Open Protocol — v1.0.0 Now Available

Your agent's memory,
anywhere it runs.

AM-01 is the universal memory protocol for AI agents. Store, retrieve, and share long-term memory across LangChain, CrewAI, AutoGen — without framework lock-in.

3 lines to connect any LangChain agent
from am01_langchain import AM01Memory

memory = AM01Memory(
    api_key="am01_your_key",
    namespace="support-team",
    agent_id="agent-v3"
)

# Done — memory is now persistent across all agent sessions
Your Agents
LangChain CrewAI AutoGen Custom
AM-01 Protocol
Episodic Semantic Procedural Identity
Any Framework
LangChain CrewAI AutoGen Custom
Open Standard
MIT Licensed
HIPAA / GDPR / SOC2
<50ms retrieval

Framework lock-in is destroying
your agent's memory.

Every agent framework stores memory differently. Switch from LangChain to CrewAI? Your agent forgets everything. That's not a bug — it's vendor lock-in.

Memory Silos

LangChain memories can't talk to CrewAI. Each framework is an island — your agent's context doesn't travel with you.

Memory Lost on Migration

Switching frameworks wipes accumulated agent knowledge. Years of learned patterns, gone in a deployment.

No Compliance Layer

Healthcare, finance, legal — none of the frameworks have HIPAA, GDPR, or SOC2 memory modes built in.

No Cross-Agent Sharing

Multiple agents in a team can't share context. Every agent starts from scratch — even when teammates already know.

Before AM-01
Framework: LangChain
Memory: 3,847 interactions stored
Customer preferences learned: 234
Strategy patterns discovered: 18
# Migration attempt...
Framework: CrewAI
Memory: 0
Customer preferences: 0
Everything lost.
After AM-01
Framework: LangChain
Memory: 3,847 interactions stored
Customer preferences: 234
Strategy patterns: 18
# Migration attempt...
Framework: CrewAI
Memory: 3,847 — intact ✓
Customer preferences: 234 — intact ✓
Everything preserved. ✓

Four memory types. Every agent use case.

AM-01 defines exactly four canonical memory types — enough to capture all agent memory needs, without over-engineering.

Episodic

Episode Memory

Records of specific past interactions and outcomes. What happened, when, and what was the result.

Example
"User alice@co.com asked about
enterprise pricing. Escalated to
sales. Demo scheduled April 20."
When: After each agent turn
Semantic

Semantic Memory

Learned facts, concepts, and patterns extracted from interactions. What the agent knows.

Example
"Customer prefers detailed
explanations with code examples
over brief summaries."
When: On insight extraction
Procedural

Procedural Memory

Behaviors and strategies that worked. How the agent should act in a given situation.

Example
"When billing query: check tier
first, then provide plan-specific
pricing. Solved 89% of queries."
When: On strategy success
Identity

Identity Memory

Agent persona, communication style, and learned preferences. Who the agent is.

Example
"Support agent. Analytical,
helpful. Always provides code
examples. Traits: precise."
When: On initialization
AM-01 Schema — am01-spec-v1.json View Full Spec
{
  "$schema": "https://json-schema.org/draft/07",
  "title": "AM-01: AI Agent Memory Protocol",
  "version": "1.0.0",
  "definitions": {
    "MemoryType": {
      "enum": ["episodic", "semantic",
                "procedural", "identity"],
      "description": "Canonical AM-01 memory types"
    },
    "Memory": {
      "type": "object",
      "required": ["id", "type", "content",
                 "agent_id", "namespace",
                 "content_hash", "created_at"],
      "properties": {
        "id":         { "type": "string", "format": "uuid" },
        "type":        { "$ref": "#/definitions/MemoryType" },
        "content":     { "type": "string", "maxLength": 65536 },
        "metadata":     { "$ref": "#/definitions/MemoryMetadata" },
        "content_hash":{ "pattern": "^[a-f0-9]{64}$" },
        "ttl":         { "type": ["integer", "null"] }
      }
    }
  }
}

Everything your agent memory stack needs.

A complete memory infrastructure layer — not just storage, but intelligence.

4 Memory Types

Episodic, semantic, procedural, and identity — a complete taxonomy for all agent memory use cases. Schema is open and extensible.

Cross-Framework

Adapters for LangChain, CrewAI, AutoGen, and LlamaIndex. Memory travels with you — no matter what framework you use.

Semantic Search

Find relevant memories instantly. Query by natural language — the API returns ranked results by relevance score.

Compliance Modes

HIPAA, GDPR, and SOC2 compliant memory storage. PHI isolation, audit logs, right-to-deletion — built in.

Analytics Dashboard

See what your agents are learning. Memory growth, type distribution, retrieval latency — all in one dashboard.

Open Source

AM-01 schema is MIT licensed. The protocol spec is open — anyone can implement it, contribute, or fork.

Try the AM-01 API

Make a request right here. No account required to explore the spec.

POST /v1/memories
Response will appear here...
GET /v1/memories?namespace=demo&per_page=10
Response will appear here...
GET /v1/memories/stats?namespace=demo
Response will appear here...

3 lines of code to connect any agent.

Install the adapter for your framework. Your agent's memory is now portable.

Coming Soon

CrewAI

Role-based agent memory. Share memories across agent crews — each agent sees what's relevant to its role.

pip install am01-crewai # TBD
Coming Soon

AutoGen

State + event persistence for Microsoft AutoGen agents. Enterprise-grade, with SOC2 compliance mode.

pip install am01-autogen # TBD
Coming Soon

LlamaIndex

RAG-centric semantic memory. AM-01 adds episodic and procedural layers on top of your existing RAG pipeline.

pip install am01-llamaindex # TBD

Start free. Scale when you're ready.

No credit card required for Sandbox. All plans include the full AM-01 protocol.

Sandbox
$0 / month
Perfect for exploring AM-01 and building your first agent memory integration.
  • 3 agents
  • 1,000 memories
  • Community adapters
  • Open protocol spec
  • API dashboard
  • Cross-agent sharing
  • Compliance modes
Get API Key
Growth
$249 / month
For growing teams with compliance needs and multiple agents that need to share context.
  • 50 agents
  • 500,000 memories
  • Cross-agent sharing
  • HIPAA / GDPR / SOC2 modes
  • Full analytics
  • Priority support
  • 99.9% SLA
Start Growth

Enterprise

Unlimited agents, custom compliance, on-premise deployment, dedicated support, and SLA guarantees.

Contact Sales

Start building in minutes.

Get your free API key. No credit card. No framework lock-in. Just universal agent memory.

Or install the LangChain adapter directly: pip install am01-langchain