Store LLM or OpenClaw agents as PostgreSQL values and process watched rows with a background worker
pgext.cloud · Source code · Documentation · License text · Control file
| Package | pgclaw |
|---|---|
| Version | 0.1.0 |
| PostgreSQL versions | 14 · 15 · 16 · 17 |
| Repository | Unspecified |
| Extension type | Preloaded |
| Project status | Active |
| Requires CREATE EXTENSION | Yes |
| Requires preload | Yes |
| Trusted | No |
| Relocatable | No |
| Shared libraries | pgclaw |
| Schema | claw |
| Stars | 210 |
| Latest commit | 2026-02-12 |
| Catalogue updated | 2026-08-30 |
| pg_deeplake | Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training. |
| pgtoken | PostgreSQL extension for compact, codebook-compressed LLM token ID storage. Encode once, retrieve forever. O(1) token count without decoding. |
| pgmnemo | Single-plan multimodal agent memory for PostgreSQL |
| lantern_extras | Convenience functions for working with vector embeddings |
| ai_toolkit | AI-powered query generation and explanation tools for PostgreSQL. |
| ollama | Ollama client for PostgreSQL |
| tencentdb_ai | TencentDB extension for calling large-model APIs and building in-database RAG workflows. |
| ai | Helper functions for AI workflows in PostgreSQL |
| avocado | AvocadoDB PostgreSQL extension for deterministic context compilation for AI agents. |
| vectorize | The simplest way to do vector search on Postgres |