ashish7802

Memora AI — AI skill for Claude Code

AI community

🧠 Enterprise-grade Agent Memory & Skills Platform - Because AI shouldn't have goldfish memory.

How to install Memora AI

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ashish7802/memora-ai and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Memora AI does

🧠 Enterprise-grade Agent Memory & Skills Platform - Because AI shouldn't have goldfish memory.

Alternatives in AI

Claude Flow — An enterprise-grade AI orchestration platform that revolutionizes how developers build with AI 22.2k ★
Claude Code Configs — A comprehensive collection of production-grade Claude Code configurations, specialized agents, and automation 624 ★
Klaatcode — Open-source AI coding agent for the terminal 357 ★

README

Memora

A cognitive memory layer for AI agents and LLM applications, backed by PostgreSQL and pgvector.

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Python 3.11+](https://img.shields.io/badge/Python-3.11+-3776AB.svg?logo=python)](https://python.org/) [![FastAPI](https://img.shields.io/badge/FastAPI-0.115+-009688.svg?logo=fastapi)](https://fastapi.tiangolo.com/) [![PostgreSQL & pgvector](https://img.shields.io/badge/pgvector-HNSW-336791.svg?logo=postgresql)](https://github.com/pgvector/pgvector) [![Next.js 15](https://img.shields.io/badge/Next.js-15-black.svg?logo=next.js)](https://nextjs.org/)

1. Overview

**Memora** is an open-source long-term memory system designed for autonomous AI agents, multi-agent frameworks, and conversational applications. It acts as an external memory substrate, providing persistence across sessions, semantic vector search, and interaction logging.

Positioning & Alternatives

Memora is positioned in the AI agent memory infrastructure category alongside:

Mem0
Zep
Letta (formerly MemGPT)
Cognee

For complete architecture details, technical decisions, and specifications, see [docs/BLUEPRINT.md](docs/BLUEPRINT.md).

2. Architecture & Tech Stack

Agent / Client / SDK
       │
       ▼
 FastAPI Backend (/v1)
       │
       ├─► PostgreSQL 16 + pgvector (HNSW cosine similarity index)
       ├─► Embedding Cascade: Ollama -> Gemini -> Deterministic fallback (dev/test)
       └─► Experience Logger & Pattern Mining Pipeline

Backend: Python 3.11+, FastAPI, SQLAlchemy (asyncio), asyncpg, pgvector
Database: PostgreSQL 16/17 + pgvector extension with HNSW index (vector_cosine_ops)
Embeddings: Ollama (primary) with fallback to Gemini API or deterministic local fallback (dev/test)
Frontend / Dashboard: Next.js 15 (App Router), React 19, Tailwind CSS v4, D3.js force graphs
SDKs: Python SDK (memora-ai) a