nikita-rulenko/Helixir
First causal agentic AI memory
This project gives AI agents a long-term memory that understands connections between facts, rather than just recalling isolated pieces of text. It takes natural language input from an AI agent's conversations, extracts specific facts, preferences, and goals, and stores them in a structured way. This helps AI agents like those used in AI assistants or automated customer service remember past interactions, individual user preferences, and even their own learning over time, making conversations more coherent and personalized.
Use this if you need an AI agent to remember past interactions, preferences, and decisions across different conversations, and perform causal reasoning based on this stored knowledge.
Not ideal if your AI agent only needs to recall information from the current conversation or you only require simple keyword or semantic search without understanding the relationships between pieces of information.
Stars
74
Forks
14
Language
Rust
License
MIT
Category
Last pushed
Feb 19, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/nikita-rulenko/Helixir"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
statespace-tech/statespace
Interactive web apps for AI agents.
mandubian/ccos
CCOS Causal Cognitive Operating System + RTFS (Reason the Fucking Spec) core language
LashSesh/apollyon
Post-symbolic cognition engine that models the Metatron Cube geometry and orchestrates a layered...
makkenzo/codename-symbiont
Codename: Symbiont - Building an evolving AI with a Rust-based microservice stack.