Flow Run State Machine With Conditional Branching And Dynamic Task Dependencies

Python workflow orchestration — decorators for tasks/flows, retries, caching, scheduling.

Unique: Implements dynamic DAGs via runtime task dependency evaluation, allowing conditional branching without pre-defining all possible execution paths. The state machine is decoupled from task logic, enabling complex workflows without explicit state management code.

vs others: More flexible than Airflow's static DAG model (which requires multiple DAGs for branching) and simpler than Dask's task graph API (which requires explicit graph construction).

via “control flow nodes for conditionals, loops, and branching”

Visual AI programming environment — node editor for designing and debugging agent workflows.

Unique: Treats control flow as first-class graph nodes rather than configuration options, making branching logic visually explicit and debuggable. Supports nested subgraphs within loops and conditionals, enabling complex workflows without flattening to a single graph level.

vs others: More visual and explicit than Langchain's conditional routing (which uses Python logic); more flexible than Promptflow's limited branching (which doesn't support nested loops).

via “conditional routing and branching with dynamic path selection”

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Unique: Implements routing via a dedicated router-executor handler that evaluates conditions in the flow execution context and selects the next step to execute. The router is integrated with the flow DAG model, allowing arbitrary branching patterns while maintaining execution order guarantees. Condition evaluation is lazy — only the selected branch is executed, avoiding unnecessary API calls.

vs others: More intuitive than Zapier's conditional logic (visual router vs nested if/then rules) and simpler than n8n (dedicated router step vs conditional node connections)

via “flow-based workflow with conditional routing and human-in-the-loop decision points”

CrewAI multi-agent collaboration example templates.

Unique: Combines CrewAI Flow framework with explicit human decision points and conditional branching, enabling workflows like Lead Score Flow that route leads to different agents based on score thresholds and require human approval before action. Supports async task execution with state transitions managed through a flow coordinator.

vs others: More human-centric than pure agent orchestration; better suited for business workflows than generic LLM chains because it explicitly models approval gates and conditional routing

via “workflow state machine with agent decision branching”

AgentFlow is a next-generation, premium agentic workflow system built on the Model Context Protocol (MCP). It transforms the way AI agents handle complex development tasks by bridging the gap between raw LLM reasoning and structured execution.

Unique: Combines state machine formalism with LLM-driven decision making by allowing state transitions to be conditioned on LLM outputs rather than just deterministic rules — bridges declarative workflow definition with agent reasoning

vs others: More structured than prompt-based agentic loops (which lack explicit control flow) but more flexible than rigid DAG-based orchestrators (which can't adapt to LLM reasoning)

via “conditional action execution with state-based branching”

Action library for AI Agent

Unique: Integrates conditional branching directly into the agent execution model, allowing agents to adapt execution paths based on runtime conditions without requiring explicit replanning or external workflow orchestration

vs others: More flexible than rigid action sequences but less powerful than full workflow engines (e.g., Airflow, Temporal) and requires manual condition definition rather than automatic inference

via “conditional branching with dynamic path selection”

A durable workflow execution engine for Elixir

Unique: Treats branching as a first-class workflow construct with full persistence and observability, rather than as imperative if/else logic in step functions. Each branch is a separate sub-graph with independent step execution history, enabling fine-grained control flow analysis and debugging.

vs others: More declarative than embedding conditionals in step logic and simpler than Temporal's workflow versioning for conditional behavior. Branch selection is queryable and auditable via database records.

via “conditional task branching and flow control”

Early-stage project for wide range of tasks

Unique: Integrates conditional branching with LLM-based task routing, allowing both explicit conditions and semantic routing decisions to determine execution paths

vs others: More flexible than Airflow DAGs for dynamic branching because conditions can depend on task outputs, but less mature for complex workflow visualization

via “dynamic workflow orchestration”

MCP server: testing-mastra

Unique: Implements a state machine architecture for dynamic workflow management, allowing for real-time adaptation and decision-making.

vs others: More responsive than traditional workflow engines that follow a fixed sequence of operations.

via “contextual task orchestration”

MCP server: clickup-mcp-faster

Unique: Incorporates a state machine design to manage task execution dynamically, allowing for context-aware workflows that adapt in real-time.

vs others: More responsive than static workflow systems, as it can change execution paths based on live data and user interactions.

via “conditional branching and decision logic in workflows”

[Documentation](https://docs.airplane.dev/?utm_source=awesome-ai-agents)

Unique: Provides visual conditional branching with support for complex boolean logic and variable interpolation, allowing non-technical users to define decision trees without writing code

vs others: More intuitive than writing conditional logic in code because the visual builder shows all branches simultaneously, versus code-based approaches where branching logic is scattered across functions

via “conditional workflow branching and decision logic”

Automate technical business workflows

Unique: unknown — insufficient data on whether Manaflow supports visual condition builders, expression languages (e.g., JSONPath, CEL), or advanced pattern matching

vs others: Conditional logic is standard in workflow platforms; differentiation depends on expressiveness and ease of use which are not documented

via “conditional branching and dynamic workflow routing based on agent outputs”

A Multi ai agents builder platform

Unique: Implements visual conditional branching in the workflow graph where edges can be labeled with conditions that evaluate agent outputs at runtime, enabling adaptive multi-agent workflows without explicit branching code

vs others: Provides visual conditional routing where LangChain requires Python if/else statements or custom routing logic, making adaptive workflows accessible to non-programmers

via “conditional branching and dynamic workflow routing”

No-code, automation workflow tool for building Generative AI media applications.

via “task sequencing with conditional logic”

Unique: Provides visual or natural-language-based workflow composition with conditional branching and state management, abstracting away scripting syntax while maintaining expressiveness for complex automation logic

vs others: More accessible than AppleScript or shell scripting for non-technical users, but less powerful than full programming languages for handling edge cases and complex state transformations

via “conditional workflow branching”

via “conditional-logic-branching”

via “conditional-branching-and-routing”

via “conditional branching and decision trees”

via “conditional workflow branching”