LangGraph
Stateful workflowsBuild stateful agent workflows with explicit control over steps, persistence and human review.
Discover the agents, frameworks and tools for your next build. 304 resources. 23 categories. One clearer place to start.
Start with the task. Choose the tools that fit.
Search the full directory, or explore a focused shortlist.
Build stateful agent workflows with explicit control over steps, persistence and human review.
Organize agents into crews and connect their tasks with stateful flows.
A TypeScript framework for building AI agents and applications.
Connect an AI client to browser automation through Microsoft's Playwright MCP server.
Add persistent memory to agents across sessions, tools and runs.
Trace agent runs, manage prompts and evaluate outputs in an AI engineering platform.
A focused route into the ecosystem.
Choose the foundations for an agent application: model integrations, orchestration and the…
89 resourcesDiscover servers and integrations that expose tools or data through the Model Context Protocol.…
21 resourcesExplore ways to carry useful context between agent sessions. Decide what should be remembered,…
25 resourcesFind tools for evaluating agent outputs and workflows. Start with representative tasks and a…
13 resourcesPractical guides for decisions that matter.
Turn a shortlist of agent frameworks into a practical decision using task boundaries, recovery tests, integration needs and maintenance costs.
Read the guideReview an MCP server's identity, exposed tools, account permissions, deployment model and failure behavior before using production credentials.
Read the guideSeparate task state, user preferences and source documents, then choose storage, retrieval and deletion rules for each type of information.
Read the guideSave a few candidates, compare their role, then check the original project before you commit.