The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
A local-first memory layer for AI agents — turns the files on your machine into bounded, verifiable memory any assistant can query over MCP. On-device, no cloud.
Git-native why next to the code, with a pin check that proves it still matches. Agents retrieve stored why before they edit; hook and CI attest the attachment. Experimental 0.0.2.
Hybrid semantic and keyword search over Oh My Pi session transcripts
Spatial Memory replaces standard cosine-similarity RAG with physics-inspired 8D manifold where memories and beliefs have: Mass — derived from confidence and affective encoding ; Temperature — recency heat that cools over time (Lorentzian decay); and Gravity — `F = T × m / d²` — hot, massive, nearby concepts pull attention
MCP-powered inventory management system
Shared memory for AI coding agents. Preserve context across sessions and enable seamless continuity between different AI agent tools.
Hypermemory marketplace and plugins for OpenAI Codex desktop and Codex CLI adding long-term persistent memory across all AI tools.
Antes do Lançamento previsto para o final de Maio de 2026 , reuni diversas conversas com outras IAS para ver o que elas respondiam e depois pedia para comparar de maneira imparcial com o texto do Agente ARIEL , irei colocar algumas aqui
public releases, GitHub Pages site, public docs, installer scripts
Giving an AI agent a sleep cycle — a 9-stage pipeline that consolidates noisy daily observations into durable, evidence-backed beliefs and lessons instead of piling up logs forever.
OpenClaw skill for HyperMemory integration
To associate your repository with the agentic-memory-system topic, visit your repo's landing page and select "manage topics."