Your AI remembers
what actually matters.

A drop-in memory layer for AI chatbots. ChatSorter scores every message, extracts structured facts, and returns only the context that's relevant right now — not everything ever stored.

3
Memory layers
Free
Open beta
2
API endpoints
integration.py
# 1. Store every message
requests.post("api.chatsorter.com/process", json={
  "chat_id": user_id,
  "message": user_message
})

# 2. Retrieve relevant context
r = requests.post("api.chatsorter.com/search", json={
  "chat_id": user_id,
  "query":   user_message
})

# What comes back
# [{ "summary": "User is allergic to peanuts",
#    "source": "structured", "score": 0.94 }]

Not just storage.
Intelligent filtering.

Most memory tools store everything and dump it all into context. ChatSorter scores, filters, and returns only what's relevant right now.

Importance Scoring

Every message scored 1–10. "I love pizza" scores 4. "I'm allergic to peanuts" scores 10. Only high-signal messages get extracted permanently.

Fact Extraction

Structured key/value facts with confidence scores. "My dog is named Max" becomes { pet: "Max", confidence: 0.95 }. Not a paragraph of text.

Narrative Summaries

Every N messages compressed into a third-person summary. Your model sees 20 summaries instead of 400 raw messages. Token costs drop fast.

Relevance Retrieval

Query returns only what matters for the current message. Semantic similarity + importance weighting + recency decay — all combined into one score.

Contradiction Handling

When someone says "I moved to SF," the system updates location — not appends it. Volatile facts like health conditions are tracked separately with staleness detection.

Drop-in Integration

Two API calls. POST /process to store a message. POST /search to retrieve relevant context. Works with any Python backend, any LLM, any stack.

Three layers.
One brain.

Most tools have one layer — a database. ChatSorter has three, each doing a specific job.

L1

Short-term Buffer

Last N messages in a rolling window. No LLM involved. Zero latency. Keeps the model aware of recent context without any processing overhead.

L2

Narrative Summaries

Every batch of N messages compressed into a single third-person summary via local LLM inference. Stored with importance scores and timestamps. Decays over time.

L3

Structured Facts

High-signal messages parsed into typed key/value facts — name, job, allergies, pets, preferences. Confidence-scored. Volatile facts (health, lawsuits) tracked separately with staleness detection.

Pick your tool.

ChatSorter is built specifically for chatbot memory — not general-purpose vector storage.

Feature Mem0 Supermemory ChatSorter
Confidence scores on facts
Importance-gated extraction
Volatile fact tracking
Bring your own vector DB
Local inference option
Free tier Limited 1M tokens/mo Full beta access
Target use case Enterprise Full platform Chatbot memory engine

Get your API key in 60 seconds.

Free beta access. No credit card. Two endpoints away from working memory for your chatbot.

Start building →