OpenViking
Self-evolving context database giving agents organized, searchable memory
Graph-native company brain giving agents structured, accountable context
An open-source 'Palantir for AI agents' that ingests messy company data and turns it into a knowledge graph agents can reason over. It's for teams that want a shared company brain instead of a personal second brain and need searchable, auditable context.
It builds a graph of entities and relationships from your scattered data sources, exposing that structure to agents as context they can query and reason across. Because the graph encodes relationships rather than raw text, retrieval is more structured than a plain Drive search, and the human curation you add makes results sharper.
Top 10 GitHub: AI videos, gorgeous diagrams, token savings and more
Self-evolving context database giving agents organized, searchable memory
Visual web search for agents using screenshots, not just text
Spec-driven development toolkit that makes agents agree before coding
Turn any codebase into a queryable knowledge graph
One CLI giving agents read access to the internet
Compress tool outputs, logs and RAG chunks before the LLM sees them