
Kady is a free, open-source AI research assistant for scientists who want to carry out analyses and review evidence on their own computer. You describe the task in plain language, and it can inspect files, write and run analysis code, search literature, and produce figures or reports. It uses the MIT license.
Projects, conversations, notebooks and results stay in ordinary local folders; K-Dense doesn't host or store them. Model choice determines what leaves your machine. Local Ollama models keep model requests on your hardware, while hosted models receive the material needed for each request directly. Kady also works with OpenRouter, your own API keys and supported subscriptions, including ChatGPT, Claude and GitHub Copilot. K-Dense Web is a separate paid, hosted research agent.
Its scientific skills and guided workflows cover fields including bioinformatics, chemistry and clinical research. Specialist agents can handle statistical review, citation checking or literature synthesis in parallel, and you can keep several chats and projects running. You can inspect generated code, redirect the work or stop a run.
A lab notebook records hypotheses, methods, decisions and linked results, with exports and Methods drafts for papers. The workspace previews scientific files such as molecular structures, sequence alignments and medical images alongside tables and Jupyter notebooks. It also includes a LaTeX editor with PDF previews and AI edits you can accept or revert. Web search works without an additional account.
Claim this page with an email at k-dense.ai. Kady 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 Kady?Promote it
Something wrong or outdated on this page?
1.7KUpdated 1 day ago
macOS · Windows · Linux · Web#Agent Client Protocol#Agent Skills#Code execution
Open Science Desktop is an AI research workbench for researchers who want to keep their project files locally and inspect how an agent reached its results. It runs on macOS, Windows and Linux, or on a self-hosted server with browser access. Its research agents connect literature searches, experiment code and analysis to a finished manuscript.
208Updated 4 months ago
Docker · Web#Ollama integration#RAG#Semantic search
SapienAI is a self-hosted academic chatbot and writing workspace for researchers who want their sources, drafts and AI conversations in one place. It runs through Docker and connects to local models through Ollama or cloud models from OpenAI, Anthropic and Google.
136Updated 14 hours agoMIT
macOS · Windows · Linux · Web#LM Studio integration#MCP#Ollama integration
77KUpdated 3 months agoAGPL-3.0
macOS · Windows · Linux · iOS · Android · Web#MCP#Multi-user access#RAG
828Updated 9 months ago
macOS · Windows · Linux · Docker#GGUF#Human approval#MCP
ARGO is a local AI agent platform for people who want assistants that can research a topic, work with their documents and carry out tasks with several steps. It runs on Windows, macOS and Linux, including Intel and Apple Silicon Macs, or through Docker. You can create specialized assistants by describing their role in plain language.
boltai.comChat With Your Documents
macOS#Code execution#Human approval#LM Studio integration
Vellium brings character roleplay and fiction writing into a desktop AI app for macOS, Windows and Linux. It's for writers and people who want conversations with multiple characters, with control over their personas and fictional worlds. The app is open source under the MIT license and supports both Apple Silicon and Intel Macs.
AppFlowy is a self-hosted Notion alternative for teams that want project management, shared documents, and AI in an environment they control. Its self-hosted enterprise offering can run on premises, in your own cloud, or in an air-gapped environment. Self-hosted LLMs and embedding models let you keep AI processing and workspace data inside your infrastructure, with no vendor access to your instance.
BoltAI is a native Mac app for people who want local LLMs and cloud AI services in the same workspace. It runs on Intel and Apple Silicon Macs and suits coding, writing, research and document analysis. The interface uses SwiftUI and AppKit.