Local note engine uses LLM to organize notes into a knowledge graph
i take a lot of notes but rarely find time to organize them so the value of most notes in my personal context quietly disappears. Notecast is a local note engine i've been building to help me with that. it runs a three stage LLM pipeline (Classify -> Organize -> Consolidate) that automatically builds and maintain a knowledge graph from the notes. the theme hierarchy emerges by subdivision as notes accumulate. Any change generates a proposal that can be edited and commited by the user. It is early stage and a lot of architectural and domain logic decisions might change but the core is working…
In plain words
Notecast is a local note-taking tool that automatically organizes notes into a knowledge graph using an on-device language model. It runs a three-stage pipeline to classify, organize, and consolidate notes, with the organizational structure emerging naturally as content accumulates. Users review and approve any proposed changes before they're committed. The tool integrates with Obsidian vaults and is actively under development.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
i take a lot of notes but rarely find time to organize them so the value of most notes in my personal context quietly disappears. Notecast is a local note engine i've been building to help me with that. it runs a three stage LLM pipeline (Classify -> Organize -> Consolidate) that automatically builds and maintain a knowledge graph from the notes. the theme hierarchy emerges by subdivision as notes accumulate. Any change generates a proposal that can be edited and commited by the user. It is early stage and a lot of architectural and domain logic decisions might change but the core is working and is already useful. It has Obsidian vault integration. I recommend using it (just set vaultPath on configurations) I'm actively developing it this year and would love feedback.
Does the same job
all alternatives →
- NINotesOllama – I added local LLM support to Apple Notes (through Ollama)2024 · smallest.app · ▲156
This lets you talk to local LLMs in Apple Notes. I saw Obsidian Ollama (https://github.com/hinterdupfinger/obsidian-ollama) and thought it was handy, but I'm too lazy to migrate away from the Apple ecosystem, so I quickly hacked this together. I tend to use Notes as a scratchpad for prompts, so it's nice to do some quick inference without leaving the app. Notes doesn't really support plugins so I'm using the macOS accessibility API for reading selections and then stream responses using the clipboard (not ideal but it works).
- OTOdin – the integration of LLMs with Obsidian note taking2023 · github.com · ▲160
- RAReor – An AI note-taking app that runs models locally2024 · github.com · ▲411
Reor is an open-source AI note-taking app that runs models locally. The four main things to know are: 1. Notes are connected automatically with vector search. You can do semantic search + related notes are automatically connected. 2. You can do RAG Q&A on your notes using the local LLM of your choice. 3. Embedding model, LLM, vector db and files are all run or stored locally. 4. Point it to a directory of markdown files (like an Obsidian vault) and it works seamlessly alongside Obsidian. Under the hood, Reor uses Llama.cpp (node-llama-cpp integration), Transformers.js and Lancedb to power…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com