MaxKB
Reduces time-to-market for AI agent deployment by providing pre-built infrastructure for enterprise agents, eliminating custom scaffolding and accelerating c…
MaxKB (Max Knowledge Brain) is an open-source platform for building enterprise-grade agents. It combines a RAG pipeline (document upload, web crawling, automatic splitting and vectorization), an agentic workflow engine with function library and MCP tool use, and zero-code embedding into third-party systems. Model-agnostic — works with private models like DeepSeek, Llama, and Qwen as well as OpenAI, Claude, and Gemini — with multimodal text, image, audio, and video support. Deployed via Docker as a standalone platform, not a Claude Code skill.
- Build a custom AI agent that answers internal documentation questions automatically
- Create an intelligent chatbot to handle repetitive customer support inquiries
- Deploy enterprise knowledge base agents without writing custom backend code
Reduces time-to-market for AI agent deployment by providing pre-built infrastructure for enterprise agents, eliminating custom scaffolding and accelerating capability delivery to internal teams.
Engineering teams building internal AI agents or automation workflows requiring open-source control and enterprise-grade reliability.
https://github.com/1Panel-dev/MaxKB
By 1Panel-dev
How to Get It
docker run -d --name=maxkb --restart=always -p 8080:8080 -v ~/.maxkb:/opt/maxkb 1panel/maxkb
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me build a custom AI agent that answers internal documentation questions automatically
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 22,510 GitHub stars; 95 contributors; last commit 3d ago; license GPL-3.0.
Things to check
- Standalone self-hosted platform (GPL-3.0) with its own web UI — it does not run inside Claude Code. Evidence-based evaluation: scored from public trust signals, not hands-on tested. Confirm fit before client deployment.
- License (GPL-3.0) may restrict commercial use. Check with your legal team.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 22,510 GitHub stars; 95 contributors; last commit 3d ago; license GPL-3.0.