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
apache/flink-agents
Apache Flink Agents is an agent framework developed inside the Apache Flink project that places language model agents on top of a stream processing engine. Instead of an agent being a request-response service invoked by a user, an agent here is a long running, event-driven job that consumes records from a data stream, reacts to each event, keeps state between events and emits results downstream, so the properties Flink already provides, meaning distributed execution, exactly once processing, checkpointing, state management and recovery after failure, apply to the agent as well. That makes it suited to real-time use cases such as monitoring, alerting, enrichment and decision making over continuous data, where an agent must react within a stream rather than be called from an application. The project is a joint Java and Python codebase: the Java side implements the runtime and integrates with the Flink APIs, while a Python package wraps the distribution jar so agents can also be authored in Python, and the build script in the tools directory produces both parts and installs the jar into the Python wheel. Building from source requires a Unix-like environment, Git, Maven, Java 11 or newer and Python 3.10 to 3.12. User documentation is published on the Apache Flink nightly documentation site. Development follows normal Apache project practice, with contribution guidelines in the repository, discussion on the Apache Flink Slack workspace in dedicated user and developer channels, and a weekly community sync whose agenda and past records are kept in GitHub Discussions. The audience is data platform and streaming teams that already run Flink and want to add agentic reasoning to existing pipelines without introducing a separate orchestration system, and engineers who need agent workloads to scale and recover like other production streaming jobs.
https://github.com/apache/flink-agents
Also in AI Workflow Orchestrators
stablyai/orca
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.
calesthio/OpenMontage
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.
stanfordnlp/dspy
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-io/kestra
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.
humanlayer/12-factor-agents
12 Factor Agents is a comprehensive framework outlining principles for building reliable, scalable, and production-ready LLM-powered AI software agents.
yoheinakajima/babyagi
BabyAGI is an experimental framework for building self-building autonomous agents using a function-centric approach with comprehensive management, logging, and a dashboard interface.
teableio/teable
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.