v0.10.0 · Cloud Edition · MIT License

Feather DB Docs.

The Living Context Engine — context infrastructure for AI agents. Embedded, open source, sub-millisecond. Start with a pip install and ship.

install

$ pip install feather-db

# or with pnpm for the JS wrapper: pnpm add feather-db

# or the Rust CLI: curl -sSf https://get.feather.store | sh

Core capabilities

Stickiness × decay × importance. Memory that ages like you do.

Typed edges, BFS traversal, bidirectional index. Knowledge that connects.

HNSW with AVX2/AVX512 kernels. <1ms at 100K vectors, C++ core.

Reciprocal Rank Fusion of dense + sparse — same RRF as Qdrant, Weaviate, Elastic.

Brand-aligned dashboard at /admin/ — records, search, schema, hierarchy, graph, context, console. New in v0.10.

Six providers (OpenAI, Azure, Gemini, Voyage, Cohere, Ollama). One-call ingest_text — embed + store. New in v0.10.

Namespace, entity, attribute, importance — all inside the core engine.

Install the Python package, Rust CLI, or compile from source.

Your first Feather DB in under 5 minutes. Add, link, query.

The full surface: DB.open, db.add, db.link, context_chain, filters.

Open an issue on GitHub, join the Discord, or book 30 min with the founder.