A local-first AI assistant that remembers and grows — available via Desktop, Cloud Server, and 12 IM channels.

Model Context ProtocolAI AgentsRust

VIEW DETAILS →

AI memory for your screen. Turns your computer into a personal AI by continuously recording screen and audio to build a searchable, local AI memory system.

Docs, Tutorials & ResourcesRAGMultimodal

VIEW DETAILS →

A local-first personal AI assistant achieving full data sovereignty and privacy protection through a LangGraph ReAct agent and personal knowledge graph, with all inference running locally via Ollama by default.

Model & Inference FrameworkMultimodalModel Context Protocol

VIEW DETAILS →

An Obsidian community plugin that integrates AI coding agents (Claude Code, Codex, Gemini CLI, etc.) into the vault via the Agent Client Protocol, featuring note mentions, multi-agent sessions, terminal integration, and chat export.

Docs, Tutorials & ResourcesMulti-Agent SystemModel Context Protocol

VIEW DETAILS →

A deep context-aware agent-based novel creation system featuring Writer/Editor/Archivist collaboration, BM25 fact tracking, and token budget management, built as a local-first desktop writing workstation for 100k-word long-form and fan fiction.

Model & Inference FrameworkLarge Language ModelsRAG

VIEW DETAILS →

A fully on-device voice AI assistant for macOS Apple Silicon, integrating STT, LLM, TTS, VLM, RAG, and system control with zero cloud dependency.

Model & Inference FrameworkLarge Language ModelsMultimodal

VIEW DETAILS →

A cross-platform desktop AI productivity client that unifies access to multiple LLM providers, featuring side-by-side model comparison, knowledge base building, AI image generation, and MCP extension support.

OtherAI AgentsMultimodal

VIEW DETAILS →

A four-service collaborative AI desktop assistant framework with streaming tool calling, GRAG knowledge graph memory, Live2D avatar, and voice interaction

RAGMultimodalAI Agents

VIEW DETAILS →

A Rust-based local-first AI assistant with persistent memory, autonomous task execution, and kernel-level sandbox security, supporting multiple LLM providers and interfaces.

Model & Inference FrameworkLarge Language ModelsRAG

VIEW DETAILS →

An open-source AI coworker (YC S24) that turns work into a local-first knowledge graph and acts on it via background agents for drafting, summarizing, and planning.

Docs, Tutorials & ResourcesModel Context ProtocolAI Agents

VIEW DETAILS →