Neurite is a browser-based AI mind-mapping workspace that places notes, media and AI conversations on a zoomable fractal canvas. It suits researchers, writers and developers who want to organize connected material and give AI agents access to it. The project is open source under the MIT license.
Its graph is both a visual notebook and a conversation interface. Connected AI nodes can exchange messages, share context from linked material and compare models using the same prompts. You can control which agents send or receive messages, including conversations that loop between nodes.
For local AI, Neurite connects to Ollama, transformers.js or a custom endpoint. It can also use OpenAI, Anthropic and Groq alongside local models. Local backends run inference on your hardware; choosing a cloud provider sends inference requests to that service.
The mind map stays synchronized with Markdown-based Zettelkasten notes in both directions, so edits in either view carry across. Graph search and vector search retrieve earlier notes and conversations as context. A local vector database stores material from webpages and PDFs for AI responses grounded in those documents.
The canvas supports images, audio and video alongside text, links and AI nodes. Physics-based node movement and customizable Mandelbrot, Julia and Burning Ship fractals shape the workspace. Wikipedia and Wolfram Alpha searches can place their results directly into the graph.
Claim this page with an email at neurite.network. Neurite gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Neurite?Promote it
Something wrong or outdated on this page?
1.3KUpdated 14 hours agoMIT
macOS · Windows · Web#Agent Skills#Code execution#Hybrid search
Inno Agent is a personal AI learning agent that keeps track of your goals, misunderstandings and study materials across conversations. It's for individual learners and educators who want ongoing tutoring with records they can inspect and correct. The open-source project uses the MIT license and runs as a macOS or Windows desktop app, a self-hosted web interface or a terminal app.
2Updated 6 days agoMIT
macOS · Windows · Linux · Docker · Web#Code execution#MCP#Multi-agent workflows
16.3KUpdated 3 days ago
macOS · Windows · Linux#LM Studio integration#Ollama integration#OpenAI-compatible API
46Updated 7 days agoAGPL-3.0
macOS · Windows · Linux · Browser Extension#Code execution#GGUF#llama.cpp backend
19Updated 1 month agoMIT
macOS · Windows#Batch processing#Hybrid search#LM Studio integration
41.3KUpdated 13 hours agoAGPL-3.0
macOS · Docker · Web#Code execution#Hybrid search#LM Studio integration
RemiAI is a self-hosted AI assistant for people who want chat to work directly with their files and carry context between conversations. It can read and edit folders you permit, extract text from PDFs and office documents, and track file changes. Persistent memory stores facts and preferences across chats, with controls to review and delete them.
SurfSense is an open-source NotebookLM alternative that turns documents into cited answers and editable deliverables on your computer. It's a desktop app for Windows, macOS and Linux, aimed at people working with confidential files, research or study material. You don't need an account.
Vyact is an open source desktop workspace for people who want to use a local LLM with their documents, email and code. It runs on Apple Silicon Macs, Windows and Linux x64 under the AGPL-3.0 license. Intel Macs aren't supported.
AI Notebook is an open-source NotebookLM alternative for people who want to research their own documents on their desktop. It runs natively on macOS 14+ and Windows 10/11, with Ollama for offline AI. You don't need an account. The project uses the MIT license.
AstrBot brings AI assistants into messaging apps such as Telegram, Discord, Slack, QQ and WeCom. It's an open source platform under AGPL-3.0 for people building personal companions, customer support bots or team automation. You can run it on your own computer or server, including through Docker, or use its desktop app for browser-style chat.