What if your AI could organise your knowledge without sending it to the cloud?

Federico — Sat, 07 Nov 2026 17:26:40 +0000

That's the idea behind Knemora, an open-source, local-first AI Second Brain I've been building in my spare time.

Imagine turning your documents into interconnected knowledge, exploring relationships, and asking an AI questions about everything you've collected.

All running locally, on your own machine.

A few weeks after releasing the first alpha, I realized something:

Building an AI application is one thing. Making it genuinely useful every day is another.

So I kept building.

Knemora v0.2.0-alpha is here!

This update focuses on making Knemora more reliable, responsive, and easier to use.

Here's what's new:

Better conversation continuity and automatic language matching.
Wiki and Direct Chat Modes.
Fast and Deep reasoning controls.
Stronger knowledge compilation and relationships.
Gemma 4 E4B joins the tested local model registry.

I also ran a small benchmark comparing Qwen3-8B and Gemma 4 E4B.

In this particular Direct-mode test, Gemma delivered 20.6% lower median application latency and 31.1% higher decode throughput.

Not a universal benchmark, just another step toward making local AI more responsive.

Knemora is still in alpha, and there's plenty left to improve. I'm building it one iteration at a time, with the goal of reaching a stable v1.0.0.

Would you use a local AI to build your own connected knowledge base? What would you expect it to do?

GitHub: https://github.com/federicolaterra/knemora

Website: https://knemora.space

Watch the demo: https://www.youtube.com/watch?v=kl5qNrWPOnY

Feedback and contributions are always welcome!

Building Knemora: An Open-source, Local-first AI (SI) Second Brain

Federico — Wed, 14 Oct 2026 14:05:42 +0000

I’m Federico, a visual designer and full-stack developer.

About six months ago, I had an idea I kept coming back to: could I turn documents and datasets into connected knowledge, explore the relationships visually, and ask questions without sending my material to a cloud inference service?

Why I built Knemora?
After a lot of research, architecture decisions, late nights, and interface iterations, that idea became Knemora.

How it works?
It’s an open-source, local-first AI (SI) Second Brain. You bring your documents and datasets; Knemora compiles knowledge into a portable Markdown wiki, connects pages, and makes that knowledge available through search, a native graph, and chat with source citations.

Architecture:
The diagrams below show the system architecture and the knowledge/inference workflow.

A few choices behind the architecture:

Portable knowledge: Markdown pages with frontmatter and explicit links. The graph is a rebuildable view of those connections.
Local inference: llama.cpp with Qwen3-8B Q3_K_M as the default model.
Retrieval: BM25 search and bounded graph navigation, without a vector database.
Traceability: original documents are preserved, and generated claims carry source references.
Dataset analysis: Polars performs structured calculations, keeping numerical results grounded in computation.

The stack includes Vue 3, FastAPI, Google ADK, SQLite, and Sigma.js/Graphology.

The initial alpha targets macOS Apple Silicon. Node.js 24 with npm is required; the launcher manages the remaining runtimes and model downloads. Initial setup needs internet access, while the core knowledge and inference workflow runs locally afterward. There’s also an isolated demo with interconnected sample knowledge.

As a designer, I care about making the interface clear and the graph useful. As a developer, I care about keeping the underlying knowledge portable and understandable.

Open-source software has helped me throughout my career, and I’m proud to contribute something of my own. This is an early alpha, with plenty left to improve.

Code, documentation, and setup:
github.com/federicolaterra/knemora

Website:
knemora.space

DEV Community: Federico

What if your AI could organise your knowledge without sending it to the cloud?

Building Knemora: An Open-source, Local-first AI (SI) Second Brain