$git clone https://github.com/trpc-group/trpc-agent-goEnglish | 中文
| 1 | <div align="center"> |
| 2 | <img src="docs/mkdocs/assets/img/logo-readme-blue.png" alt="tRPC logo" width="260"> |
| 3 | |
| 4 | <a id="trpc-agent-go"></a> |
| 5 | <h1>tRPC-Agent-Go</h1> |
| 6 | |
| 7 | <p> |
| 8 | English | <a href="README.zh_CN.md">中文</a> |
| 9 | </p> |
| 10 | |
| 11 | <p align="center"> |
| 12 | <a href="https://trendshift.io/repositories/15288"><img src="https://trendshift.io/api/badge/repositories/15288" alt="GitHub Trending #3 Repository Of The Day archived by Trendshift" width="250" height="55"></a> |
| 13 | <a href="https://trendshift.io/repositories/15288"><img src="https://trendshift.io/api/badge/trendshift/repositories/15288/daily?language=Go" alt="Trendshift #1 Go Repository Of The Day" width="250" height="55"></a> |
| 14 | </p> |
| 15 | |
| 16 | <p align="center"> |
| 17 | <a href="https://pkg.go.dev/trpc.group/trpc-go/trpc-agent-go"><img src="https://pkg.go.dev/badge/trpc.group/trpc-go/trpc-agent-go.svg" alt="Go Reference"></a> |
| 18 | <a href="https://github.com/trpc-group/trpc-agent-go/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-green.svg" alt="LICENSE"></a> |
| 19 | <a href="https://github.com/trpc-group/trpc-agent-go/releases"><img src="https://img.shields.io/github/release/trpc-group/trpc-agent-go.svg?style=flat-square" alt="Releases"></a> |
| 20 | <a href="https://github.com/trpc-group/trpc-agent-go/actions/workflows/prc.yml"><img src="https://github.com/trpc-group/trpc-agent-go/actions/workflows/prc.yml/badge.svg" alt="Tests"></a> |
| 21 | <a href="https://app.codecov.io/gh/trpc-group/trpc-agent-go/tree/main"><img src="https://codecov.io/gh/trpc-group/trpc-agent-go/branch/main/graph/badge.svg" alt="Coverage"></a> |
| 22 | <a href="https://trpc-group.github.io/trpc-agent-go/"><img src="https://img.shields.io/badge/Docs-Website-blue.svg" alt="Documentation"></a> |
| 23 | </p> |
| 24 | |
| 25 | <hr /> |
| 26 | </div> |
| 27 | |
| 28 | **tRPC-Agent-Go is a Go framework for building production agent systems.** |
| 29 | It provides LLM agents, graph workflows, tool calling, session and memory |
| 30 | state, knowledge retrieval, agent self-evolution, evaluation, and OpenTelemetry |
| 31 | observability in one Go-native stack. |
| 32 | |
| 33 | Use it when you want agent applications that fit Go services: concurrent, |
| 34 | observable, easy to deploy, and ready to integrate with A2A, AG-UI, and MCP. |
| 35 | |
| 36 | **Why tRPC-Agent-Go?** |
| 37 | |
| 38 | - **Go-Native Agent Runtime**: Streaming runners, context cancellation, and |
| 39 | service-friendly APIs |
| 40 | - **GraphAgent**: Type-safe graph workflows with multi-conditional routing, |
| 41 | functionally equivalent to LangGraph for Go |
| 42 | - **Multi-Agent Collaboration**: Chain, parallel, and cycle-based workflows |
| 43 | - **Rich Tool Ecosystem**: Function tools, MCP tools, web search, code |
| 44 | execution, and custom services |
| 45 | - **Persistent State**: Session, memory, artifacts, and knowledge retrieval |
| 46 | - **Agent Skills**: Reusable `SKILL.md` workflows with safe execution |
| 47 | - **Agent Self-Evolution**: Hermes-style session reviews that extract, gate, |
| 48 | and publish reusable `SKILL.md` workflows |
| 49 | - **Prompt Caching**: Automatic cost optimization with 90% savings on cached content |
| 50 | - **Evaluation & Benchmarks**: Eval sets + metrics to measure quality over time |
| 51 | - **Protocol Integration**: AG-UI for frontends, A2A for agent |
| 52 | interoperability, and MCP for tools |
| 53 | - **Production Observability**: OpenTelemetry tracing, metrics, and Langfuse |
| 54 | examples |
| 55 | |
| 56 | ## Use Cases |
| 57 | |
| 58 | **Perfect for building:** |
| 59 | |
| 60 | - **Customer Support Bots** - Intelligent agents that understand context and solve complex queries |
| 61 | - **Data Analysis Assistants** - Agents that query databases, generate reports, and provide insights |
| 62 | - **DevOps Automation** - Smart deployment, monitoring, and incident response systems |
| 63 | - **Business Process Automation** - Multi-step workflows with human-in-the-loop capabilities |
| 64 | - **Research & Knowledge Management** - RAG-powered agents for document analysis and Q&A |
| 65 | |
| 66 | ## Key Features |
| 67 | |
| 68 | <table> |
| 69 | <tr> |
| 70 | <td width="50%" valign="top"> |
| 71 | |
| 72 | ### Multi-Agent Orchestration |
| 73 | |
| 74 | ```go |
| 75 | // Chain agents for complex workflows |
| 76 | pipeline := chainagent.New("pipeline", |
| 77 | chainagent.WithSubAgents([]agent.Agent{ |
| 78 | analyzer, processor, reporter, |
| 79 | })) |
| 80 | |
| 81 | // Or run them |