Mistral CLI v0.3.0 and Vibe v2.24.2 Released

LangGraph SDK 0.4.3 Released with Decrypt Replacement Result

LangChain released langgraph-sdk 0.4.3, adding a decrypt replacement result feature and supporting clearing cron end_time via update(end_time=None). The update includes dependency bumps and internal fixes across the LangGraph ecosystem.

Liquid AI Releases LFM2.5 Q4_0 Checkpoints via Quantization-Aware Distillation

Liquid AI published LFM2.5 Q4_0 checkpoints, produced through quantization-aware distillation (QAD). The method integrates quantization during training to preserve model quality at 4-bit precision. The checkpoints are available on Hugging Face, offering efficient deployment options for edge and resource-constrained environments.

OpenAI Codex v0.148.0 Adds Markdown Export, Session Forking, and Amazon Bedrock Support

OpenAI released Codex v0.148.0, adding TUI conversation export to Markdown, session forking with `codex exec fork`, draft prompts during startup, and Amazon Bedrock Runtime as a built-in provider. Bug fixes include model switching, session restoration, and sandbox restrictions failing closed on denied paths.

Mojo programming language goes open source

Mojo, the Python-inspired language for GPU programming, is now open source. The compiler and toolchain were released under an Apache 2 license, following the 1.0 release last week. Originally planned as a Python superset, Mojo is now its own language, prioritizing GPU programming ease.

Sentence Transformers Adds Multi-Vector Embedding Models

Hugging Face's Sentence Transformers library now supports multi-vector (late interaction) embedding models, enabling richer document representation. This update allows for more nuanced semantic search and retrieval, improving performance on complex queries.