Explore 2387 PostgreSQL extensions from PGEXT, maintained by Pigsty.
73 extensions found. Clear filters
| Name | Version | Description | Category | License | Language | PG Version | Stars |
|---|---|---|---|---|---|---|---|
| vector | 0.8.6 | vector data type and ivfflat and hnsw access methods | RAG | PostgreSQL | C | 14–18 | 23k |
| pg_deeplake | 1.0 | Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training. | RAG | Apache-2.0 | C++ | — | 9.2k |
| ai | 0.11.3-dev | Helper functions for AI workflows in PostgreSQL | RAG | PostgreSQL | Python | 16–18 | 5.8k |
| ruvector | 0.3.0 | SIMD-accelerated vector type and indexes with graph, solver, TDA, local embedding, and AI SQL functions. | RAG | MIT | Rust | 14–17 | 4.5k |
| vectorscale | 0.9.0 | Advanced indexing for vector data with DiskANN | RAG | PostgreSQL | Rust | 14–18 | 3.1k |
| vectors | 0.4.0 | Vector database plugin for PostgreSQL, written in Rust, specifically designed for LLM | RAG | Apache-2.0 | Rust | 14–17 | 2.2k |
| gp_sparse_vector | 1.0.1 | Sparse vector implementation for Greenplum-family databases. | RAG | Apache-2.0 | C | — | 1.4k |
| vectorize | 0.27.1 | The simplest way to do vector search on Postgres | RAG | PostgreSQL | Rust | 14–18 | 831 |
| embedding | 0.3.6 | HNSW vector similarity search extension for PostgreSQL real[] embeddings. | RAG | Apache-2.0 | C | 12–16 | 579 |
| pg_gpt | 0.0.0 | Experimental extension that brings OpenAI API to your PostgreSQL to run queries in human language. | RAG | Apache-2.0 | Rust | — | 458 |
| pgcontext | 0.3.0 | Vector, filter-aware HNSW, and hybrid retrieval over authoritative PostgreSQL tables. | RAG | Apache-2.0 | Rust | 17–18 | 251 |
| pgcontext_pgvector | 0.2.0 | Optional pgvector compatibility bridge for pgcontext HNSW indexes. | RAG | Apache-2.0 | Rust | 17 | 251 |
| pgclaw | 0.1.0 | Store LLM or OpenClaw agents as PostgreSQL values and process watched rows with a background worker | RAG | MIT | Rust | 14–17 | 210 |
| jev | 0.2.0 | Natural-language row filtering, ranking and classification through TypeSafe | RAG | PostgreSQL | Python | 14–17 | 195 |
| kmeans | 1.1.0 | K-means clustering window function for PostgreSQL | RAG | PostgreSQL | C | 10–18 | 106 |
| rag_bge_small_en_v15 | 0.0.0 | rag_bge_small_en_v15: local bge-small-en-v1.5 embeddings in PostgreSQL | RAG | Apache-2.0 | Rust | 13–18 | 101 |
| pgdl | 1.3.0 | PostgreSQL extension for deep learning model inference and vector storage inside the database. | RAG | — | C++ | 12 | 63 |
| pg_onnx | 1.2.1 | ONNX Runtime integrated with PostgreSQL. Perform ML inference with data in your database. | RAG | MIT | C++ | 13–18 | 62 |
| pg_tiktoken | 0.0.1 | tiktoken tokenizer for use with OpenAI models in postgres | RAG | Apache-2.0 | Rust | 14–18 | 52 |
| neurondb | 4.0.0-devel | AI database extension for vector search, ML inference, hybrid search, and RAG in PostgreSQL. | RAG | Proprietary | C | 16–18 | 50 |
| pase | 0.0.1 | PostgreSQL ultra-high dimensional approximate nearest neighbor search extension. | RAG | — | C | — | 50 |
| pgpu | 2.1.0 | GPU acceleration for PostgreSQL vector index builds using NVIDIA CUDA/cuVS and VectorChord. | RAG | AGPL-3.0 | Rust | 14–18 | 42 |
| pgedge_vectorizer | 1.1 | Asynchronous text chunking and embedding generation for PostgreSQL using background workers and pgvector. | RAG | PostgreSQL | C | 14–18 | 36 |
| pgafis | 1.2 | AFIS Support for PostgreSQL | RAG | GPL-2.0 | C | — | 28 |
