A solo developer of the network security tool RoamSwitch ran a fire drill using a local LLM to test incident response when network access is severed. The drill simulated a ransomware attack and the lo…
A developer recommends Ollama as a tool for running large language models locally, detailing hardware requirements such as a minimum of 16GB of VRAM or an Apple Silicon Mac with unified memory. The se…
Sentry's AI security research team, led by Armend Gashi and Redon Gashi, presented at DEF CON 34 a new tool called infreerence that demonstrates how adversaries exploit exposed self-hosted inference s…
Developer Hassan Faryad has released MindMirror, an open-source AI companion for emotional reflection that runs entirely on local hardware via Ollama, eliminating the need for paid cloud AI APIs. Buil…
A developer running custom simulation software has moved from cloud-based AI coding assistance to local inference on high-end HPC equipment, using Hermes, Ollama, vLLM, and SGLang with models like Qwe…
A developer at JPMorgan Chase has built 45 AI tools using local models like Llama 3.2 via Ollama, avoiding API costs and data privacy concerns. The tools are open source and available on GitHub, enabl…
Tencent's Zhuque Lab released AI-Infra-Guard, an open-source security scanner for AI systems that fingerprints services such as Ollama, vLLM and ComfyUI, checks them against more than 1,600 known CVEs…
Developer oguzbilgic released Aish, a 300-line Zsh plugin that provides Warp-style AI command suggestions after every shell command, predicting the next command based on failure status, output, and pr…
A developer built a monitoring setup to track AI token spend and usage across Claude Code, Codex, and Ollama in a homelab, integrating metrics into Prometheus and Grafana. The system handles three dif…
TrustGraph 2.8 has been released, introducing an asynchronous architecture, hybrid retrieval, structured output, and a plugin-based workbench. The update replaces thread-per-consumer pub/sub with conf…
A developer's guide to setting up Qwen2.5-Coder locally recommends using the Q4_K_M GGUF quantization to run the 32B model on 16GB machines, reducing RAM requirements from 64GB+ to 20GB with minimal i…
Gremlord, a new open-source tool announced on Hacker News, wraps Anthropic's Claude Code in a local router that lets users run the coding assistant on any model—including OpenAI, xAI, Ollama, vLLM, an…
A developer built Agenci, an open-source CI/CD testing tool for AI agents, and used it to test a local model, phi4-mini running via Ollama. The tool caught a prompt-injection vulnerability: the model …
BankMCP™, a new open-source tool, lets users connect their European bank accounts to AI assistants like Claude and ChatGPT via the standard Model Context Protocol, supporting 2,700+ banks through lice…
Vaenyx, a self-hosted, local-first personal AI agent for households, is now available as a pre-1.0 release, with data stored in a local SQLite database and support for cloud or local model backends. T…
A developer's practical review highlights four AI agent harnesses—Pi, OMP, OpenAI's Codex, and Zcode—used daily for coding and automation, with Pi praised as a minimalist open-source option supporting…
Open Fabrica, a new open-source project, has released a single-binary local AI builder that lets users create and serve AI-powered apps, games, and websites entirely from their own machines, with no h…
A new arXiv paper reports that between January 2024 and March 2026, researchers identified 3,471 original uncensored open-weight AI models on HuggingFace, repackaged an average of 2.4 times, with thre…
A developer praised OpenClaude-Portable, a project that packages the coding agent, runtime, and persistent data into a self-contained folder, making it portable across machines. The tool supports mult…
SayItErmano v0.4.0, an unofficial community port of FluidVoice for Linux, is now available as a local-first voice dictation app that transcribes speech on-device and optionally polishes text via OpenA…