The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
AWS Bedrock Integration and spell checks (#3124)
Antaripa Sahade0513fc9f2d
diff --git a/docs/changelog.mdx b/docs/changelog.mdxindex 68189b6df..01b7496e5 100644--- a/docs/changelog.mdx+++ b/docs/changelog.mdx@@ -496,7 +496,7 @@ mode: "wide"<Update label="2025-04-28" description="v2.1.20">**Improvements:**-- **Client:** Fixed `organizationId` and `projectId` being asssigned to default in `ping` method+- **Client:** Fixed `organizationId` and `projectId` being assigned to default in `ping` method</Update><Update label="2025-04-22" description="v2.1.19">@@ -555,7 +555,7 @@ mode: "wide"<Update label="2025-03-29" description="v2.1.13">**Improvements:**-- **Introuced `ping` method to check if API key is valid and populate org/project id**+- **Introduced `ping` method to check if API key is valid and populate org/project id**</Update><Update label="2025-03-29" description="AI SDK v1.0.0">diff --git a/docs/docs.json b/docs/docs.jsonindex 3f6bbd2ce..e5c3d45af 100644--- a/docs/docs.json+++ b/docs/docs.json@@ -260,6 +260,7 @@"integrations/livekit","integrations/pipecat","integrations/elevenlabs",+ "integrations/aws-bedrock","integrations/flowise","integrations/langchain-tools","integrations/agentops",diff --git a/docs/examples/ai_companion.mdx b/docs/examples/ai_companion.mdxindex 945a6da4a..56a786c40 100644--- a/docs/examples/ai_companion.mdx+++ b/docs/examples/ai_companion.mdx@@ -61,7 +61,7 @@ class Companion:check_prompt = f"""Analyze the given input and determine whether the user is primarily:1) Talking about themselves or asking for personal advice. They may use words like "I" for this.- 2) Inquiring about the AI companions's capabilities or characteristics They may use words like "you" for this.+ 2) Inquiring about the AI companion's capabilities or characteristics They may use words like "you" for this.Respond with a single word:- 'user' if the input is focused on the userdiff --git a/docs/examples/llama-index-mem0.mdx b/docs/examples/llama-index-mem0.mdxindex 371b3e526..19c867e18 100644--- a/docs/examples/llama-index-mem0.mdx+++ b/docs/examples/llama-index-mem0.mdx@@ -80,7 +80,7 @@ agent = FunctionCallingAgent.from_tools(```Start the chat.-<Note> The agent will use the Mem0 to store the relavant memories from the chat. </Note>+<Note> The agent will use the Mem0 to store the relevant memories from the chat. </Note>Input```python@@ -139,7 +139,7 @@ Added user message to memory: I am feeling hungry, order me something and send m=== LLM Response ===Please let me know your name and the dish you'd like to order, and I'll take care of it for you!```-<Note> The agent is not able to remember the past prefernces that user shared in previous chats. </Note>+<Note> The agent is not able to remember the past preferences that user shared in previous chats. </Note>### Using the agent WITH memoryInput@@ -171,4 +171,4 @@ Emailing... David=== LLM Response ===I've ordered a pizza for you, and the bill has been sent to your email. Enjoy your meal! If there's anything else you need, feel free to let me know.```-<Note> The agent is able to remember the past prefernces that user shared and use them to perform actions. </Note>+<Note> The agent is able to remember the past preferences that user shared and use them to perform actions. </Note>diff --git a/docs/examples/multimodal-demo.mdx b/docs/examples/multimodal-demo.mdxindex 935e616ef..1f034e82c 100644--- a/docs/examples/multimodal-demo.mdx+++ b/docs/examples/multimodal-demo.mdx@@ -6,28 +6,28 @@ title: Multimodal Demo with Mem0Enhance your AI interactions with **Mem0**'s multimodal capabilities. Mem0 now supports image understanding, allowing for richer context and more natural interactions across supported AI platforms.-> π Experience the power of multimodal AI! Test out Mem0's image understanding capabilities at [multimodal-demo.mem0.ai](https://multimodal-demo.mem0.ai)+> Experience the power of multimodal AI! Test out Mem0's image understanding capabilities at [multimodal-demo.mem0.ai](https://multimodal-demo.mem0.ai)-## π Features+## Features-- **πΌοΈ Image Understanding**: Share and discuss images with AI assistants while maintaining context.-- **π Smart Visual Context**: Automatically capture and reference visual elements in conversations.-- **π Cross-Modal Memory**: Link visual and textual information seamlessly in your memory layer.-- **π Cross-Session Recall**: Reference previously discussed visual content across different conversations.-- **β‘ Seamless Integration**: Works naturally with existing chat interfaces for a smooth experience.