What an agent keeps across sessions, and how it decides what to recall.
Memory enables agents to be reflective, interactive, proactive, and autonomous, mimicking human intelligence where recall determines capability. Without it, applications remain stateless and heavily reliant on repetitive prompt engineering.
▶ 3:15
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
You need to install Docker on your laptop and pull the workshop's Docker image to run the local server. Then, you clone the repository, navigate into the example folder, and launch the Jupyter notebook to act as the client.
▶ 0:20
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Agent memory is built on a combination of embedding models, databases, and large language models. The embedding models handle semantic search representation, databases store and retrieve information, and LLMs provide static parametric memory.
▶ 4:32
Why your Agent needs Memory, not just context
Claude Tag provides an extra degree of proactivity by autonomously initiating conversations, managing cross-channel memory, and executing long-running tasks. It can spin up its own sandboxes and ping you when a pull request is ready, shifting workflows from single-player sessions to asynchronous, multiplayer collaboration.
▶ 4:02
Inside Anthropic: How Claude Tag Is Changing Agentic Work
Memory management involves generation, storage, retrieval, integration, updating, and specialized deletion mechanisms like forgetting. The retrieval phase is particularly crucial for pulling relevant structured memories into the context window rather than stuffing all data in.
▶ 6:37
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Transformers are inherently stateless machines, meaning that when you close an interaction loop, the model has no built-in way to update its state or learn over time. Relying purely on appending messages to a list held in process memory leads to severe failures when trying to build reliable long-horizon agents.
▶ 2:43
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
While context engineering focuses on curating information for limited context windows, memory engineering optimizes retrieval pipelines and latency. It combines disciplines like database engineering, search optimization, and AI engineering to manage agent recall.
▶ 6:33
Why your Agent needs Memory, not just context
Developers move away from single-player IDE sessions toward asynchronous, multiplayer collaboration directly inside communication channels like Slack. Instead of stepping through every turn of the agent, developers define success criteria and let long-running agents execute complex tasks and ping teams for reviews.
▶ 11:33
Inside Anthropic: How Claude Tag Is Changing Agentic Work
MongoDB provides a flexible document data model that adapts to various data structures alongside multiple retrieval capabilities like graph, vector, text, and geospatial queries in one database. This allows developers to store diverse memory types and build custom memory management solutions.
▶ 8:36
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
It uses a server-client architecture where memory is organized into explicit memory blocks, such as persona and human profiles, represented as editable strings. The system makes the LLM aware of its context window and gives it tool-calling capabilities to actively manage and rewrite its own memory.
▶ 23:22
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Skills act as standard operating procedures for agents, serving as procedural memory for tasks. They provide step-by-step instructions and tool locations to ensure consistent execution, similar to how human SOPs transfer knowledge.
▶ 10:05
Why your Agent needs Memory, not just context
Agent execution time horizons are on an exponential trajectory, doubling roughly every four months according to METR research. This increase in capability means agents can handle more multi-step tasks, verify their own work, and earn greater human trust.
▶ 15:55
Inside Anthropic: How Claude Tag Is Changing Agentic Work
Persona memory helps assign a consistent personality to AI systems to make them more believable and human-like. Developers can model this personality data inside MongoDB to foster better relationships with users.
▶ 10:09
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Leta acts as a context management system that controls the context window, allowing developers to set strict limits like 10k tokens. This prevents payloads from creeping up over time and causing high latency during enterprise workflows. Despite the small window, the agent retains its memory through external storage mechanisms.
▶ 25:06
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Entity memory stores user-specific details like preferences, working styles, and tool stacks to build a persona. This memory helps make the agent's interactions more believable and tailored to the individual user.
▶ 23:26
Why your Agent needs Memory, not just context
Claude Tag agents are given their own independent permissions and API keys rather than assuming the user's permissions. This allows them to work autonomously on behalf of the team instead of an individual. Consequently, it becomes much easier to audit the agent's actions securely.
▶ 34:15
Inside Anthropic: How Claude Tag Is Changing Agentic Work
Instead of stuffing all tool schemas into the limited context window, developers can store JSON schemas of tools inside MongoDB. Just before hitting the LLM, the system queries the database to retrieve only the relevant tool via search.
