hindsight
Agent memory that learns instead of just recalling
Self-evolving context database giving agents organized, searchable memory
A context and memory layer for AI agents that stores everything an agent knows in an organized, searchable file-based structure. It's for developers frustrated that their coding agent forgets context between sessions or fails to understand a new project.
It exposes a virtual file-system style drive that Claude, Codex and other coding agents can read and write directly, so memory, knowledge RAG and usable skills live as files the model already knows how to manipulate. You point the agent at the structured store and it retrieves and updates context instead of losing it between sessions.
Top 10 GitHub: AI videos, gorgeous diagrams, token savings and more
Agent memory that learns instead of just recalling
Graph-native company brain giving agents structured, accountable context
Visual web search for agents using screenshots, not just text
Fully local voice cloning, dubbing and transcription studio
Compress tool outputs, logs and RAG chunks before the LLM sees them
Self-hosted net-worth tracker connected to thousands of banks