vektori-ai/vektori
Memory that remembers the story not just the facts. Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.
This project helps AI agents remember full conversations and context, not just isolated facts. It takes in conversational turns (like chat messages) and allows the agent to recall specific facts, behavioral patterns, or even the entire exchange. This is ideal for developers building intelligent agents that need a deeper, more nuanced understanding of past interactions.
Available on PyPI.
Use this if you are developing AI agents and need a memory system that captures the 'why' and 'how' of past interactions, beyond simple factual recall.
Not ideal if you only need to store and retrieve simple, isolated facts without needing to understand the conversational flow or discover behavioral patterns.
Stars
64
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 03, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/vektori-ai/vektori"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
superlinked/sie
Superlinked Inference Engine is an Open-source inference server and production cluster for...
unohee/OpenSwarm
OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control,...
BlackyDrum/chromadb-ui
Modern ChromaDB web UI for browsing collections, inspecting records, running queries, and...
qdrant/skills
Agent skills for Qdrant vector search: scaling, performance optimization, search quality,...
DopamineDriven/slipstream
byok multi-provider medium supporting OpenAI, Anthropic, xAI, Google, Meta, & Mistral models...