223 stories
NVIDIA Nemotron 3.5 Lightning is now available on Ollama. It's a 30 billion parameter (3B active) open model built for agents that stay running, gathering context, calling tools, and working through multi-step tasks on your own hardware.
Meta's Muse Glimmer, the first open model released by Meta Superintelligence Labs, is now available. Muse Glimmer is a 30B multimodal model released under the Apache 2.0 license, designed for local coding agents, and accelerated by Ollama's MLX engine with new native DFlash and image input support.
Serene Docs Search is a self-hosted, Apache 2.0-licensed documentation search stack with BM25, optional hybrid search, Ask AI and MCP, powered by SereneDB.
Status: Proposed Experimental implementation: Draft PR #17784 TL;DR LobeHub currently uses SWR keys as request identities and, for selected domains, persist...
Last Updated on July 30, 2026 Microsoft Word users now have several AI assistants to choose from. Two notable options are GPTLocalhost and GPT for Word. Both integrate […] The post GPTLocalhost vs GPT for Word: Which AI Assistant for Microsoft Word Is Right for You? appeared first on GPTLocalhost.
Notebook by Kacper Łukawski 🚀 Part of Haystack 3.0 Launch Week: five days of new drops (July 20–24). In this notebook, we build a fully local, fully async agent that uses a skill to change how it reports back, and a custom bash tool to actually use the machine it runs on.
In this tutorial, I’ll show you how to serve a multi-user local AI agent as a REST API using FastAPI, then add a lightweight Streamlit UI on top. Instead of interacting with the agent through a termin
Ollama runs language models on your own hardware with almost one command. The catch is picking one your machine can hold. How to read a model listing, do the RAM math, and run it.
Prompt injection turns untrusted data into instructions a model obeys. The categories of prompt injection examples, why they work, and how to defend without pretending it is solved.
The best local LLM is the smallest one that does your task and fits your memory. A buyer's guide organized by hardware tier and task, with honest evaluation advice.
Claude Code is a terminal agent you delegate tasks to; Cursor is an AI-first editor you stay inside. A fair comparison of form factor, interaction and where each one shines.
Serving 8.9 million developers, Ollama has raised $88M from Benchmark, Theory Ventures, 8VC, Y Combinator, and many incredible angel investors.
Folders, faster and more secure video with AI captions and translations, new AI features, an integrated dashboard, and a lot more.
Using Open-Weight Models in Local Coding Harnesses as an Alternative to Claude Code and Codex Subscriptions
Lightpanda now has a built-in agent. Talk to it in natural language, get a reliable script back. Run that script forever only calling an LLM when it needs fixing.
Ollama's MLX engine has been updated to deliver its highest performance on Apple Silicon yet. Models output higher quality responses, respond faster, and use less memory.
Learn how Hexabot uses LiteLLM to connect built-in AI actions to 100+ model providers through one OpenAI-compatible gateway.
Ollama 0.30 is now available with improved performance and GGUF model compatibility through llama.cpp. This augments Ollama's MLX engine on Apple silicon, bringing support to more models on a wider range of hardware.
Showing 162 of 223 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
