Skip to content

Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

Add Google ADK long-running agent guide

ai-boost3485b87148c5
diff --git a/README.md b/README.md
index ab3bcd1..c6f3ab1 100644
--- a/README.md
+++ b/README.md
@@ -248,6 +248,7 @@ Harness components organized by the problem they solve, not by vendor.
- [LangGraph](https://github.com/langchain-ai/langgraph) — Graph-based state machine framework for multi-agent harnesses: models supervisor/subagent topologies, error-recovery branches, and checkpoint persistence as first-class primitives. The most widely adopted harness orchestration layer in production. ![Stars](https://img.shields.io/github/stars/langchain-ai/langgraph?style=flat-square&label=★&color=yellow)
- [OpenAI Agents SDK](https://github.com/openai/openai-agents-python) — Lightweight multi-agent framework built around handoffs and guardrails; the production successor to Swarm. Complements LangGraph for harnesses where delegation patterns are simpler than full graph orchestration. ![Stars](https://img.shields.io/github/stars/openai/openai-agents-python?style=flat-square&label=★&color=yellow)
- [Google ADK](https://github.com/google/adk-python) — Google's code-first agent framework with built-in multi-agent orchestration, tool registration, session state, and eval pipeline. Its `Runner` and `AgentTool` patterns are the reference implementation for wrapping sub-agents as tools in a larger harness. ![Stars](https://img.shields.io/github/stars/google/adk-python?style=flat-square&label=★&color=yellow)
+- [Build Long-running AI agents that pause, resume, and never lose context with ADK](https://developers.googleblog.com/build-long-running-ai-agents-that-pause-resume-and-never-lose-context-with-adk/) — Google's May 2026 guide to production agents that survive days-long idle periods: `DatabaseSessionService` for persistent sessions, webhook-triggered `state_delta` resumption that lets containers scale to zero, and explicit state machines instead of dumping raw JSON into vector databases. Complements Anthropic's managed-agents architecture with a cloud-native deployment perspective.
- [AutoGen](https://github.com/microsoft/autogen) — Microsoft's multi-agent conversation framework with a complete AgentChat layer covering agent loop, tool integration, termination conditions, and human-in-the-loop. The most comprehensive open-source reference for large-scale multi-agent harness design. ![Stars](https://img.shields.io/github/stars/microsoft/autogen?style=flat-square&label=★&color=yellow)
- [CrewAI](https://github.com/crewAIInc/crewAI) — Dual-layer harness orchestration: Crew handles autonomous agent delegation, Flow provides event-driven deterministic control (branching + shared Pydantic state). The clearest open-source example of mixing autonomous and scripted execution in the same harness. ![Stars](https://img.shields.io/github/stars/crewAIInc/crewAI?style=flat-square&label=★&color=yellow)
- [PydanticAI](https://github.com/pydantic/pydantic-ai) — Type-safe agent framework where tool definitions, parameters, and return values are Pydantic models. Shifts "agent output doesn't match expected structure" from a runtime bug to a type-check failure; its `RunContext` dependency injection pattern is the reference design for passing session-scoped objects through the harness without global state. ![Stars](https://img.shields.io/github/stars/pydantic/pydantic-ai?style=flat-square&label=★&color=yellow)