Verba, an open-source language-learning app, lets users practice eight languages through conversations with an AI that runs entirely offline on their machine, with no account or server required. The a…
Deviad's job-hunter repository provides a complete job-search pipeline for the Pi Agent, enabling search, scoring, salary enrichment, and assisted applications via Node.js scripts and Docker services.…
Project Nexus YR released Xyzzy, an open-source (Apache-2.0) Python framework for multi-human and AI-agent teamwork with a tamper-evident, hash-chained event log, available via Docker (ghcr.io/project…
Unsloth Desktop, an open-source Apache-licensed application from the two-brother team Daniel and Michael Han, lets users run and train large language models locally on Windows, macOS, and Linux, with …
A developer has identified critical security blind spots in local AI workflows, including unauthenticated network exposure when tools like Ollama and vLLM bind to 0.0.0.0, clipboard API key leakage, a…
A developer reported that LM Studio's runtime auto-update silently broke model loading on an RTX 5090, with the error dialog showing an unsigned exit code that decodes to an NTSTATUS value indicating …
A Linux novice reports that combining AMD's Strix Halo integrated GPU (Radeon 8060S) with an external Nvidia RTX 2080 Ti via Oculink for local LLM inference is problematic, with LM Studio failing to d…
A practical guide from an unnamed author outlines a four-layer framework for building productive local AI stacks with small language models (1B–14B parameters), naming Ollama, LM Studio, llama.cpp, an…
Revalvo, a new local-first LLM evaluation workbench, launched on Product Hunt today, enabling users to run prompts against multiple models in parallel with per-response latency, tokens, and cost track…
A developer has released OIHK, an open-source autonomous multi-agent AI penetration-testing engine that requires real tool execution and independent validation before reporting a finding, avoiding the…
A developer running an automated content pipeline on a Mac mini with 48GB of unified memory switched from a cloud LLM API to a local model after the provider's free tier rate limit dropped from 60 to …
LM Studio has added Z.ai's GLM-5.3-Flash model to Bionic, its AI agent platform for Mac and Windows, bringing multimodal input, a 1-million-token context window, and pricing up to 10 times cheaper tha…
Apple Inc. unveiled the Mac Studio powered by M5 Max and M5 Ultra chips, featuring up to 1.2TB/s memory bandwidth, the most powerful Apple silicon GPU, and on-device AI capabilities for running large …
IBM released Granite 4.2, a family of open reasoning language models in 3B, 8B, and 30B parameter sizes, available under Apache 2.0. The models are decoder-only dense transformers pre-trained on rough…
Apple introduced the M6 and M5 Ultra chips, with the M6 being its first 2nm chip debuting in a Mac mini at $899 and the M5 Ultra powering a Mac Studio with up to 512GB of unified memory and 1.2TB/s ba…
Apple launched a new Mac mini with M6 and M5 Pro chips, featuring up to 4x faster AI performance, 2x faster storage and graphics, and 40 percent faster CPU performance compared to M4 models. The M6 mo…
Apple announced the new Mac mini with M6 and M5 Pro chips, delivering up to 4x faster AI performance, 2x faster graphics and storage, and 40 percent faster CPU performance, with pre-orders starting to…
Apple unveiled the next-generation Mac Studio, powered by the M5 Max and M5 Ultra chips, with the M5 Ultra offering up to a 36-core CPU, an 80-core GPU, and up to 512GB of unified memory. The M5 Max M…
A new developer stack is emerging for AI agents, privacy, and lightweight tooling, moving away from centralized 'wrapper apps' to local-first, modular, and privacy-centric architectures. Tools like Ch…
A developer discovered that their local LLM was running at only 1.6% of its context capacity due to a default setting in LM Studio, which capped the context length at 4096 tokens despite the model sup…