Knowledge catalogue
Ollama makes it easy to run a model locally, but the hard part for me starts after the model responds: what keeps an agent from having unclear tool permissions, unbounded loops, silent partial failure
I keep seeing the 'use a big model via API as the architect, run local small/mid models as workers' pattern recommended for people with modest local hardware. I've been running it myself (orchestrator
I’m one of the builders of LOLM, a hybrid Transformer–SSM model and agent system from Qira. The model separates surface token processing from persistent latent-state tracking. An NFET controller can s
Meta's Apache-2.0 30B Muse Glimmer targets local agentic tool use, multi-step coding, and vision, sized to leave headroom on 32GB machines.
Disclosure first: I work at Vstorm and I build AgenticOS, an open-source (Apache-2.0), self-hosted platform for building AI agents in a browser. This post was drafted with an LLM's help and edited by
I've been experimenting with running larger models locally with Ollama, mainly because I'm interested in using them for agentic coding. I kept seeing benchmarks expressed as something like: 40 tokens/
I’ve been experimenting with local AI lately, and one thing I’m finding interesting is what comes after getting a model running. Ollama makes local model access pretty straightforward, but for an actu
arXiv:2609.20620v1 Announce Type: cross Abstract: Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate a
Up front: I'm one of the people building the page-perception layer used here. We started by testing small local models. The result turned out to be more interesting than the original test. 12 small mo
I'm looking for more information to expand my creativity around this. I don't really have a realistic idea of what people actually do with local AI yet, I mostly just want to explore the possibilities
arXiv:2609.00669v1 Announce Type: new Abstract: Physical human--robot interaction software often couples desired-behavior specification with constrained realization; we treat these as separate layers.
arXiv:2608.23078v1 Announce Type: new Abstract: Large language models increasingly operate over large collections of tools, functions, APIs, and specialized agents. As the candidate action space grows
I'm running Qwen 3.8 27B locally on a single GPU. I can push the context to 131k, but I'd rather run it faster at 64k if the agent can manage context properly. What I have in mind is pretty simple: on
AQuA's preprint uses 'recursive self-improvement' for a bounded research loop. It does not say the research-agent LM rewrites its own weights. The paper separates three objects: The language model dri
Hey! Like a lot of people here with consumer GPUs (RTX 4060 8GB in my case), I wanted to see if I could use local models for daily coding tasks instead of burning cloud credits on simple boilerplate.
Hello; I'm a semi-beginner at local AI. I've been experimenting with this tech for a while, and I still haven't found a proper harness that fits my models, hardware, and needs. My use case is pretty s
arXiv:2608.08746v1 Announce Type: new Abstract: Prospective daily symptom tracking is central to premenstrual health assessment, but repeated ordinal forms impose substantial response burden. We formu
What Local Embedding + Reranking Models are you guys running for RAG? I went down this rabbit hole because I wanted a Embedding Model + Reranker for a Translation Memory Server. Essentially, given X p
Built my 1st inference machine and have been tweaking models trying to get the most out of my modest hardware. I think I’m at a good place but I’m testing with my own prompts. I’ve looked into some of
Hello fellow local AI people! I took 'you must create your own benchmarks' literally, and built a website for this. How does the end result look like Let's say I want to know which model has most comm
DeepSeek V4 Flash got me thinking... We keep seeing smaller models get way better. A model at a certain parameter count today can be much smarter than a model of the same size from a year or two ago.
I’ve been building ClawLite, an open-source personal AI assistant that talks to you through Telegram and defaults to Ollama (local models). What it does: Multi-agent research with actual cross-source
Most graph-based LLM interfaces use a canvas as a visual layer over what is still a linear chat. I wanted the graph itself to determine what Ollama receives. ThoughtDAG has one rule: wires are the con
arXiv:2607.12713v1 Announce Type: cross Abstract: Generated tokens are a direct driver of the cost, latency, and energy of generative AI (GAI) code editing. We show the format of feedback is a lever o
arXiv:2606.22496v1 Announce Type: cross Abstract: Large language models (LLMs) offer a natural-language interface for interpreting Internet of Things (IoT) sensor data in smart environments; however,
arXiv:2605.17172v1 Announce Type: cross Abstract: Personal AI stacks, like OpenClaw and Hermes Agent, are becoming central to daily work, yet they route nearly every query (often over sensitive local
arXiv:2604.07304v1 Announce Type: cross Abstract: Large Language Models (LLMs) challenge conventional automated programming assessment because students can now produce functionally correct code withou