Works withClaudeGPT-4Geminiand more

Memory for AI agents that never silently loses or overwrites a fact.

The reliable memory layer for CrewAI, LangGraph, LlamaIndex and any agent. Every change is archived with full lineage — so your agent's memory never lies to it. (Works across Claude, GPT and Gemini too.)

CLS++ Memory Explorer
1{
2 "session_id": "cls_a1b2c3d4e5",
3 "model": "claude-3-opus",
4 "messages": [
5 {
6 "role": "user",
7 "content": "Help me build a React app"
8 },
9 {
10 "role": "assistant",
11 "content": "I'd be happy to help! Let's start with...",
12 "context": {
13 "topic": "React development",
14 "expertise_level": "intermediate",
15 "preferences": ["TypeScript", "Tailwind"]
16 }
17 }
18 ],
19 "memory": {
20 "user_preferences": {
21 "code_style": "functional",
22 "framework": "Next.js",
23 "testing": "vitest"
24 },
25 "conversation_summary": "Building a React dashboard app",
26 "key_decisions": [
27 "Using TypeScript for type safety",
28 "Tailwind CSS for styling",
29 "Server components where possible"
30 ]
31 }
32}
JSONUTF-8
Ln 32CLS++ v1.0
TERMINAL$cls chat -m claude "What do you know about me?"● Connected

Access Status

Open Access
Instant Access Available

Sign up now and get immediate access to CLS++ Memory API — open worldwide.

0
Active now
Try It Live - No Signup Required

Experience Cross-LLM Memory

Chat with one LLM, then switch to another. Watch your context transfer automatically. Tell me your name, what you're working on, and then switch LLMs!

Start a conversation

Try: "Hi, my name is Alex and I'm building a SaaS app" then switch to another LLM!

Stored Memories

No memories yet

Start chatting to build context

Memories sync across all LLMs
Switch LLMs to see it work!

Memory you can trust

Built so your agent's memory never silently loses or wrongly overwrites a fact — and proves what it did to each one.

Belief revision with lineage

A contradicting fact archives the old one with full lineage and version — never a silent overwrite or delete. Your agent's memory has a provable history.

No silent data loss

Writes persist from the engine's own index; a failed embedder degrades ranking, never loses a fact. Run the proof — it's reproducible.

Drop-in for your agent

Three lines to integrate. Native adapters for CrewAI, LangGraph, LlamaIndex, AutoGen and MCP. TypeScript and Python SDKs.

Durable by design

Writes are fsync-acknowledged to a write-ahead log, with recovery tested against process death and torn-tail records. An accepted write is a kept write.

Works across models

Store a memory once and recall it in Claude, GPT or Gemini — switch providers without re-introducing context.

Yours to control

Encrypted in transit; delete any memory on request (GDPR right-to-be-forgotten). Your data stays yours.

Three lines of code. Memory you can trust.

Drop CLS++ into your agent in minutes. It stores, recalls, and revises memory — and proves what it did to each fact.

  • Archives every superseded fact with lineage — never a silent overwrite
  • Survives embedder failures — a dead embedder loses nothing
  • Drop-in for CrewAI, LangGraph, LlamaIndex, AutoGen and MCP
  • TypeScript and Python SDKs
Learn How It Works
Quick Start
npm install clsplusplus

import { Brain } from 'clsplusplus';

const brain = new Brain('alice', { apiKey: 'cls_live_...' });

// Teach it anything
await brain.learn('I prefer Python over JavaScript');

// Recall — semantic, across any LLM
const facts = await brain.ask('What languages do I like?');

Ready for memory your agent can trust?

Start with 50 free API calls per day. No credit card required. Upgrade anytime as you scale.