AI Briefing#open-source
The latest AI and developer news about #open-source, with the original source and a short summary.
The latest AI and developer news about #open-source, with the original source and a short summary.
The new program covers all Vercel products and open-source projects, consolidating previous private and OSS initiatives.
An open-source project has been released that enables running NVIDIA's Parakeet speech recognition model on the JVM with native-like performance.
Jevper, an open-source library that performs Jev classification on OpenAI-compatible APIs, has been released, offering automatic logprobs detection and reasoning model support.
Hugging Face has added native support for the GGUF format to the Transformers library, enabling debugging and flexible use of locally quantized models.
A tool named 'stuntd' for Claude Code has been released, which determines command permissions locally without API calls.
The rootless sandbox tool 'Drop' has been released, blocking dangerous command execution by AI coding agents at the OS level and supporting gVisor.
The PostgreSQL extension pgjev has been released, enabling natural language row filtering in SQL WHERE clauses without embeddings or vector columns.
AntLing has released the open-source 6B image generation model 'Ming-Image-0.1-Design' and related agent skills.
TextCLF has released 'Quant Factory', an open-source tool that enables immediate 4-bit quantization without calibration data.
The MCP server proofcut for Claude Code has released transcription-based automatic editing and self-verification rendering features.
A new benchmark, LinearSolveBench, has been released to evaluate the ability of AI models to write C-language numerical solutions for large-scale sparse linear systems.
The open-source dynamic quantization tool 'Dynamic Quantiser' has been released, offering higher accuracy than standard quantization in VRAM-constrained environments for llama.cpp-compatible GGUF files.
NVIDIA has released Isaac ROS 5.0, featuring enhanced AI agent workflows and GPU acceleration capabilities.
NVIDIA has released AIPerf, an LLM inference benchmarking tool that eliminates client-side bottlenecks.
Xiaomi released 'MiMo-V2.6-Distill-Qwen-9B', an agent-specialized model fine-tuned from Qwen3.5-9B using MiMo data.
Alibaba Qwen has released Qwen-Image-2.1, an image generation model that reduces parameters to 7B and supports transparency generation.
Jared Palmer released Kev, a lightweight decision-making model based on Qwen3.5, offering simultaneous processing of Yes/No, multiple-choice, and rating tasks with Apple Silicon support.
Hugging Face has hired oMLX developer Jun Kim to strengthen support for the Apple Silicon-based MLX ecosystem and local AI infrastructure.
The open-source tool 'phantom-kv' has been released, bypassing LLM censorship by injecting approximately 18MB of KV cache without modifying model weights.
Starting with Claude Code 2.1.224, inter-session communication is supported via JSON files and Unix sockets, and an open-source bridge project leveraging this has been released.
Foremerge v0.5.0, a Rust-based open-source coordination protocol that pre-detects logical conflicts between parallel AI coding agents, has been released.
Microsoft has open-sourced the code and weights of RetroChimera, a retrosynthesis AI published in Nature, under the MIT license.
The open-source Kev series of decision models based on Qwen3.5 has been released, offering TypeSafe API compatibility and detailed performance metrics.
A Claude Code plugin has been released that selectively deletes unnecessary tool call results without summarizing the conversation, utilizing TypeSafe AI's Jev model.