AI and infrastructure news
Filter by type: Project140
- 18 days ago github.com
OpenTinker proposes RL infrastructure for foundation models
A description published on January 8, 2026 presents an open-source reinforcement learning platform for agents, separating programming from execution and enabling a transition from training to inference.
- 18 days ago github.com
OpenVul proposes an LLM framework for vulnerability detection
Published on March 5, 2026, the OpenVul repository describes an open-source post-training framework for language models aimed at vulnerability detection.
- 18 days ago github.com
Penny: GPU communication in an open-source library
The Penny repository, published on October 26, 2025, presents a hand-crafted GPU communication library that is open to the community. Companies can assess its fit through controlled testing.
- 18 days ago github.com
Research on LLMs for vulnerability detection
A GitHub collection gathers research on using language models to detect software vulnerabilities in functions and repositories, including agent-based approaches. Published on June 14, 2026.
- 18 days ago github.com
pyptx brings PTX kernels to Python workflows with JAX and PyTorch
Published on April 25, 2026, the pyptx repository presents a Python DSL for NVIDIA PTX kernels, with Hopper and Blackwell support and examples of accelerated computing operations.
Compact reasoning could lower inference costs
A post published on April 22, 2026 describes Latent Reasoning Tuning, a method that trains models to reason with compact internal representations and claims gains over other efficient reasoning methods on mathematics and general benchmarks.
- 18 days ago github.com
Community recipes for serving LLMs on RTX GPUs
Published on May 24, 2026, the repository collects model-independent configurations for serving LLMs on RTX 3090, 4090, and 5090 GPUs, using vLLM, llama.cpp, and ik_llama.
- 18 days ago github.com
Speech recognition across more than 1,600 languages
On November 10, 2025, Meta announced open-source speech recognition models and a dataset covering more than 1,600 languages, including 500 described as previously unsupported.
- 18 days ago github.com
Cybersecurity resources: posts, papers and tools
A GitHub list gathers blog posts, writeups, papers and cybersecurity tools as a starting point for engineers.
- 18 days ago github.com
Open-source repository provides a starting point for voice agents
Published on February 6, 2026, the repository offers a basis for engineers to create voice agents with open-source models.
Scaled dot-product attention: from mechanism to practice
A post published on February 1, 2026 explains how queries, keys, and values guide token relevance and presents a notebook for implementing LLM and NLP systems from first principles.
- 18 days ago github.com
slime v0.2.2 expands Int4-QAT and R3 support
Published on January 18, 2026, the slime v0.2.2 version announcement highlights memory and performance improvements, Int4-QAT training, and R3 support with DeepEP and MTP.
- 18 days ago github.com
Stop hooks can keep agents on longer tasks
An Anthropic post dated December 27, 2025 describes using a stop hook to ask an agent to continue after it stops, presenting the technique as support for orchestrating longer tasks.
- 18 days ago github.com
Tencent presents HPC-Ops operators for LLM inference
On January 27, 2026, Tencent presented HPC-Ops, an open-source library of operators for LLM inference, with GPU operations and multinode communication support.
- 18 days ago github.com
Training neural networks on the Neural Engine: evaluating the ANE repository
Published on March 2, 2026, the ANE repository describes neural network training using private APIs reverse-engineered from Apple's Neural Engine. Learn how to evaluate this approach before adopting it.
- 18 days ago github.com
UNITTS combines inference and benchmarking for speech synthesis
A post dated June 9, 2026 presents UNITTS, a toolkit for inference and benchmarking of open-source TTS models, with support for Chatterbox and Fish Audio s2-pro.
- 18 days ago github.com
Voice agents: parallel models may reduce silence
A contribution to Gradbot, published on June 5, 2026, describes sending a brief response to TTS while another model reasons and calls tools in the background.
- 18 days ago github.com
Public exploit index supports CVE security testing
Published on October 6, 2025, the repository indexes public proof-of-concept exploits linked to CVEs across five sources, supporting vulnerability research and security testing.
- 18 days ago github.com
NVIDIA Model Optimizer gathers model compression techniques for inference
NVIDIA published a post on Model Optimizer, a library with quantization, distillation, pruning, neural architecture search and speculative decoding, with exportable checkpoints for vLLM, SGLang, TensorRT-LLM and TensorRT.
- 18 days ago github.com
8-bit emulators in standalone C headers
Published on July 15, 2026, the floooh/chips repository collects emulators of chips and 8-bit systems implemented as standalone C headers.
