DejaVu

Curiosity is the context graph for industrial AI. It connects the knowledge spread across an organization's files, messages, wikis, ticketing systems and databases into a single graph that teams can search, explore and put to work with AI. Most search tools treat each document in isolation. Curiosity keeps the relationships between records intact, so a part, a supplier, a ticket and a field report stay linked. Search returns answers with that context attached, and every answer carries a clear trail back to the source. It holds data in memory, so results return as you type across structured and unstructured sources, and connects to systems such as network drives, SharePoint, Jira and ServiceNow without moving your data. Curiosity runs on your own infrastructure for data privacy, respects your existing permissions and combines your knowledge graph with the AI models you choose. Built for industrial enterprises that need trustworthy answers from complex, connected data.

Osaurus is a native AI harness for macOS that lets users run open models entirely on their Mac, connect cloud models when greater capability is needed, and carry shared memory across them. Built in Swift for Apple Silicon, it works fully offline with local models through Ollama, MLX, or LM Studio, keeping conversations, code, files, settings, agents, skills, and provider keys on the device unless the user explicitly chooses a cloud provider. A system-wide chat overlay provides quick access from any app, while separate agents can be created for coding, research, file organization, and other jobs, each with its own prompt, history, and memory. Osaurus distills past conversations into relevant facts, loads packaged skills when tasks require them, and gives agents scoped access to working folders, file search, Git, and other tools. Agents can run code in an isolated sandbox, delegate work to subagents, operate on schedules, respond to folder changes, use voice input, and generate images.