Percolation-Labs/percolate
An agentic orchestrator *inside* a relational-vector-graph/key-value database!
Percolate helps software developers build advanced AI applications directly within a Postgres database. It takes various AI models and tools as input, allowing developers to orchestrate complex "agentic" workflows, where AI agents can reason, use tools, and interact with data. The output is a more streamlined application tier, where the core AI logic resides efficiently within the database. It is designed for software architects and AI developers who need to manage and scale agent-based systems.
Use this if you are a software developer or architect looking to integrate AI agents and their workflows deeply into your database layer, rather than managing them separately in your application code.
Not ideal if you are looking for a simple, off-the-shelf AI chatbot or a tool that doesn't require direct database interaction for AI orchestration.
Stars
61
Forks
2
Language
Python
License
MIT
Category
Last pushed
Oct 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/Percolation-Labs/percolate"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...