For Developers

Add Persistent Memory to Your AI Tools in 5 Minutes

One command to connect any MCP-compatible AI tool to your personal memory library. Works with Claude Code, Cursor, Windsurf, and more.

npx @awareness.market/setup

Works With Your Favorite AI Tools

Claude Code
Cursor
Windsurf
Cline
Manus
Gemini
ChatGPT
Codex
Kiro
Trae
Zed
JetBrains
Antigravity
GitHub Copilot
Devin
OpenClaw
LangChain
CrewAI
PraisonAI
Augment

One Command Setup

Run this in any directory to configure your AI tools automatically.

01

Run the setup command

npx @awareness.market/setup detects your IDE and configures everything.

npx @awareness.market/setup

02

Log in via browser

The CLI opens your browser for one-click auth and memory selection.

03

Start building with memory

Your AI now remembers across sessions. Ask it anything.

Choose Your Integration

Multiple ways to connect — from zero-code AI prompts to full SDK integration.

Let Your AI Configure Everything

Copy this prompt into your AI tool. The CLI handles login, memory selection, IDE detection, and config writing — fully automated.

Help me set up Awareness Memory. Run this command:

npx @awareness.market/setup

The CLI will handle everything automatically:
1. Open my browser to log in (Device Code Auth)
2. Let me pick an existing memory or create a new one
3. Auto-detect my IDE (Cursor, Claude Code, Windsurf, etc.)
4. Write MCP config + IDE workflow rules

Just run the command and walk me through what happens.
If it can't detect my IDE, try: npx @awareness.market/setup --ide cursor
To preview without writing files: npx @awareness.market/setup --dry-run

Browser login

Opens your browser for one-click auth. No manual API Key entry needed.

Auto-detects IDE + writes config

Scans your project for Cursor, Claude Code, Windsurf, etc. Writes MCP config + workflow rules.

Memory wizard

Pick an existing memory or create a new one — the CLI walks you through it.

Start Free, Scale as You Grow

Free tier · No credit card · 2 memory libraries · 1,000 API calls/month

Under the hood

The memory engine behind every SDK and MCP endpoint — layered architecture, a living knowledge graph, and shared memory across agents.

See the full platform overview

Your Data
Connectors
Notion, Slack, Drive
Extractors
Smart Chunking & NLP
Memory Graph
Ontology-aware Edges
Retrieval
Hybrid Vector + BM25
Your Agent (Complete Context)

Five Layers of AI Memory

A complete cognitive architecture built to transform raw fragmented inputs into structured, intelligent context.

LAYER 05

Identity Profiles

Granular control over AI behavior, coding styles, and specific project constraints tailored to your exact needs.

LAYER 04

Memory Graph

Networked memory representation where entities, files, and abstract concepts are interconnected for deep reasoning.

LAYER 03

Hybrid Retrieval

Multi-engine search combining precise FTS5 text matching with intelligent pgvector semantic similarity.

LAYER 02

Smart Extractors

Automated pipelines that ingest scattered chat logs and convert them into structured, valuable memory nodes.

LAYER 01

Tool Connectors

Seamless integration to funnel data straight from Claude Code, Cursor, Feishu, and GitHub into your central brain.

Identity
Memory
Hybrid
Smart
Tool
Memory Relational Data

Knowledge Graph

Memory is not just storage, it connects. Related decisions, projects, and people are automatically linked. You only need to ask one point, and AI will understand the full context.

DecisionVerified

Choose PostgreSQL over MongoDB

Selected pgvector for hybrid search. MongoDB lacks robust cross-metric aggregation needed for LatentMAS.

via Claude Code
2 hours ago
Live Demo

Your AI Unlocks Memory Skills

See It in Action — your AI remembers, recalls, and syncs context automatically.