1. Conduid
  2. RAG
  3. VLS 32M Context Local LLM
MCP server · RAG

VLS 32M Context Local LLM

by · github.com/Veloresearch/VLS-32M-Context-Local-LLM

Give Claude Code, Codex and opencode a 32M-token memory that never leaves your machine. Local LLM server (MCP + OpenAI API) that runs any GGUF model with a context far larger than its window - no cloud, no retraining, no vector database. Windows and Linux, one command.

Unclaimed aiai-agentsclaude-codeggufinference-serverlinuxllama-cppllmlocal-llmlong-contextmcpmcp-serverofflineopenai-apiprivacyragrustself-hostedvector-databasewindows
InstallView source
34Low

Scored 13 days ago · breakdown

About VLS 32M Context Local LLM

VLS 32M Context Local LLM is an MCP server published by Veloresearch in the RAG category: give Claude Code, Codex and opencode a 32M-token memory that never leaves your machine. Local LLM server (MCP + OpenAI API) that runs any GGUF model with a context far larger than its window - no cloud, no retraining, no vector database. Windows and Linux, one command.

The repository has 5 stars and 0 forks, with the last commit 6 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/Veloresearch/VLS-32M-Context-Local-LLM

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about VLS 32M Context Local LLM

Powered by Claude · Grounded in docs

I know everything about VLS 32M Context Local LLM. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.1.1-preview.2.1VLS 0.1.1 Preview 2.1 · 11 Oct 2026VLS 0.1.1 Preview 2.1 fixes what people hit first in Preview 2. Fixed Schematics:** A microcontroller with LEDs, buttons and an RGB LED (ESP32, ESP32-S3, Arduino) now comes from a checked design: every LED with its resistor, every button…
v0.1.1-preview.2VLS 0.1.1 Preview 2 · 11 Oct 2026VLS 0.1.1 Preview 2 is the biggest update so far: VLS now opens as its own app, the chat can search, calculate, run code and draw, and every screen was rebuilt. Install Windows:** download `VLSSetup.exe` and run it. It's an unsigned…
v0.1.1-preview.1VLS 0.1.1 Preview 1 · 11 Oct 2026The whole panel, redesigned. Apple-style continuous corners and calm, solid surfaces everywhere; a new sidebar and a simple toolbar with one model switcher and one machine meter; a Home that walks you from first start to first answer;…
v0.1.0-preview.56VLS Preview-56 · 9 Oct 2026A new look, faster memory, and an ASCII wallpaper. Solid, Apple-style interface: small controls are pills, icon buttons are circles, and nothing is outlined any more. Top bar chips are solid pills; focus rings show only for the keyboard.…
v0.1.0-preview.55VLS Preview-55 · 7 Oct 2026AMD and Intel GPUs. VLS now runs models on any Vulkan GPU, including the Radeon built into Ryzen processors, on Windows and Linux. New Windows package with the Vulkan engine (VLS-windows-x64-vulkan.zip); the installer picks it for AMD and…
Questions

About VLS 32M Context Local LLM

How do I install VLS 32M Context Local LLM?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is VLS 32M Context Local LLM safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is VLS 32M Context Local LLM still maintained?

Yes — the latest release is v0.1.1-preview.2.1 (11 Oct 2026), and the last commit was 6 days ago. The repository has 5 stars.