by keta1930 · MCP Server · ★ 199
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
English | 中文 Agent-Graph is a Multi-Agent System built on the principles of Context Engineering. It integrates Sub-agent, Long-term Memory, MCP, Agent-based Workflow, and other capabilities. By integrating Context Engineering best practices into a visual development experience, Agent-Graph enables developers to rapidly build, test, and deploy complex multi-agent applications. Table of Contents Framework Deployment Guide Clone Project Configure and Start Docker Services Deploy Backend Access Application Core Features Future Roadmap Coming Soon Future Plans Frontend Feature Showcase Citation WeChat Group Framework System Architecture User Journey Deployment Guide 📖 Detailed Installation Documentation: docs/first-steps/install.md System Requirements Lin
| Stars | 199 |
| Forks | 33 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 67.4912685155845/100 |
| Open Issues | 4 |
| Last Updated | 2026-05-17 |
| Created | 2025-04-24 |
| Platforms | mcp, python |
| Est. Tokens | ~5443k |
These tools work well together with agent-graph for enhanced workflows:
Looking for a agent-graph alternative? If you're comparing agent-graph with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A security scanner for your LLM agentic workflows
OpenLoomi is a Claude Cowork-style open-source alternative for builders who want local-first work memory aroun
Evo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI
Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas
A minimal yet powerful framework for creating AI agents with full control over tools, providers, and execution
Agentic RAG for any scenario. Customize sources, depth, and width
Explore other popular mcp server tools:
agent-graph is Agent Graph is a Multi-Agent System built on the principles of Context Engineering. It is categorized as a MCP Server with 199 GitHub stars.
agent-graph is primarily written in Python. It covers topics such as agent, agentic-framework, agentic-workflow.
You can find installation instructions and usage details in the agent-graph GitHub repository at github.com/keta1930/agent-graph. The project has 199 stars and 33 forks, indicating an active community.
agent-graph is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to agent-graph on Agent Skills Hub include agentic-radar, openloomi, evo-ai. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.