What are the best Go AI agents?

The Go projects listed below, ranked by maintained adoption — GitHub stars plus recent commit activity — so you see what's genuinely used and still maintained, not abandoned.

Are these Go AI agents open source and free?

Yes — every project on this page is open source and written primarily in Go. The software is free to run and self-host; you still pay for the infrastructure you run it on and any model or API usage it makes.

Why choose Go AI agents specifically?

Staying in your team's primary language — Go — makes self-hosting, extending, and debugging far easier, because you can read and modify the source directly instead of treating it as a black box.

Open source · Go

Best Go AI agents

The open-source AI agents written in Go, from the Agent Search Engine index — ranked by real maintained adoption (GitHub stars and recent commit activity), never by sponsorship. Every project here is Go-first, self-hostable, and free to run; the trade-off is you host and maintain it yourself. Right now it's led by ragflow (89k stars), with github-mcp-server and pentagi close behind. Rankings shift as projects gain stars and ship commits.

12 open-source records · the full index · more best-of lists · how we rank

ragflowPlatformRAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMsGo · 89k stars · Apache-2.0 · Aug 2026Go · 89k stars · Apache-2.0Verified · Active github-mcp-serverMCP serverGitHub's official MCP ServerGo · 32k stars · MIT · Aug 2026Go · 32k stars · MITVerified · Active pentagiAgentFully autonomous AI Agents system capable of performing complex penetration testing tasksGo · 22k stars · MIT · Aug 2026Go · 22k stars · MITVerified · Active WeKnoraPlatformOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.Go · 20k stars · Aug 2026Go · 20k stars · Aug 2026Verified · Active xiaohongshu-mcpMCP serverMCP for xiaohongshu.comGo · 15k stars · Aug 2026Go · 15k stars · Aug 2026Verified · Active robotgoSDK / libraryRobotGo, Go Native cross-platform RPA, GUI automation, Auto test and Computer use @vcaesarGo · 11k stars · Apache-2.0 · Jul 2026Go · 11k stars · Apache-2.0Verified · Active yaoFrameworkBuild AI agents and web apps — with a single binary.Go · 7.6k stars · Aug 2026Go · 7.6k stars · Aug 2026Verified · Active bifrostInfrastructureFastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.Go · 7.4k stars · Apache-2.0 · Aug 2026Go · 7.4k stars · Apache-2.0Verified · Active registryInfrastructureA community driven registry service for Model Context Protocol (MCP) servers.Go · 7.2k stars · Aug 2026Go · 7.2k stars · Aug 2026Verified · Active toolhiveInfrastructureToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.Go · 2.0k stars · Apache-2.0 · Aug 2026Go · 2.0k stars · Apache-2.0Verified · Active rulegoFrameworkRuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.Go · 1.6k stars · Apache-2.0 · Aug 2026Go · 1.6k stars · Apache-2.0Verified · Active flowcraftSDK / libraryProduction-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.Go · 416 stars · MIT · Aug 2026Go · 416 stars · MITVerified · Active

Frequently asked

What are the best Go AI agents?: The Go projects listed below, ranked by maintained adoption — GitHub stars plus recent commit activity — so you see what's genuinely used and still maintained, not abandoned.
Are these Go AI agents open source and free?: Yes — every project on this page is open source and written primarily in Go. The software is free to run and self-host; you still pay for the infrastructure you run it on and any model or API usage it makes.
Why choose Go AI agents specifically?: Staying in your team's primary language — Go — makes self-hosting, extending, and debugging far easier, because you can read and modify the source directly instead of treating it as a black box.