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.
PaddleOCR has unveiled PP-OCRv6, a new OCR model series with significantly improved accuracy and speed.
EAGLE3, an inference acceleration technology, has been merged into llama.cpp, improving inference efficiency.
InfiniteKV has been released, dramatically extending a model's context length by compressing the KV cache and storing it in RAM or on disk.
The Temenos project has been released, isolating only the code that AI agents execute rather than the agents themselves, securing both security and convenience at the same time.
OpenAI has launched the Codex program to support open source project maintainers.
Future AGI has unveiled an open-source AI agent evaluation and observability platform with features similar to LangSmith.
Hugging Face has released Open-R1, an open-source project to reproduce DeepSeek-R1's training pipeline.
It's an open-source engine that automatically indexes files within a folder, allowing AI agents and users to search them using natural language.
A team of former Hugging Face members has launched Refiner, a data refinement library that supports a variety of robotics data formats.
A memory layer engine that provides fact extraction, automatic forgetting, and hybrid search to supplement AI's short-term memory limitations.
The maintainer of the open-source testing engine Jqwik sparked controversy by adding a log that refuses the use of AI coding agents.
SenseNova-U1 model weights and InternEvo-based training code have been open-sourced.
A fine-tuned model specialized for infographic structure output, based on SenseNova U1-8B-MoT, has been released.
LiteLLM has launched an open-source platform for building autonomous agents using a variety of LLMs.
GitHub-hosted, Microsoft-owned open-source projects were hacked in a supply chain attack that steals credentials from users of AI development tools.
Xiaomi's MiMo team has unveiled MiMo Code, an open-source coding agent designed for complex, long-horizon coding tasks.
Cohere has released North Mini Code, an open-source agentic coding model for developers.
SCAIL-2, a model that animates characters via video without intermediate representations, has been released.
The ntkMirror technique, which prevents hallucinations by leveraging changes in a model's answers depending on evidence order, has been released.
It's a security firewall tool that monitors AI agent traffic and controls execution according to HCL rules.
Cohere has released North Mini Code, an MoE model optimized for agentic software engineering.
The Duckle MCP server has been released, allowing Claude to build data pipelines directly in a local environment.
Luce Spark has been released, learning real-time routing patterns to efficiently keep MoE experts resident on the GPU.
An update has been applied to llama.cpp that improves inference performance for Gemma-4 models by preventing KV cache copying.