# Add a chat message to the graph await "Jane" "user" "I can't log in!" # Add business data to the graph await type "json" "account_status" "suspended" # get memory relevant to the current conversation "session_id" print """FACTS and ENTITIES represent relevant context to the current conversation.# These are the most relevant facts and their valid date ranges# format: FACT (Date range: from - to) - Emily is experiencing issues with logging in. (2024-11-14 02:13:19+00:00 - present) - Emily's account has a suspended status due to payment failure. (2024-11-14 02:03:58+00:00 - present) ...""" // Add a chat message to the graph add "session_id" role "Jane" roleType "user" content "I can't log in!" // Add business data to the graph add "json" account_status "suspended" // Get memory relevant to the current conversation const memory get "session_id" log and # These are the most relevant facts and their valid date ranges # format: FACT (Date range: from - to) 2024 11 14 02 13 19 00 00 's account has a suspended status due to payment failure. (2024-11-14 02:03:58+00:00 - present) ...``` Add TODO "sessionId" Messages Content "I can't log in!" RoleType Add TODO UserId Type "json" Data string interface "account_status" "suspended" Get TODO "session_id" Println and # These are the most relevant facts and their valid date ranges # format: FACT (Date range: from - to) 2024 11 14 02 13 19 00 00 's account has a suspended status due to payment failure. (2024-11-14 02:03:58+00:00 - present) ...``` without adding latency Equip your agents with the knowledge to complete tasks, from the mundane to monumental. Zep's ChatHistory class makes production-ready personalization simple for any LangChain Expression Language or LangGraph app. Zep's ChatHistory class makes production-ready personalization simple for any LangChain Expression Language or LangGraph app. Zep is the current state-of-the-art in agent memory, excelling in the LongMemEval benchmark, a challenging evaluation that closely models enterprise use cases. Zep shows an aggregate accuracy improvement of up to 18.5% over the baseline, and 100% improvements for many individual evaluations. All while simultaneously reducing response latency by 90%. "Zep just introduced a game-changing way for AI agents to remember and learn. Unlike other systems that only retrieve static documents, Zep uses a temporal knowledge graph to combine conversations and structured business data, keeping track of how things change over time." "Zep is one of the most exciting things I've seen for real-world agent use cases in a long time. Their innovative approach is truly game-changing." "Zep AI was instrumental in enabling the Sidekick’s personalized experience through dynamic memory retrieval. Their innovative tech stack is powering groundbreaking projects like ArtPrize 2024, taking personalized AI experiences to the next level." "Zep AI empowers AI systems to think and remember like humans. By organizing memories into structured episodes and extracting key insights, it builds smarter, more intuitive AI agents that revolutionize how businesses harness intelligence." Get relevant results from memory in milliseconds. Scale to millions of users with ease. Tailor memory extraction and relevance with custom rating frameworks and controls. Be assured with SOC 2 Type II compliance. Zep also offers privacy controls to support CCPA and GDPR compliance. With minimal code changes, enable your agent with rich, relevant context from chat and business data. Develop agents in Python, TypeScript, or Go - with any framework or none at all. Build your agent in Python, TypeScript, or Go using your favorite framework, or none at all. Get structured output from chat messages, more accurately and faster than your LLM provider's JSON or Structured Output mode. Zep offers built-in types for datetimes, floats, emails, RegEx patterns, and more. Understand user intent and emotion, segment users, and more. Route chains based on semantic context, and trigger events. All without adding latency to your user experience.