Auto-Ontology

Context Ontology Accelerator is an open-source semantic context layer for AWS and AI agents. It combines knowledge graphs, formal ontologies, rule-based systems, and modern AI in a Scan → Model → Serve workflow: it connects data sources, discovers schemas, enriches metadata, and ingests documents; induces and manages ontologies, defines metrics, and builds a unified semantic graph; then serves context through SPARQL federation using a Virtual Knowledge Graph, knowledge-graph traversal, queries, and MCP tools. The repository includes source-ingestion services for databases and documents, ontology induction and reasoning with HermiT and ELK, an Ontop-based Virtual Knowledge Graph, a context manager for query orchestration, and a React frontend. Access is controlled through namespace isolation and role-based authorization, with namespace-scoped roles and platform-level roles. The implementation uses Python and TypeScript, AWS CDK, Smithy-generated API contracts, and an Nx-managed monorepo; the project is licensed under Apache License 2.0.

AutoGen is an open-source framework from Microsoft for building and orchestrating agent-based workflows that use large language models. It provides components for defining agents, managing conversations and interactions, and integrating models and external tools.

AutoBot is an open-source, self-hosted AI platform for running conversational AI, private knowledge bases, workflows, and installable modules on infrastructure controlled by the operator. It accepts documents, codebases, runbooks, and business knowledge into a locally stored RAG knowledge base backed by a knowledge graph, and connects to local or hosted language models through a provider-agnostic gateway with configurable fallback. Its platform provides chat, streaming, retrieval, memory, governance, local inference, visual and code-based workflow creation, browser automation, vision processing, transcription, and codebase analysis. A Service Lifecycle Manager deploys, operates, and scales services such as databases, vector storage, inference, and workers across one or more machines, with modules including Company OS, Codebase Analytics, and Transcriber.

Omni Analytics is an AI analytics platform with a governed semantic layer that captures shared business definitions and context for data analysis. It lets users ask questions in an AI chat interface, refine results, build dashboards and workbooks, create visualizations, use spreadsheets and SQL, and receive summaries or diagnoses of metric changes. Its built-in modeling agent helps build metrics and add AI context, while skills, APIs, and an MCP server let agents query data, build models, run queries, and manage content. Omni also provides embedding, SSO, APIs, and integrations for shipping analytics inside other products. The platform includes permissions, branch mode for testing AI context without changing live content, and Git and version-control support.

OpenBot is an open-source AI agent platform from CopilotKit that gives each agent its own computer with a browser, logins, files, tools, and a dedicated interaction channel. It runs in the user's infrastructure and accepts agents that speak the AG-UI protocol, including agents built with LangGraph, Mastra, CrewAI, Pydantic AI, Google ADK, or custom code. A single gateway mediates actions involving the computer, files, MCP servers, and UI components: it decides whether an action is permitted before execution and records it afterward. Agents can operate their own browser screen, hand control to a human for restricted actions, and return component-based responses. Docker Compose runs the application components and PostgreSQL, while the administrator supplies the model credentials; the repository describes the project as alpha software under active development.