AgenticGoKit and gollem
Both frameworks provide Go-based toolkits for building agentic AI applications with multi-agent coordination (MCP) and built-in tool discovery, making them direct competitors for developers seeking a Go solution in this domain.
About AgenticGoKit
AgenticGoKit/AgenticGoKit
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agnostic, event-driven, with multi-agent workflows, MCP tool discovery, and production-grade observability.
Built on streaming-first architecture with native multimodal support (images, audio, video), AgenticGoKit integrates OpenTelemetry for zero-config distributed tracing and includes embedded vector DB (chromem) for RAG out-of-the-box. Supports 10+ LLM providers via pluggable architecture and implements the Model Context Protocol (MCP) for standardized tool discovery and interoperability across agent workflows.
About gollem
m-mizutani/gollem
Go framework for agentic AI app with MCP and built-in tools
Supports multimodal input (images, PDFs), structured JSON output with schema validation, and portable conversation history for distributed applications. Built-in middleware system enables monitoring and behavior control, while swappable execution strategies (simple, ReAct, Plan & Execute) allow different reasoning patterns. Integrates with MCP servers for external tool discovery alongside custom tools, with automatic history compaction for stateless deployments across Gemini, Claude, and OpenAI APIs.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work