PPraise James·Oct 11How Regenesis built MedShift's self-healing loop with VectorAI DBThis article was originally published on the Actian blog. The build was first submitted to the Self-Evolving Agents Hack. A self-healing agent that repairs failures without remembering them has a str8 min read·actiandev.hashnode.dev
PPraise James·Oct 11Add persistent memory to a Pydantic AI agent with VectorAI DBThis article was originally published on the Actian blog. A Pydantic AI run starts with only the context you pass in, and that context disappears when the process exits. An agent that has learned a us10 min read·actiandev.hashnode.dev
PPraise James·Sep 2How to self-host mem0 with a local vector storeIf you've used mem0 and discovered it calls OpenAI by default, the fix is three configuration values. mem0's Memory() class is cloud-by-default. It calls OpenAI for fact extraction, calls OpenAI again12 min read·actiandev.hashnode.dev
PPraise James·Aug 31Replace CrewAI Memory in Production with VectorAI DBIf you've deployed a CrewAI application with memory=True and you're seeing "database is locked" errors under concurrent load, lost memory after a container restart, or memory bleeding between users in13 min read·actiandev.hashnode.dev
PPraise James·Jul 27Build a local RAG pipeline on declassified UFO files with VectorAI DB and OllamaBuild a local RAG pipeline with Actian VectorAI DB, Ollama, and LlamaIndex to search and analyze declassified UFO documents privately.11 min read·actiandev.hashnode.dev
PPraise James·Jul 27Build a Local Document Intelligence Agent with LlamaIndex and VectorAI DBLearn how to build a local document intelligence agent with LlamaIndex and VectorAI DB for private, fast document search and AI-powered retrieval.15 min read·actiandev.hashnode.dev
PPraise James·Jul 15How to Build Persistent Agent Memory Across SessionsYour agent can follow a rule perfectly at the start of a conversation and still miss it later. Maybe the rule is simple: don't share user contact details, don't book meetings outside business hours, o14 min read·actiandev.hashnode.dev
PPraise James·Jul 15Running Gemma 2B on Edge Hardware with Actian VectorAI DBToday, running a powerful language model entirely on edge hardware is no longer the hard part. The problem is making it useful once it is there. A developer can deploy Gemma 2B on NVIDIA Jetson Orin N16 min read·actiandev.hashnode.dev
PPraise James·Jul 15Build an OpenClaw Memory Plugin with Actian VectorAI DBContext compaction is a common failure point for most OpenClaw memory systems. When the context window fills, OpenClaw compacts the session to make room for new messages. Any memory operations that we14 min read·actiandev.hashnode.dev