Open Source · Serverless · AWS-native

The memory infrastructure for AI agents

One API for four memory types. Working, semantic, episodic, and procedural — all serverless, all AWS-native. Give your agents persistent memory in minutes, not months.

View on GitHub
DynamoDBpgvectorS3Bedrock Titan
Integrations

Built for your stack

LangGraphCheckpointSaver
LangChainMemory retriever
CrewAIShared memory
AutoGenState store
OpenAI Agents SDKTool integration
HubSpot CRMFull CRM sync
LangGraphCheckpointSaver
LangChainMemory retriever
CrewAIShared memory
AutoGenState store
OpenAI Agents SDKTool integration
HubSpot CRMFull CRM sync
REST APIDirect access
Python SDKAsync + sync
pgvectorVector search
DynamoDBSub-10ms state
BedrockTitan embeddings
REST APIDirect access
Python SDKAsync + sync
pgvectorVector search
DynamoDBSub-10ms state
BedrockTitan embeddings
Quickstart

Your first agent memory in 15 lines

Install pip install mnemora and you're ready.

quickstart.py
Python
1from mnemora import MnemoraSync
2 
3with MnemoraSync(api_key="mnm_...") as client:
4 # Store working-memory state
5 client.store_state("agent-1", {"task": "summarize Q4", "step": 1})
6 
7 # Semantic memory — auto-embedded server-side
8 client.store_memory("agent-1", "User prefers bullet points over prose.")
9 
10 # Vector search across all stored memories
11 results = client.search_memory("user formatting preferences", agent_id="agent-1")
12 for r in results:
13 print(r.content, r.similarity_score)
14 
15 # Log an episode to the time-series history
16 client.store_episode(agent_id="agent-1", session_id="sess-001",
17 type="action", content={"tool": "summarize", "input": "Q4 report"})
The problem

AI agents are stateless by default

To give them memory, developers stitch together four databases, four clients, four billing accounts — with no unified query layer.

01

Four databases to stitch together

Redis for state. Pinecone for vectors. Postgres for structured data. S3 for logs. Four billing accounts, four clients, zero unified memory layer.

02

No unified query layer

State lives here. Vectors live there. Events are somewhere else. You write glue code instead of writing agents.

03

Agents forget everything

Without persistence, every invocation starts from scratch. Context, preferences, and history vanish between calls.

The solution

One API. Four memory types.

Serverless-first. Every component scales to zero. No LLM required for CRUD operations.

No LLM in your CRUD path — direct database ops, sub-10ms reads
<10ms

Working Memory

Key-value state in DynamoDB. Sub-10ms reads with optimistic locking and configurable TTL. Ideal for agent step state and task context.

1024d

Semantic Memory

Natural-language text stored as 1024-dimensional vectors in Aurora pgvector. Auto-embedded via Bedrock Titan. Duplicates are merged, not re-inserted.

Hot + Cold

Episodic Memory

Append-only time-series event log. Hot data in DynamoDB, automatically tiered to S3. Full session replay and time-range queries.

v0.2

Procedural Memory

Tool definitions, prompt templates, schemas, and rules stored in Postgres. Version-controlled and queryable by name. Schema is live; SDK methods ship in v0.2.

Multi-tenant by defaultLangGraph native checkpoints
Comparison

How Mnemora compares

Concrete data. No hype.

FeatureMnemora
Mem0ZepLetta
Memory types4 (state, semantic, episodic, procedural)1 (semantic only)2 (semantic + temporal)2 (core + archival)
Vector searchpgvector 1024dExternal DBBuilt-inBuilt-in
LLM required for CRUDEvery opEvery op
Serverless
Self-hostablePartial
Multi-tenant
LangGraph checkpoints
State latency<10ms~500ms<200ms~1s

Data based on public documentation as of 2025. Subject to change.

Proven Impact

From generic responses to personalized support

+123%

overall quality improvement

Measured across 10 real customer scenarios with HubSpot CRM data

Relevance+32%·Specificity+380%·Helpfulness+75%·Personalization+345%

Customer asks: “I spoke to someone last week about my API issue, any updates?”

Without Mnemora

“I'd be happy to help with your API integration issue. Could you provide your account email or ticket number? What specific issue were you experiencing?”

With Mnemora

“I can see you've had a few API-related items with us recently. Are you referring to the API rate limiting issue where you were getting 429 errors in production? That's currently marked as high priority and still being worked on.”

Powered by HubSpot CRM data synced to Mnemora semantic memory

Use Cases

Built for every agent type

From customer support to autonomous research — Mnemora adapts to your agent's memory needs.

Customer Support Agent

Remembers every customer interaction, surfaces relevant past tickets, and personalizes responses across channels.

EpisodicSemantic

Episodic memory logs each conversation. Semantic search finds similar past issues to suggest resolutions.

Research Agent

Accumulates findings across sessions, deduplicates sources, and builds a searchable knowledge base over time.

SemanticEpisodic

Semantic memory stores and deduplicates research findings. Episodic logs track the full research trail.

Coding Assistant

Maintains project context, remembers architectural decisions, and tracks code review patterns per repository.

StateSemantic

Working state holds active context. Semantic memory recalls past decisions and patterns across sessions.

Sales Agent / CRM

Tracks deal stages, remembers client preferences, and surfaces talking points from previous meetings.

StateEpisodic

State tracks deal pipeline status. Episodic memory replays past interactions for personalized follow-ups.

Workflow Automation

Persists multi-step workflow state with optimistic locking, checkpoints progress, and resumes on failure.

StateProcedural

LangGraph checkpoints persist workflow state. Procedural memory stores rules and tool definitions.

AI Tutor

Adapts to each learner, tracks mastery across topics, and builds a personalized curriculum over time.

EpisodicSemantic

Episodic memory tracks learning history. Semantic memory stores curriculum knowledge for adaptive recall.

Pricing

Simple, transparent pricing

Start free. Scale as you grow. No surprises.

Free

For exploration and side projects

Free
  • 500 API calls / day
  • 1 agent
  • 50 MB storage
  • 5K vectors
  • Community support
Get started

Starter

For early-stage products

$29/month
  • 5,000 API calls / day
  • 10 agents
  • 500 MB storage
  • 50K vectors
  • Email support
Subscribe
Most popular

Pro

For production applications

$49/month
  • 25,000 API calls / day
  • 50 agents
  • 5 GB storage
  • 250K vectors
  • Priority support
Subscribe

Scale

For high-volume teams

$99/month
  • 50,000 API calls / day
  • Unlimited agents
  • 10 GB storage
  • 500K vectors
  • Dedicated support
Subscribe

Enterprise

Unlimited everything, custom SLA, SSO/SAML, VPC peering, and dedicated infrastructure for organizations with custom needs.

Contact us

All plans include TLS encryption, AWS-native infrastructure, all four memory types, and the full Python SDK. No credit card required for Free.

FAQ

Frequently asked questions

Ready to give your agents memory?

Start in under 5 minutes. No infrastructure to configure. No servers to manage. Just memory that works.