| pg_ai | 0.0.1 | PostgreSQL extension that provides (RAG capable)SQL functions to interpret data using multi modal LLMs and vectors. | RAG | Apache-2.0 | C | — | 25 |
| pgpyml | 0.3.1 | Run scikit-learn machine-learning models inside PostgreSQL through PL/Python functions and triggers. | RAG | PostgreSQL | Python | — | 18 |
| pg4ml | 2.0 | Machine learning framework for PostgreSQL | RAG | AGPL-3.0 | C | 14–18 | 13 |
| avocado | 2.2.0 | AvocadoDB PostgreSQL extension for deterministic context compilation for AI agents. | RAG | MIT | Rust | 16 | 12 |
| llama_embed | 0.1.0 | llama.cpp embedding extension for dense and multivector search | RAG | PostgreSQL | C | — | 9 |
| pg_colbert_llama | 0.1.0 | ColBERT embedding companion extension for pgturbohybrid | RAG | PostgreSQL | C | — | 9 |
| pgturbohybrid | 0.2.0 | hybrid vector and BM25 search for PostgreSQL on top of pgvector | RAG | PostgreSQL | C | — | 9 |
| pgturbohybrid_experimental | 0.2.0 | experimental sparse and multivector features for pgturbohybrid | RAG | PostgreSQL | C | — | 9 |
| maludb_core | 0.104.0 | A memory DBMS for long-term institutional memory, human-AI knowledge sharing, and contextual recall. PostgreSQL 17 extension. | RAG | — | C | — | 8 |
| pg_semantic_cache | 0.1.0-beta4 | Caches query results and retrieves semantically similar results using pgvector embeddings and configurable eviction policies. | RAG | PostgreSQL | C | 14–18 | 8 |
| sveddy | 0.1.0 | A PostgreSQL extension for collaborative filtering using low-rank matrix approximation techniques. | RAG | MIT | C | — | 8 |
| pg_cuvs | 0.5.0 | ⚡ Blazing-fast GPU vector search for PostgreSQL powered by NVIDIA cuVS. | RAG | PostgreSQL | C | — | 7 |
| pgmnemo | 0.20.0 | Single-plan multimodal agent memory for PostgreSQL | RAG | Apache-2.0 | SQL | 17–18 | 6 |
| rikai | 0.1 | rikai ML extensions | RAG | Apache-2.0 | SQL | — | 5 |
| pg_ask | 1.0 | Postgres Extension which uses AI to create SQL from Natural language. | RAG | MIT | C++ | 16–18 | 4 |
| ecaz | 0.1.1 | Rust PostgreSQL extension for high-performance vector storage with broad quantization and index support. | RAG | MIT | Rust | — | 3 |
| mtree | 0.0.1 | Metric-space index access method derived from PostgreSQL GiST | RAG | — | C | — | 3 |
| otlet | 0.1.0 | Local LLM inference inside PostgreSQL with background workers, queued tasks, receipts, and semantic data operations. | RAG | — | Rust | — | 3 |
| pg_tiktoken_c | 1.1 | Fast tiktoken BPE tokenizer for PostgreSQL implemented in C | RAG | Apache-2.0 | C | 14–18 | 3 |
| pg_knowledge_graph | 0.1.0 | Knowledge graph extension for PostgreSQL with graph algorithms and pgvector integration. | RAG | MIT | Rust | 16–18 | 2 |
| pgtoken | 1.0 | PostgreSQL extension for compact, codebook-compressed LLM token ID storage. Encode once, retrieve forever. O(1) token count without decoding. | RAG | MIT | Python | — | 2 |
| postllm | 0.1.0 | postllm: PostgreSQL-native access to OpenAI-compatible and local LLM runtimes | RAG | MIT | Rust | 13–18 | 2 |
| svs | 0.1.0 | SVS Vamana approximate-nearest-neighbor index with LeanVec and LVQ compression for pgvector. | RAG | PostgreSQL | C | — | 2 |
| ai_toolkit | 1.0 | AI-powered query generation and explanation tools for PostgreSQL. | RAG | — | C++ | 18 | 1 |
| malwaredb_pg | 0.0.1-dev | PostgreSQL extension for MalwareDB similarity functions: SSDeep, LZJD, and TLSH | RAG | Apache-2.0 | Rust | 13–18 | 1 |
| pg_fela | 1.0.0 | The holy grail of AutoML for PG - self classifying and regressing tabular data! | RAG | — | Rust | — | 1 |