langflow-ai/langflow
Langflow is a powerful open-source platform for building, testing, and deploying AI-powered agents and workflows with visual authoring, multi-agent orchestration, and API integration capabilities.
Awesome AI Agents › AI Workflow Orchestrators
Pixelagent is a comprehensive framework designed for building multimodal stateful agents that integrate large language models (LLMs) with data orchestration, storage, and orchestration capabilities. It is built on top of Pixeltable's data infrastructure, providing a unified declarative interface that allows engineers to create custom agentic applications with flexible memory, tool-calling, and other functionalities. The framework supports native multimodal inputs including text, images, audio, and video, making it versatile for various applications. Pixelagent is model-agnostic and extensible to multiple AI providers such as Anthropic, OpenAI, and AWS Bedrock, allowing users to connect different blueprints to these providers seamlessly. It offers plug-and-play extensions for adding custom tools, implementing long-term memory with semantic search, enabling self-improvement through reflection loops, and incorporating reasoning and planning capabilities. The framework also supports multimodal agentic retrieval augmented generation (RAG). The system is designed with observability in mind, providing complete traceability through automatic logging of messages, tool calls, and performance metrics. Users can transform their agent blueprints into distributable packages on PyPI, facilitating deployment and sharing. The framework includes detailed documentation, API references, and example use cases to help users get started and explore advanced patterns. Pixelagent's declarative model is type-safe and implemented in Python, supporting versions 3.10 through 3.13 across Linux, macOS, and Windows platforms. It enables state management by persisting agent memory and tool call history in tables, allowing for customizable memory databases. The framework encourages building sophisticated agentic strategies such as the ReAct pattern for step-by-step reasoning and planning. Overall, Pixelagent serves as a powerful blueprint for agent engineering, combining LLMs, storage, and orchestration into a single framework that supports multimodal inputs, extensibility, observability, and advanced agentic workflows.
https://github.com/pixeltable/pixelagent
Langflow is a powerful open-source platform for building, testing, and deploying AI-powered agents and workflows with visual authoring, multi-agent orchestration, and API integration capabilities.
Orca is an AI Orchestrator that provides an integrated development environment for running and managing parallel AI agents across various platforms, including desktop and mobile.
OpenMontage is an open-source, agentic video production system that transforms AI coding assistants into full video studios for automated video creation from text prompts.
DSPy is a framework that enables programming language models with compositional Python code to build modular AI systems and optimize their performance beyond traditional prompting methods.
Kestra is an open-source, event-driven orchestration platform for data, AI, and infrastructure workflows, enabling declarative and code-based automation with a rich plugin ecosystem.
12 Factor Agents is a comprehensive framework outlining principles for building reliable, scalable, and production-ready LLM-powered AI software agents.
BabyAGI is an experimental framework for building self-building autonomous agents using a function-centric approach with comprehensive management, logging, and a dashboard interface.
Teable is an AI spreadsheet platform that integrates data management, AI workflows, and app building on a PostgreSQL backend, enabling users to create custom business applications.