pg_vectorsearch is a PostgreSQL extension for high-performance approximate nearest neighbor search. It adds a PRISM index built for 100M+ vectors with hierarchical routing, RaBitQ quantization with theoretical error bounds, and SIMD-optimized distance computation, and it can index existing pgvector columns as-is.
Be the first to rate pg_vectorsearch. Your feedback helps other users decide.
The PRISM index is IVF-style with hierarchical routing and is built for 100M+ vectors.
Index existing vector and halfvec columns as-is instead of migrating data.
Inserts, updates and deletes are supported, with posting-list splits through prism_rebalance.
Similar tools in the same category — compare side-by-side
Bomfather is an open source runtime security agent you deploy on your Linux servers to protect the r...
Enki LLM is a pure Rust Transformer inference engine of about 2,000 lines that runs Llama-3.2 1B at ...
Shadowclone keeps your engineering preferences the same in every coding agent. It maintains one set ...
Guides and comparisons about code tools
Eleven Show HN launches for the unglamorous middle: vector search, Postgres indexes, waste audits, budget breakers, routing, inference fleets and optimizers.
Four Show HN launches that verify agent work rather than trusting its summary: an execution record, an AI-app scanner, a local guardrail and adversarial tests.
Five Show HN launches that keep work on your machine: a ternary model runner, a distillation proxy, a PostgreSQL client, CAD over MCP and a local ETL builder.
Four Show HN launches around voice and ops: voice planning for agents, a live game coach, CI for AI phone agents and a self-hosted MCP platform on Kubernetes.
Ten Show HN launches that answer the same question differently: where does what an agent learned live, who owns it, and who can read it back?
