# trpc-group/trpc-agent-go

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

Repository: https://github.com/trpc-group/trpc-agent-go
Canonical: https://ross.abutalabs.com/products/trpc-agent-go
Homepage: https://trpc-group.github.io/trpc-agent-go/
Language: Go
License: Apache-2.0
License Family: permissive
Topics: a2a, agent, ai, llm, mcp, a2a-protocol, ag-ui, agent-framework, ai-agents, evaluation, go, golang, graph-workflows, model-context-protocol, multi-agent, observability, opentelemetry, rag
Last push: 2026-08-26T09:31:43+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 34
- inputs: {"age_days": 476, "days_push": 7, "days_rel": 13, "gap_med": 0.0, "n_releases_24m": 117}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1733, forks 298 (observed 2026-08-28T04:05:28.880300+00:00)

## What it is
tRPC-Agent-Go is a Go-native framework for building production LLM agent systems, offering agents, graph workflows (LangGraph-equivalent), tool calling, session/memory state, RAG knowledge retrieval, and evaluation. It integrates with A2A, AG-UI, and MCP protocols and includes OpenTelemetry-based observability.

## Use cases
- build multi-agent systems in Go
- orchestrate LLM workflows with graph routing
- add RAG knowledge retrieval to a Go service
- connect agents via MCP tools and A2A protocol
- evaluate and benchmark LLM agents
- add observability to agent applications
- implement agent self-evolution with reusable skills

## When to choose
- you need a production agent framework in Go rather than Python
- your stack is Go microservices and you want concurrent, deployable agents
- you need graph-based multi-agent workflows with type safety
- you want built-in evaluation, memory, and OpenTelemetry tracing

## When to avoid
- your team is Python-based and prefers AutoGen, CrewAI, or LangChain ecosystems
- you only need a simple single-prompt LLM call without agent orchestration
- you need a mature ecosystem with extensive third-party integrations
- you require non-Go language support

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, mcp, workflow-automation, tracing, chatbot
- domain: large-language-models, developer-tools, backend
- platform: go, cross-platform, self-hosted
- tags: multi-agent, graph-workflows, a2a-protocol, ag-ui, opentelemetry, tool-calling, session-memory, agent-evaluation, self-evolution, tencent-trpc, evaluation, ai-agents, retrieval-augmented-generation

## Member repositories
- trpc-group/trpc-agent-go (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.880300+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:31:28.615625+00:00, confidence not recorded.
  - readme: https://github.com/trpc-group/trpc-agent-go (fetched 2026-08-28T04:05:28.880300+00:00, sha c4b4d34986d3)
  - homepage: https://trpc-group.github.io/trpc-agent-go/ (fetched 2026-08-29T11:08:12.490259+00:00, sha 37d1ed79b4d5)
- Data as of 2026-08-30T08:39:29.467469+00:00.