this since 2023.
A lightweight Python runtime introduces a context type system that enforces type safety on agent context objects before prompt serialization to prevent type confusion bugs.
FreeToken enables running 290B+ parameter MoE models locally on consumer hardware with optimized CPU-GPU co-execution and semantic caching.
LLM Anthropic plugin v0.27 released with compatibility for anthropic Python SDK v1.0.0 migration from httpx to httpx2.
OCR It is a Chrome extension that extracts text from un-copyable documents using offline Tesseract OCR for LLM processing.
OpenAI is removing instructions for automated export to Promptfoo from Evals in its cookbook, making migration a manual configuration process.
