Flow – A dynamic task engine for building AI agents
I think graph is a wrong abstraction for building AI agents. Just look at how incredibly hard it is to make routing using LangGraph - conditional edges are a mess. I built Laminar Flow to solve a common frustration with traditional workflow engines - the rigid need to predefine all node connections. Instead of static DAGs, Flow uses a dynamic task queue system that lets workflows evolve at runtime. Flow is built on 3 core principles: * Concurrent Execution - Tasks run in parallel automatically * Dynamic Scheduling - Tasks can schedule new tasks at runtime * Smart Dependencies - Tasks can…
Flow – A dynamic task engine for building AI agents launched on December 2, 2024 with 160 votes, #268 of 5,365 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
Flow is a task engine for building AI agents that uses dynamic task queues instead of static graph structures. Rather than requiring predefined connections between nodes, it allows workflows to evolve at runtime through concurrent execution, dynamic task scheduling, and smart dependency management. Tasks run in parallel and can create new tasks or await results from other operations while sharing thread-safe context for state management. The system is designed to simplify complex patterns like map-reduce, streaming, and self-modifying workflows for AI agents that need to make decisions dynamically.
written from the facts on this page · September 2026
From the sources
The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web - lmnr-ai/index
Index Index is a state-of-the-art open-source browser agent that autonomously executes complex web tasks. It turns any website into an accessible API and can be seamlessly integrated with just a few lines of code. prompt: go to ycombinator.com. summarize first 3 companies in the W25 batch and make new spreadsheet in google sheets. pip install lmnr-index ' lmnr[all] ' # Install playwright playwright install chromium Setup model API keys Setup your model API keys in .env file in your project root: GEMINI_API_KEY= ANTHROPIC_API_KEY= OPENAI_API_KEY= # Optional, to trace the agent's actions and record browser session LMNR_PROJECT_API_KEY= Run Index with code import asyncio from index import…from github.com
In the maker’s words, at launch
I think graph is a wrong abstraction for building AI agents. Just look at how incredibly hard it is to make routing using LangGraph - conditional edges are a mess. I built Laminar Flow to solve a common frustration with traditional workflow engines - the rigid need to predefine all node connections. Instead of static…
Does a similar job
all alternatives →
Flow by Laminar [LW24]2024 · github.com · ▲161Open-source dynamic task engine for building AI agents
FlowTask 2.0Jul 2026 · flowtask.work · ▲138For years, I was stuck. Trapped in a loop. Every new project, every team initiative – it began with the same soul-crushing setup. Hours. Gone. Not on the actual work, mind you. But on the meta-work. Defining tasks. Sketching forms. Mapping workflows. Hunting for that 'perfect' template that never quite fit. Just trying to get to zero. To a starting line where meaningful work could actually begin. Most project management tools? They're brilliant once things are up and running. Tracking, collaborating, reporting – they nail it. But that initial blank canvas? That moment you’re staring at an…
Flows – Google Colab meets Notion, designed for AI workflows2025 · app.athina.ai · ▲11Hey HN! Pretty excited to show Flows— something that we’ve been working on for past few weeks! What is Flows? Flows lets you create multi-step AI workflows in minutes by chaining modular blocks like: - LLM calls - API calls, - Code execution - RAG - Document Parsing …and 50+ more tools. Why You'll Love Flows - Test Flows on your datasets—with thousands of rows effortlessly! - Deploy workflows to production and scale your AI applications. - Collaborate with your team or share workflows publicly. Which workflow would you build with Flows? Share your ideas below!
ElevenCreative FlowsMay 2026 · elevenlabs.io · ▲84Node-based creative pipelines, now with real-time collab
20+ Claude Code agents coordinating on real work (open source)Feb 2026 · github.com · ▲53Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