+- **Image Understanding**: Share and discuss images with AI assistants while maintaining context.+- **Smart Visual Context**: Automatically capture and reference visual elements in conversations.+- **Cross-Modal Memory**: Link visual and textual information seamlessly in your memory layer.+- **Cross-Session Recall**: Reference previously discussed visual content across different conversations.+- **Seamless Integration**: Works naturally with existing chat interfaces for a smooth experience.-## π How It Works+## How It Works-1. **π Upload Visual Content**: Simply drag and drop or paste images into your conversations.-2. **π¬ Natural Interaction**: Discuss the visual content naturally with AI assistants.-3. **π Memory Integration**: Visual context is automatically stored and linked with your conversation history.-4. **π Persistent Recall**: Retrieve and reference past visual content effortlessly.+1. **Upload Visual Content**: Simply drag and drop or paste images into your conversations.+2. **Natural Interaction**: Discuss the visual content naturally with AI assistants.+3. **Memory Integration**: Visual context is automatically stored and linked with your conversation history.+4. **Persistent Recall**: Retrieve and reference past visual content effortlessly.## Demo Video<iframe width="700" height="400" src="https://www.youtube.com/embed/2Md5AEFVpmg?si=rXXupn6CiDUPJsi3" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>-## π₯ Try It Out+## Try It OutVisit [multimodal-demo.mem0.ai](https://multimodal-demo.mem0.ai) to experience Mem0's multimodal capabilities firsthand. Upload images and see how Mem0 understands and remembers visual context across your conversations.diff --git a/docs/faqs.mdx b/docs/faqs.mdxindex edf9bc361..c1efef9f1 100644--- a/docs/faqs.mdx+++ b/docs/faqs.mdx@@ -14,7 +14,7 @@ iconType: "solid"When an AI agent or LLM needs to access memories, it employs the `search` method. Mem0 conducts a comprehensive search across these data stores, retrieving relevant information from each.- The retrieved memories can be seamlessly integrated into the LLM's prompt as required, enhancing the personalization and relevance of responses.+ The retrieved memories can be seamlessly integrated into the system prompt as required, enhancing the personalization and relevance of responses.</Accordion><Accordion title="What are the key features of Mem0?">@@ -23,7 +23,7 @@ iconType: "solid"- **Developer-Friendly API**: Offers a straightforward API for seamless integration into various applications.- **Platform Consistency**: Ensures consistent behavior and data across different platforms and devices.- **Managed Service**: Provides a hosted solution for easy deployment and maintenance.- - **Save Costs**: Saves costs by adding relevent memories instead of complete transcripts to context window+ - **Save Costs**: Saves costs by adding relevant memories instead of complete transcripts to context window</Accordion><Accordion title="How Mem0 is different from traditional RAG?">diff --git a/docs/features.mdx b/docs/features.mdxindex 6d758f263..08114c1a0 100644--- a/docs/features.mdx+++ b/docs/features.mdx@@ -13,7 +13,7 @@ iconType: "solid"- **Developer-Friendly API**: Offers a straightforward API for seamless integration into various applications.- **Platform Consistency**: Ensures consistent behavior and data across different platforms and devices.- **Managed Service**: Provides a hosted solution for easy deployment and maintenance.-- **Save Costs**: Saves costs by adding relevent memories instead of complete transcripts to context window+- **Save Costs**: Saves costs by adding relevant memories instead of complete transcripts to context windowdiff --git a/docs/integrations/agno.mdx b/docs/integrations/agno.mdxindex 77ff91401..018323137 100644--- a/docs/integrations/agno.mdx+++ b/docs/integrations/agno.mdx@@ -7,10 +7,10 @@ Integrate [**Mem0**](https://github.com/mem0ai/mem0) with [Agno](https://github.## Overview-1. π§ Store and retrieve memories from Mem0 within Agno agents-2. πΌοΈ Support for multimodal interactions (text and images)-3. π Semantic search for relevant past conversations-4. π Personalized responses based on user history+1. Store and retrieve memories from Mem0 within Agno agents+2. Support for multimodal interactions (text and images)+3. Semantic search for relevant past conversations+4. Personalized responses based on user history## Prerequisitesdiff --git a/docs/integrations/aws-bedrock.mdx b/docs/integrations/aws-bedrock.mdxnew file mode 100644index 000000000..bc718fd0f--- /dev/null+++ b/docs/integrations/aws-bedrock.mdx@@ -0,0 +1,132 @@+---+title: AWS Bedrock+---++<Snippet file="security-compliance.mdx" />++This integration demonstrates how to use **Mem0** with **AWS Bedrock** and **Amazon OpenSearch Service (AOSS)** to enable persistent, semantic memory in intelligent agents.