#4242nd of 48 in Agent frameworks and SDKs
eino
Go framework for building LLM agents and graph-based workflows
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 13.3k
- License
- Apache-2.0
- Last commit
- Sep 2026
- Last release
- Sep 2026
- Language
- Go
Missed the latest GitHub check; these facts may be older.
Overview
Eino is a Go framework for LLM applications, modeled on LangChain and Google ADK but following Go conventions. It provides component interfaces (ChatModel, Tool, Retriever, Embedding), an Agent Development Kit with ReAct agents, a multi-agent DeepAgent and interrupt/resume, and a compose package for typed graphs and workflows. Component implementations live in the separate eino-ext repo.
Who it is for: Go developers building agents and LLM pipelines in code
Strengths
- Typed graph and workflow composition, with graphs exposable as agent tools
- Handles stream concatenation, merging and copying between nodes automatically
- Interrupt/resume with checkpoints for human-in-the-loop agents
- Official integrations for OpenAI, Claude, Gemini, Ark, Ollama and Elasticsearch
Weaknesses
- Go only; no Python or TypeScript bindings
- Component implementations are in a separate eino-ext repository
- README documentation links point to the Chinese-language manual path
- No built-in UI; visual debugging is a separate devops module
What it needs
- no GPU
- Needs Go 1.18+
- Models: OpenAI, Claude, Gemini, Ark, Ollama
Also in Agent frameworks and SDKs
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 93 out of 100 |
| 2 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 88 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 87 out of 100 |