- 18 days ago github.com
Anthropic repository outlines a security analysis and remediation workflow
Published on July 12, 2026, the repository includes skills for threat modeling, scanning, triage, and patching, plus a customizable harness for autonomous scanning.
- 18 days ago github.com
Reverse engineering roadmap guides malware analysis
Published on June 25, 2026, the GitHub repository organizes reverse engineering and malware analysis topics and tools, including x86/x64 assembly, static and dynamic analysis, and anti-RE techniques.
- 18 days ago github.com
Structuring transcription for long recordings
A description published on September 17, 2025 presents a Python tool that splits audio using voice activity detection, processes parallel calls, and accepts multiple media formats.
- 18 days ago github.com
Agentic components for APIs: what the repository demonstrates
Published on GitHub on July 24, 2024, the repository gathers agentic components for Llama Stack APIs and highlights the use of tools and functions with Llama 3.1 models.
- 18 days ago github.com
RAG tutorials outline techniques for improving search
Published on October 15, 2024, the RAG_Techniques repository offers notebooks on reranking, chunking, filtering, and Graph RAG to explore retrieval-augmented generation approaches.
- 18 days ago github.com
ckit.h: reusable utilities for C projects
Published on October 2, 2025, the ckit.h repository describes itself as a small kit of essentials for C projects. This pauta outlines how a company could assess its suitability and integrate it into its codebase.
- 18 days ago github.com
Audio codec for Speech LLMs: parallel tokens and streaming
In a post published on October 17, 2025, Meituan presented an open-source audio codec optimized for Speech LLMs, with parallel semantic and acoustic tokens at 16.7 Hz and low-latency streaming decoding.
- 18 days ago github.com
How to assess tools that bypass network inspection
A publication dated August 30, 2024, cites three open-source tools for bypassing deep packet inspection and points to a practical use: assessing network filtering controls.
- 18 days ago github.com
How to build a RAG pipeline for PDFs
A notebook published on November 28, 2024 demonstrates a RAG recipe for PDFs with Docling and Weaviate, using document conversion to Markdown or JSON.
- 18 days ago github.com
DeepSpeed Domino and distributed LLM training
A November 26, 2024 post describes a tensor-parallelism mechanism designed to reduce communication overhead in LLM training.
- 18 days ago github.com
DocEx tests defenses against document exfiltration
Published on April 20, 2025, the text describes DocEx, an APT emulation tool that simulates the exfiltration of DOCX, PPTX, XLSX, and PDF files to assess security defenses.
- 18 days ago github.com
Hibiki: streaming speech translation
A repository published on February 6, 2025 presents a decoder-only model for simultaneous French-to-English and English-to-French speech translation, trained on synthetic data.
- 18 days ago github.com
Linux-insides updates chapter on kernel boot
On September 24, 2025, the linux-insides project updated its fourth chapter on Linux kernel boot to cover modern kernel versions.
- 18 days ago github.com
LLM Compressor brings model compression techniques to vLLM
In a post published on August 16, 2024, Neural Magic introduced a library of compression techniques intended to reduce inference latency while preserving accuracy.
- 18 days ago github.com
Mirage compiles LLMs into persistent megakernels
Published on June 19, 2025, the publication describes a compiler that transforms LLMs into persistent megakernels and claims latency reductions of 1.2 to 6.7 times.
- 18 days ago github.com
OpenScholar brings code, models and 45 million papers
On November 19, 2024, the OpenScholar repository presented code, model checkpoints, a collection of more than 45 million papers through October 2024, and the ScholarQABench benchmark.
- 18 days ago github.com
Qwen3-Omni: multimodal models with speech
On September 22, 2025, Qwen introduced three models combining text, images, audio, and video, with speech input and output.
- 18 days ago github.com
Fast response to compromised crypto wallets
Published on October 16, 2024, the text describes an open-source Bash script for attempting to recover funds from compromised wallets before bots move them.
- 18 days ago github.com
A Python RLM implementation for long contexts
Published on October 17, 2025, this repository presents an open-source Recursive Language Models implementation that keeps long inputs in a Python environment for analysis.
- 18 days ago github.com
SkyRL tx v0.0.2 enables multi-LoRA training
On October 14, 2025, version 0.0.2 of the open SkyRL tx backend added support for training multi-LoRA models through the Tinker API.
Let's assess your project

I reply with scope and a proposal.






































