Free Beta — 95% recall accuracy

Your AI remembers
what actually matters.

ChatSorter is a drop-in memory layer for AI chatbots. It scores every message, extracts facts, and returns only the relevant context — not everything you've ever stored.

95%
Recall accuracy
1000+
Msgs tested
2 calls
To integrate

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 5 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

Tentative/confirmed fact buckets. When someone says "I moved to SF," the system resolves the conflict and updates location — not appends it.

🔌

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.

Three layers.
One brain.

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

L1

Short-term Buffer

Last 5 messages kept 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 5 messages compressed into a single third-person summary via local inference. Stored with importance scores and timestamps. Decays over time.

L3

Structured Fact Extraction

High-signal messages parsed into typed key/value facts — name, job, allergies, pets, preferences. Stored with confidence scores. Never decays. Always surfaced first in retrieval.

Pick your tool.

Feature Mem0 Supermemory ChatSorter
Confidence scores on facts
Importance-gated extraction
Tentative/confirmed fact buckets
Bring your own RAG/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 curl commands away from working memory for your chatbot.

Start building →