openai-agents-go and agentcore

These two Go libraries are competitors, as both aim to provide frameworks or core functionalities for building AI agent applications, requiring a choice between them based on desired features and architectural approaches.

openai-agents-go
51
Established
agentcore
43
Emerging
Maintenance 10/25
Adoption 10/25
Maturity 15/25
Community 16/25
Maintenance 13/25
Adoption 6/25
Maturity 9/25
Community 15/25
Stars: 241
Forks: 29
Downloads:
Commits (30d): 0
Language: Go
License: Apache-2.0
Stars: 18
Forks: 5
Downloads:
Commits (30d): 0
Language: Go
License: Apache-2.0
No Package No Dependents
No Package No Dependents

About openai-agents-go

nlpodyssey/openai-agents-go

A lightweight, powerful framework for multi-agent workflows in Go

Supports agent handoffs for control transfer, built-in tools (code interpreter, web search, file operations), and guardrails for safety validation—all compatible with OpenAI's Responses API, Chat Completions, and other LLM providers. Implements a turn-based agent loop that terminates when structured output or tool-free responses are produced, with Model Context Protocol integration for local and hosted tool servers. A direct Go port of OpenAI's Python Agents SDK maintaining API parity while offering fluent builder patterns for agent configuration, tools, and multi-agent orchestration.

About agentcore

voocel/agentcore

A minimal, composable Go library for building AI agent applications.

Implements a **double-loop architecture** (inner tool-steering loop + outer follow-up loop) with dependency injection, alongside built-in LLM adapters (OpenAI, Anthropic, Gemini via litellm), filesystem tools (read/write/edit/bash), and automatic context compaction via LLM summarization. Multi-agent orchestration works through a SubAgent tool supporting single/parallel/chain/background execution modes, while all lifecycle events (streaming, tool execution, errors) flow through a unified event channel for UI-agnostic subscription.

Scores updated daily from GitHub, PyPI, and npm data. How scores work