▶ 10:45
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Letta uses core memory which sits inside the context window for immediate top-level recall like hobbies and names. Archival memory acts as an infinite read-write data source like a vector database for large documents outside the context window. Recall memory functions as a write-protected conversation history mimicking messaging search.
▶ 29:55
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
The memory life cycle starts with data ingestion, cleaning, and encoding via embedding models into a database. Crucially, it also requires mechanisms like forgetting or suppressing outdated information to keep the system accurate.
▶ 28:12
Why your Agent needs Memory, not just context
Anthropic found that opinionated memory abstractions and indexed stores were often too restrictive and prone to issues. As models became more capable, agents performed better using native bash, grep, and straightforward file systems. Removing complex memory structures simplified harnesses while letting models handle data effectively.
▶ 36:56
Inside Anthropic: How Claude Tag Is Changing Agentic Work
When an agentic system executes steps that fail, that failure can be stored in the database as a learning experience. This historical failure data is then pulled into subsequent execution steps to prevent the LLM from repeating the same mistake.
▶ 12:15
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Traditional React agents loop indefinitely until they decide they are done, which increases the risk of derailment. In Letta, the agent uses heartbeat requests where it must explicitly say it wants to keep going. This inverse approach makes the agent much less likely to derail over long time horizons.
▶ 44:25
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Omnipresent agents operate across tools like Slack and Google Workspace to track successful workflows and processes. They automatically document these events into skills or workflow memory, capturing tribal knowledge before it is lost.
▶ 34:18
Why your Agent needs Memory, not just context
Teams can build a journey of trust by configuring human-agent interaction gates according to their risk tolerance. They can start by having agents diagnose fixes or create draft pull requests while keeping traditional safety processes in place. Over time, confidence grows, allowing teams to delegate more automated resolution tasks.
▶ 45:48
Inside Anthropic: How Claude Tag Is Changing Agentic Work
MongoDB acquired Voyage AI to integrate their embedding models and re-rankers directly into MongoDB Atlas. This integration aims to reduce AI hallucinations and eliminate the need for developers to write custom chunking strategies.
▶ 14:09
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Multi-agent communication relies on stateful agents interacting through API-backed messaging tools similar to asynchronous chat. Agents can message each other either asynchronously to receive delivery receipts or synchronously by waiting for replies. This design allows independent agents to coordinate via shared communication channels.
▶ 1:02:24
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
File systems allow developers to build quickly without worrying about infrastructure setup or tool selection because LLMs have a natural affinity for bash and shell commands. However, this speed comes at the cost of enterprise security, concurrency, and data privacy.
▶ 0:42
Why your Agent needs Memory, not just context
Dreaming is a research feature that runs automated jobs to review session transcripts and memory stores for discrepancies or stale information. Another agent analyzes these execution traces to find missing context or misleading data, generating hypotheses for improvements. This automated review process paves the way for continual learning and better agent performance.
▶ 50:02
Inside Anthropic: How Claude Tag Is Changing Agentic Work
Historical neuroscience research on the visual cortex of cats inspired convolutional neural networks for object and face detection. Today, agent architects collaborate directly with neuroscientists studying human memory to apply nature's blueprint to advanced artificial intelligence systems.
▶ 15:59
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
When working with active documents, language models generally perform better when rewriting the entire document from scratch rather than generating line-by-line diffs. You can structure this using simple file read and write tools inspired by Anthropic benchmarks. This avoids the complexity of precise partial edits that models often struggle with.
▶ 1:17:12
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Future systems will merge the agent loop with the model training loop by feeding collected traces back into training. This allows models to continuously improve their core latent memory rather than relying solely on retrieval context.
▶ 41:05
Why your Agent needs Memory, not just context
Running arbitrary tool code requires a secure execution sandbox to prevent agents from compromising the host system. Leta supports integration with E2B by default to isolate tool execution when an API key is provided. While this introduces a trade-off with cold start latency, it safely isolates multi-tenant environments.
▶ 1:00:15
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
No answer mentions that.