M
Give Moltbot superpowered memory with one command
Install Now
All Features

Memory That Works
for Both of You

Give your AI agent persistent, searchable memory that you can see, edit, and trust.

The Problem with AI Memory Today

AI agents forget everything between sessions

Every conversation starts from scratch. Context is lost.

Chat history is linear, not searchable

Good luck finding that one thing from three weeks ago.

No way to see what your AI "remembers"

It's a black box. You have no control or visibility.

You and your AI can't share knowledge

Your notes are separate from your AI's context.

The Onelist Solution

Shared memory store

Both you and your AI read and write to the same knowledge base.

AI writes via API

Agents store memories programmatically through a clean REST API.

Human reviews and organizes

You have full visibility. Edit, tag, and organize AI memories.

Both search the same knowledge

Hybrid search works for humans and AI alike.

How It Works

┌─────────────┐                 ┌─────────────┐                 ┌─────────────┐
│             │                 │             │                 │             │
│     You     │◄───────────────►│   Onelist   │◄───────────────►│     AI      │
│             │   Read/Write    │             │   Read/Write    │   Agent     │
│             │                 │             │                 │             │
└─────────────┘                 └─────────────┘                 └─────────────┘
                                      │
                                      │
                          ┌───────────┴───────────┐
                          │                       │
                          │   Same entries.       │
                          │   Same search.        │
                          │   Shared understanding│
                          │                       │
                          └───────────────────────┘
        

Intelligent Memory Hierarchy

Not all memories are equal. Onelist organizes memory into four layers for optimal retrieval and cost efficiency.

LAYER 1

Foundational

Core facts that never change. Always loaded.

~200-500 tokens

Name, timezone, critical rules

LAYER 2

Profile

Dynamic preferences. Topic-based loading.

~300-800 tokens

Communication style, patterns

LAYER 3

Episodic

Recent context. Recency + relevance.

~500-2000 tokens

Recent conversations, threads

LAYER 4

Task-Specific

Generated on-demand. Temporary.

~200-500 tokens

Synthesized answers, insights

Total context budget: ~1,200-3,800 tokens

vs. unbounded loading in naive approaches

10x Cost Reduction

Multiple representations of the same content let you optimize for cost without sacrificing quality.

Naive Approach

Load full content for every memory

100 memories x 500 tokens = 50,000 tokens

~$0.50 per request

Onelist Approach

Load summaries, fetch full only when needed

100 memories x 50 tokens = 5,000 tokens

~$0.05 per request

Use Cases

Moltbot Integration

Moltbot remembers your preferences, past conversations, and accumulated knowledge across sessions.

Research Assistant

AI accumulates research findings that you can review, annotate, and build upon.

Personal AI Context

Your AI learns your preferences, writing style, and domain knowledge over time.

Shared Project Notes

You and your AI collaborate on the same project documentation.

Simple API Integration

# Store a memory via API
curl -X POST https://api.onelist.my/v1/entries \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "entry_type": "memory",
    "title": "User prefers dark mode",
    "content": "User mentioned they always use dark mode...",
    "tags": ["preferences", "ui"],
    "metadata": {
      "source": "moltbot",
      "confidence": 0.95
    }
  }'

Full API documentation available at /docs/api

Give Your AI a Memory

Start building AI-powered applications with persistent memory today.