Agent Memory
Covers the four agent memory types (in-context, episodic, semantic, procedural) and how to implement each — getting this right separates agents that learn across sessions from ones that forget everything.
Agent Memory Systems
Production memory infrastructure for AI agents — Mem0 (ecosystem breadth), Zep/Graphiti (temporal facts), and Letta (long-horizon paging) — with the dual-layer hot/cold architecture as the emerging production standard.
AutoGen / AG2
AG2 (formerly AutoGen) is Microsoft's event-driven multi-agent framework. GroupChat is its primary pattern — multiple agents in a shared conversation thread. Renamed from AutoGen in late 2024. Best for enterprise-scale, cross-language, and complex group coordination.
Computer Use
Computer Use lets Claude control a computer by observing screenshots and issuing mouse/keyboard actions in a tight loop — use only when structured APIs are unavailable, always inside a sandbox container.
CrewAI
CrewAI is the fastest path to a working multi-agent prototype — role-based crews, linear workflows, readable code. LangGraph wins on production-grade control. Use CrewAI for content pipelines and research automation; LangGraph for anything with cycles, branching, or checkpointing.
Google Agent Development Kit (ADK)
Google's open-source Python SDK for building production-ready agents — code-first, A2A-native, deploys to Vertex AI Agent Engine. v1.0.0 went GA in 2025; v1.18.0 is the current release (November 2025).
LangChain
The base LLM application framework. Provides document loaders, text splitters, prompt templates, chains, and the LangChain Expression Language (LCEL) pipe operator for composing LLM pipelines.
LangGraph
LangGraph v1.0 is the production standard for stateful multi-agent orchestration in Python, offering fine-grained graph-based control with built-in checkpointing and human-in-the-loop support.
LangGraph Cloud / LangGraph Platform
LangGraph Cloud (now part of LangSmith Deployment) is the managed runtime for LangGraph agents. Handles persistence, horizontal scaling, and Studio UI. Cloud (SaaS) is fastest to start; self-hosted is available for compliance.
LangMem
LangMem is LangChain's library for long-term agent memory — extracting, storing, and retrieving facts from conversations across sessions. Works with any storage backend. Integrates natively with LangGraph's memory store.
Mastra
TypeScript-native agent and workflow framework from the Gatsby team — batteries-included alternative to LangGraph for JS/TS stacks, with built-in memory, evals, observability, and durable workflows.
Multi-Agent Patterns
The three foundational multi-agent topologies (supervisor, swarm, parallel fan-out) and when each is worth the added complexity over a single agent.
OpenAI Agents SDK
OpenAI's official Python framework for multi-agent systems (March 2025) — lightweight, model-driven handoffs, built-in guardrails; trade-off vs LangGraph is simplicity at the cost of persistence and HITL support.
Practical Agent Design
Single agent first — only escalate to multi-agent when tooling-rich single agents consistently fail. Tools have three types. Guardrails are layered, not singular.
PydanticAI
Python-first agent framework by the Pydantic team — type-safe agents with Pydantic-validated outputs, dependency injection via RunContext, and automatic retry on validation failure.
ReAct Pattern
ReAct (Reasoning + Acting) is the foundational agent loop that interleaves chain-of-thought with tool calls and observations, grounding reasoning in actual tool results rather than hallucinated facts.
Strands Agents SDK
Strands Agents is AWS's open-source Python SDK for building agents in a few lines of code. Uses the Bedrock Converse API under the hood; @tool decorator turns any Python function into an agent tool; native MCP server support. Used in production by Amazon Q Developer and AWS Glue.
Voice Agents
Voice agents run on either a pipeline (STT+LLM+TTS, 800ms–2s, most production) or a native multimodal model (GPT-4o Realtime/Gemini Live, 200–500ms); LiveKit Agents v1.5 is the leading open-source framework, VAPI/Retell for managed deployment.