Repository files navigation

The memory fabric for enterprise AI

Memori plugs into the software and infrastructure you already use. It is LLM, datastore and framework agnostic and seamlessly integrates into the architecture you've already designed.

Install Memori:

pip install memori

importosimportsqlite3frommemoriimportMemorifromopenaiimportOpenAIdefget_sqlite_connection():returnsqlite3.connect("memori.db")client=OpenAI(api_key=os.getenv("OPENAI_API_KEY"))memori=Memori(conn=get_sqlite_connection).llm.register(client)memori.attribution(entity_id="123456",process_id="test-ai-agent")memori.config.storage.build()response=client.chat.completions.create(model="gpt-4.1-mini",messages=[        {"role":"user","content":"My favorite color is blue."}    ])print(response.choices[0].message.content+"\n")# Advanced Augmentation runs asynchronously to efficiently# create memories. For this example, a short lived command# line program, we need to wait for it to finish.memori.augmentation.wait()# Memori stored that your favorite color is blue in SQLite.# Now reset everything so there's no prior context.client=OpenAI(api_key=os.getenv("OPENAI_API_KEY"))memori=Memori(conn=get_sqlite_connection).llm.register(client)memori.attribution(entity_id="123456",process_id="test-ai-agent")response=client.chat.completions.create(model="gpt-4.1-mini",messages=[        {"role":"user","content":"What's my favorite color?"}    ])print(response.choices[0].message.content+"\n")

/bin/echo"select * from memori_conversation_message"| /usr/bin/sqlite3 memori.db/bin/echo"select * from memori_entity_fact"| /usr/bin/sqlite3 memori.db/bin/echo"select * from memori_process_attribute"| /usr/bin/sqlite3 memori.db/bin/echo"select * from memori_knowledge_graph"| /usr/bin/sqlite3 memori.db

• Significant performance improvements using Advanced Augmentation.
• Threaded, zero latency replacement for the v2 extraction agent.
• LLM agnostic with support for all of the major foundational models.
• Datastore agnostic with support for all major databases and document stores.
• Adapter/driver architecture to make contributions easier.
• Vectorized memories and in-memory semantic search for more accurate context.
• Third normal form schema including storage of semantic triples for a knowledge graph.
• Reduced development overhead to a single line of code.
• Automatic schema migrations.

To get the most out of Memori, you want to attribute your LLM interactions to an entity (think person, place or thing; like a user) and a process (think your agent, LLM interaction or program).

If you do not provide any attribution, Memori cannot make memories for you.

mem.attribution(entity_id="12345",process_id="my-ai-bot")

Memori uses sessions to group your LLM interactions together. For example, if you have an agent that executes multiple steps you want those to be recorded in a single session.

By default, Memori handles setting the session for you but you can start a new session or override the session by executing the following:

mem.new_session()

or

session_id=mem.config.session_id# ...mem.set_session(session_id)

To make sure everything is installed in the most efficient manner, we suggest you execute the following once:

python -m memori setup

This step is not necessary but will prep your environment for faster execution. If you do not perform this step, it will be executed the first time Memori is run which will cause the first execution (and only the first one) to be a little slower.

1. Run this command once, via CI/CD or anytime you update Memori.

   Memori(conn=db_session_factory).config.storage.build()

2. Instantiate Memori with the connection factory.

   fromopenaiimportOpenAIfrommemoriimportMemoriclient=OpenAI(...)mem=Memori(conn=db_session_factory).llm.register(client)

• Anthropic
• Bedrock
• Gemini
• Grok (xAI)
• OpenAI (Chat Completions & Responses API)

(unstreamed, streamed, synchronous and asynchronous)

• Agno
• LangChain

• Nebius AI Studio

• DB API 2.0 - Direct support for any Python database driver that implements thePEP 249 Database API Specification v2.0. This includes drivers likepsycopg,pymysql,MySQLdb,cx_Oracle,oracledb, andsqlite3.
• Django - Native integration with Django's ORM and database layer
• SQLAlchemy

• CockroachDB - Full example with setup instructions
• MariaDB
• MongoDB - Full example with setup instructions
• MySQL
• OceanBase - Full example with setup instructions
• Neon - Full example with setup instructions
• Oracle
• PostgreSQL - Full example with setup instructions
• SQLite - Full example with setup instructions
• Supabase

For more examples and demos, check out theMemori Cookbook.

Memories are tracked at several different levels:

• entity: think person, place, or thing; like a user
• process: think your agent, LLM interaction or program
• session: the current interactions between the entity, process and the LLM

Memori's Advanced Augmentation enhances memories at each of these levels with:

• attributes
• events
• facts
• people
• preferences
• relationships
• rules
• skills

Memori knows who your user is, what tasks your agent handles and creates unparalleled context between the two. Augmentation occurs in the background incurring no latency.

By default, Memori Advanced Augmentation is available without an account but rate limited. When you need increased limits,sign up for Memori Advanced Augmentation or execute the following:

python -m memori sign-up<email_address>

Memori Advanced Augmentation is always free for developers!

Once you've obtained an API key, simply set the following environment variable:

export MEMORI_API_KEY=[api_key]

At any time, you can check your quota by executing the following:

python -m memori quota

Or by checking your account athttps://memorilabs.ai/. If you have reached your IP address quota, sign up and get an API key for increased limits.

If your API key exceeds its quota limits we will email you and let you know.

To use the Memori CLI, execute the following from the command line:

python -m memori

This will display a menu of the available options. For more information about what you can do with the Memori CLI, please referenceCommand Line Interface.

We welcome contributions from the community! Please see ourContributing Guidelines for details on:

• Setting up your development environment
• Code style and standards
• Submitting pull requests
• Reporting issues

• Documentation:https://memorilabs.ai/docs
• Discord:https://discord.gg/abD4eGym6v
• Issues:GitHub Issues

Apache 2.0 - seeLICENSE