Open-Source AI Hub · sourced & dated

Open-Source AI

Hugging Face, GitHub, Ollama, local models, agent frameworks

147 stories published 100% sourced & dated

The lead

Latest first

Latest in Open-Source AI

Open-Source AI GitHub Ships CodeQL 2.26.4 With Go 1.27 and Actions Fixes

GitHub Ships CodeQL 2.26.4 With Go 1.27 and Actions Fixes

CodeQL 2.26.4 adds Go 1.27 support, improves Rust alert locations, and strengthens GitHub Actions security detections across C#, Java/Kotlin, and Actions workflows.

Jinultimate · Sep 8, 2026
Open-Source AI MSTest 4.4 Lets .NET Tests Run as Native AOT Executables

MSTest 4.4 Lets .NET Tests Run as Native AOT Executables

MSTest 4.4 adds source generation so test projects can publish as Native AOT executables, matching the deployment model of the apps they…

Jinultimate · Sep 6, 2026
Open-Source AI Go 1.27 adds generic methods and faster allocation

Go 1.27 adds generic methods and faster allocation

Go 1.27 lands generic methods, a 30% cut in small-object allocation cost, post-quantum ML-DSA signing, and a native UUID package in the…

Jinultimate · Aug 20, 2026
Open-Source AI AutoMem finds task-specific memory that beats hand design

AutoMem finds task-specific memory that beats hand design

Researchers built AutoMem to search for the best agent memory per task. It outperformed human-designed baselines by 2.8 points and cut token…

Jinultimate · Aug 19, 2026
Open-Source AI Public EEG models can be turned against private AI

Public EEG models can be turned against private AI

Researchers showed that open EEG foundation encoders let attackers build adversarial samples from public models that fool private brain-signal AI.

Jinultimate · Aug 19, 2026
Open-Source AI DeAR lets AI agents collaborate without a central controller

DeAR lets AI agents collaborate without a central controller

DeAR drops the central dispatcher in multi-agent AI, letting agents consult peers directly and beat baselines on 9 reasoning tests.

Jinultimate · Aug 19, 2026
Open-Source AI New redaction model explains every cut it makes

New redaction model explains every cut it makes

A new arXiv paper shows a redaction model that follows plain-language rules and explains each removal, making AI sanitization auditable for legal…

Jinultimate · Aug 19, 2026
Open-Source AI Memory trained on one AI model can run on another

Memory trained on one AI model can run on another

Engram-style memory frozen on one language model can be reused on another once a small reader is tuned to the target, nearly…

Jinultimate · Aug 19, 2026
Open-Source AI Aegis puts a trusted gate between AI agents and your tools

Aegis puts a trusted gate between AI agents and your tools

Researchers built Aegis, a runtime layer that approves or blocks each AI agent tool action and logged zero risky side effects across…

Jinultimate · Aug 19, 2026
Open-Source AI GitHub adds org-wide code quality trend tracking

GitHub adds org-wide code quality trend tracking

GitHub's Code Quality dashboard now plots open findings over 7, 14, or 30 days and ranks repositories by improvement, so teams catch…

Jinultimate · Aug 19, 2026
The zBrandco Edition

Never miss what matters in Open-Source AI.