AI Wiki — Knowledge Base

ToolOllama8 recent entries

19 Jul 2026Wiki Lint Report — 2026-07-19

Automated lint: 20 errors, 8743 warnings, 3 info

27 Jul 2026Give any Ollama-compatible client session memory + a shared knowledge wiki by swapping the chat URL

Hey folks — I built ContextMemory, an open-source agentic context gateway for apps that already talk to LLMs. The idea is simple: keep your existing POST /api/chat client (Ollama wire format), point i

19 Aug 2026I built Polish – A local AI text polisher and Oracle SQL fixer for Windows with automated PII data masking

Hi everyone, I built an open-source Windows desktop utility called **Polish** that lets you highlight text or SQL in ANY app (Slack, Teams, Outlook, DBeaver, SQL Developer, browser) and rephrase or fi

28 Aug 2026Self-hosted agent + BI platform that runs fully local, Ollama or vLLM for both chat and embeddings

Been building AgentSwarms for a while. Agent platform with RAG, multi-agent workflows and a BI layer over your own data. Posting here because the whole thing runs without a single hosted API if you wa

11 Sept 2026Detecting hallucinations in local models without eating VRAM: What we learned testing 1.5B to 120B models

Hey everyone, If you run local models via Ollama in production or personal projects, you've probably run into the hallucination problem: how do you know when a model is hallucinating without burning e

24 Sept 2026Running a local model as a SQL assistant against real databases: notes on what breaks

Context: we build an open-source (MIT) self-hosted database client and added a natural-language-to-SQL assistant that can point at a local runtime like Ollama instead of a hosted API. I want to share

1 Oct 2026Built an SQLite-based memory system for Ollama that doesn't eat all your VRAM

Wanted to share a project I've been working on to give local Ollama models persistent document memory without needing heavy vector databases. It's called Hillock. The main problem I had with standard

10 Oct 2026Mreaia v1.0.0: Universal Zero-Token Engine & Hardware-Locked Context Distillation for LLMs (>99.9% Reduction)

Hey everyone! 👋 Feeding multi-gigabyte files (SQL dumps, videos, audio, PDFs, and spreadsheets) directly into LLMs often causes context window overflow, GPU VRAM bottlenecks, massive token bills, and

Search: “sql”

Tools