Logo
Deploy Now

Categories

Self-Hosted LLM Chatbot RAG Agent Platform Enterprise AI AI Knowledge Base

Stars

5,550

Forks

645

Watchers

56

Developer links

Last Updated: 08-23-2026 03:23 AM (UTC)

Casibase

Casibase lets organizations build AI-powered knowledge bases that answer questions from their own documents, connecting to 30+ model providers through a unified admin interface with RAG retrieval and multi-agent orchestration via MCP and A2A protocols. The platform plugs into OpenAI GPT-4o, Anthropic Claude, Meta Llama, Google Gemini, DeepSeek, Ollama local models, HuggingFace, Azure OpenAI, and additional providers, while embedding APIs from OpenAI Ada and Baidu handle vector representation of ingested documents. Document ingestion parses TXT, Markdown, DOCX, PDF, CSV, XLSX, and PPTX files with intelligent chunking strategies for optimal retrieval accuracy. The built-in chat interface provides real-time AI conversations with manual session handover for human agent escalation, and comprehensive chat session logging enables audit trails for compliance. Enterprise identity management integrates Casdoor for Single Sign-On supporting GitHub, Google, WeChat, and OIDC providers with fine-grained access control via the Casbin permission engine. The multi-tenant architecture supports isolated knowledge bases per organization with role-based user management and configurable storage, model, and embedding providers per tenant. The React frontend with Ant Design v5 provides a polished admin dashboard for managing providers, knowledge stores, chat sessions, and user access, while the Go backend with Beego framework handles API logic with MySQL or MariaDB persistence. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Casibase
Casibase
Casibase
Casibase
Casibase

Benefits

  • 30+ AI Model Provider Support
  • Unified configuration connects OpenAI GPT-4o, Anthropic Claude, Meta Llama, Google Gemini, DeepSeek, Ollama local models, HuggingFace, and Azure OpenAI through a single admin interface.
  • Enterprise SSO and Access Control
  • Casdoor Single Sign-On integration supports GitHub, Google, WeChat, and OIDC providers with Casbin permission engine enforcing fine-grained role-based access control policies per tenant.
  • RAG Document Intelligence System
  • Intelligent document parsing handles TXT, Markdown, DOCX, PDF, CSV, XLSX, and PPTX formats with configurable chunking strategies and vector embedding for accurate knowledge retrieval.
  • MCP and A2A Protocol Management
  • Model Context Protocol and Agent-to-Agent protocol support enables structured AI agent orchestration, tool integration, and multi-agent communication workflows within the platform.

Features

  • Real-Time Chat Interface
  • Built-in AI conversation interface with session logging, human agent handover, audit trails, and multi-model selection per conversation for compliance.
  • Multi-Tenant Knowledge Bases
  • Isolated knowledge stores per organization with configurable storage, model, and embedding providers and role-based user management for each tenant.
  • Admin Dashboard UI
  • React and Ant Design v5 management interface for configuring providers, knowledge stores, chat sessions, users, and access control policies.
  • Multilingual Interface
  • Interface localization supporting Chinese, English, French, German, Spanish, Japanese, Korean, Russian, Portuguese, Italian, Vietnamese, and additional languages via Crowdin.
  • Vector Embedding APIs
  • OpenAI Ada and Baidu embedding provider integration generates vector representations for knowledge documents enabling semantic similarity search during RAG retrieval.