Memory & Knowledge Agent Skills for Windsurf (legacy)

Mem0 memory layer integration for AI agents.

Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search

SOTA semantic search — hybrid (sparse+dense), Graph RAG multi-hop, MMR diversity reranking, recency weighting

Design short-term, long-term, and graph-based memory architectures.

Guide for creating templates for the Obsidian Web Clipper.

Manage RVF (Ruflo Vector Format) files for portable agent memory and cross-platform transfer

Persist and restore agent sessions across conversations with state snapshots

Pick up where you left off from a previous session — use after context resets, compaction, or new conversations

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections.

Work like Manus: Use persistent markdown files as your \"working memory on disk.\

Persist user decisions and project constraints to mdbase across sessions.

Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements.

Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents, storing entities…

Load relevant .agents context.

Portable OKF knowledge bundle for coding-agent memory and LLM wikis — start a wiki, ingest a source, query project knowledge with…

Semantic search over agent memory files — find conceptually related memory blocks, discover forgotten reference files, and check what you…

Manage durable working-session memory for coding agents, preserving and recovering context across disconnects, restarts, handoffs and…

This skill should be used when the user asks to start a new research project, import an existing code-plus-Markdown repository into…