++## Overview++In this guide, you'll:++1. Configure AWS credentials to enable Bedrock and OpenSearch access+2. Set up the Mem0 SDK to use Bedrock for embeddings and LLM+3. Store and retrieve memories using OpenSearch as a vector store+4. Build memory-aware applications with scalable cloud infrastructure++## Prerequisites++- AWS account with access to:+ - Bedrock foundation models (e.g., Titan, Claude)+ - OpenSearch Service with a configured domain+- Python 3.8++- Valid AWS credentials (via environment or IAM role)++## Setup and Installation++Install required packages:++```bash+pip install mem0ai boto3 opensearch-py+```++Set environment variables:++Be sure to configure your AWS credentials using environment variables, IAM roles, or the AWS CLI.++```python+import os++os.environ['AWS_REGION'] = 'us-west-2'+os.environ['AWS_ACCESS_KEY_ID'] = 'AKIA...'+os.environ['AWS_SECRET_ACCESS_KEY'] = 'AS...'+```++## Initialize Mem0 Integration++Import necessary modules and configure Mem0:++```python+import boto3+from opensearchpy import OpenSearch, RequestsHttpConnection, AWSV4SignerAuth+from mem0.memory.main import Memory++region = 'us-west-2'+service = 'aoss'+credentials = boto3.Session().get_credentials()+auth = AWSV4SignerAuth(credentials, region, service)++config = {+ "embedder": {+ "provider": "aws_bedrock",+ "config": {+ "model": "amazon.titan-embed-text-v2:0"+ }+ },+ "llm": {+ "provider": "aws_bedrock",+ "config": {+ "model": "anthropic.claude-3-5-haiku-20241022-v1:0",+ "temperature": 0.1,+ "max_tokens": 2000+ }+ },+ "vector_store": {+ "provider": "opensearch",+ "config": {+ "collection_name": "mem0",+ "host": "your-opensearch-domain.us-west-2.es.amazonaws.com",+ "port": 443,+ "http_auth": auth,+ "embedding_model_dims": 1024,+ "connection_class": RequestsHttpConnection,+ "pool_maxsize": 20,+ "use_ssl": True,+ "verify_certs": True+ }+ }+}++# Initialize memory system+m = Memory.from_config(config)+```++## Memory Operations++Use Mem0 with your Bedrock-powered LLM and OpenSearch storage backend:++```python+# Store conversational context+messages = [+ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},+ {"role": "assistant", "content": "How about a thriller?"},+ {"role": "user", "content": "I prefer sci-fi."},+ {"role": "assistant", "content": "Noted! I'll suggest sci-fi movies next time."}+]++m.add(messages, user_id="alice", metadata={"category": "movie_recommendations"})++# Search for memory+relevant = m.search("What kind of movies does Alice like?", user_id="alice")++# Retrieve all user memories+all_memories = m.get_all(user_id="alice")+```++## Key Features++1. **Serverless Memory Embeddings**: Use Titan or other Bedrock models for fast, cloud-native embeddings+2. **Scalable Vector Search**: Store and retrieve vectorized memories via OpenSearch+3. **Seamless AWS Auth**: Uses AWS IAM or environment variables to securely authenticate+4. **User-specific Memory Spaces**: Memories are isolated per user ID+5. **Persistent Memory Context**: Maintain and recall history across sessions++## Help++- [AWS Bedrock Documentation](https://docs.aws.amazon.com/bedrock/)+- [Amazon OpenSearch Service Docs](https://docs.aws.amazon.com/opensearch-service/)+- [Mem0 Platform](https://app.mem0.ai)++<Snippet file="get-help.mdx" />+diff --git a/docs/integrations/langchain.mdx b/docs/integrations/langchain.mdxindex df249c260..1ac215181 100644--- a/docs/integrations/langchain.mdx+++ b/docs/integrations/langchain.mdx@@ -64,11 +64,11 @@ Create functions to handle context retrieval, response generation, and additiondef retrieve_context(query: str, user_id: str) -> List[Dict]:"""Retrieve relevant context from Mem0"""memories = mem0.search(query, user_id=user_id)- seralized_memories = ' '.join([mem["memory"] for mem in memories])+ serialized_memories = ' '.join([mem["memory"] for mem in memories])context = [{"role": "system",- "content": f"Relevant information: {seralized_memories}"+ "content": f"Relevant information: {serialized_memories}"},{"role": "user",diff --git a/docs/integrations/llama-index.mdx b/docs/integrations/llama-index.mdxindex cbf43377d..77fe57acd 100644--- a/docs/integrations/llama-index.mdx+++ b/docs/integrations/llama-index.mdx@@ -103,7 +103,7 @@ memory_from_config = Mem0Memory.from_config()```-Intilaize the LLM+Initialize the LLM```pythonimport os