Open-source skills for designing and reviewing software with AI agents

Context retrieval for DeepSeek Harness: ranks docs, code and media by relevance into a sidebar Context Pack. Lexical and fully local by default. Hybrid is off until you configure a provider; it sends your query and file titles/summaries, not bodies.

A living personal wiki. Wenlan turns your documents, notes, and AI chats into pages with links to their sources, and updates them as sources change without overwriting your edits. Claude Code, Codex and other AI tools can build on it.

Long-term memory for you and your AIs: search memories, read the profile, add facts and documents.

Shared project memory for people and AI agents: workspaces, documents, ERD, diagrams and boards.

Keeps large tool outputs out of an agent's context window by spilling them to disk and handing back a short pointer instead. Lets the agent pull only what it needs — exact numbered line ranges read directly from disk, or verbatim relevant lines returned by a small model answering a question about the stored output, plus tools to open, list, and close documents.

Enables full read/write automation of AFFiNE workspaces, documents, databases, journals, and comments through MCP tools over stdio or HTTP, supporting self-hosted and AFFiNE Cloud instances as well as multi-tenant deployments where each session supplies its own domain and credentials.

Private memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.