#494 · Primary category: AI Agents & Automation

trpc-agent-go

a2a a2a-protocol ag-ui agent agent-framework ai ai-agents evaluation go golang graph-workflows llm mcp model-context-protocol multi-agent observability opentelemetry rag

A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

Project last updated:08/29/26

GitHub Stars

1.7K

Forks

301

Contributors

57

License

Apache-2.0

Why we included this project

Go teams that want to ship agent features inside existing services often find most of the ecosystem is Python-first, forcing a separate runtime and a different deployment story. tRPC-Agent-Go is a native Go alternative, with streaming runners and context cancellation, type-safe graph workflows with conditional routing (its GraphAgent component, effectively LangGraph for Go), and multi-agent collaboration that goes beyond simple chains to parallel and cyclic patterns. It also bundles tool calling, session and memory state, knowledge retrieval, evaluation, and OpenTelemetry tracing, so a single service stays observable end to end instead of you assembling those pieces yourself. Support for A2A, AG-UI, and MCP out of the box fits teams already on tRPC microservices and anyone who wants to interoperate with the wider agent ecosystem without leaving Go. For a developer choosing an agent framework for real concurrency and deployment rather than a research toy, not many options in this space combine all of that in one Go-native stack.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category