Category
Frameworks and runtimes for building, orchestrating, and supervising autonomous agents.
12 products, 9 Projects: 6 open source, 0 source-available, 3 unresolved-license
Visual workflow automation with room to drop into code
n8n sits between a no-code automation builder and a scripting environment. Workflows are assembled on a canvas from several hundred integrations, and any node in that canvas can be replaced with a JavaScript or Python function when the visual version stops being expressive enough.
Turn any website into clean, model-ready data
Firecrawl handles the unglamorous part of feeding the web to a language model: rendering JavaScript, following pagination, stripping navigation and cookie banners, and returning markdown or structured JSON that a model can actually use.
Build and deploy AI agents and RAG pipelines visually
Dify is where a prompt experiment becomes something a team can operate. Workflows are assembled on a canvas, datasets are indexed and versioned, and every deployment gets an API endpoint with logging and cost tracking attached.
Drag-and-drop builder for agents and RAG pipelines
Langflow turns pipeline construction into a graph you can see. Components are Python underneath, so a flow that outgrows the canvas can be exported and run as code rather than rebuilt.
One chat interface for every model you run or connect
Open WebUI is the front end that turns a local inference server into something a household or a team can actually use. It handles accounts, conversation history, document retrieval, and model switching, and speaks to both local runtimes and hosted APIs.
OpenAI's assistant and the interface that set the pattern
ChatGPT is the product that made conversational assistants ordinary. Beyond the chat box it now covers file analysis, image generation, web browsing, voice, and custom assistants sharing one account.
Let AI agents drive a real browser
Browser Use gives an agent a real browser rather than an HTTP client. It handles the translation between a model's intent and DOM actions, keeps a structured representation of the page in context, and recovers from the usual navigation failures.
Autonomous agents that complete real engineering tasks
OpenHands runs agents that plan and execute multi-step engineering work: reading a repository, editing files, running tests, and iterating until a task is done. Each agent works inside a sandboxed runtime rather than on the host machine.
Polished chat interface for many model providers
LobeChat is the most designed of the open chat front ends. Plugins, an assistant marketplace, voice input and output, and vision support are all present, and the interface holds up next to commercial products.
Hosted headless browser infrastructure for agents
Browserbase runs the browsers so you do not have to. Sessions, proxies, captcha handling, and stealth configuration are managed, which removes the least interesting and most fragile part of building anything that scrapes or automates the web.
Anthropic's assistant, strongest on long documents and code
Claude is positioned around careful reasoning over long inputs. The large context window makes whole-repository and long-document work practical in a way that shorter context assistants cannot match.
A control layer for customer-facing AI agents
Parlant addresses the problem that stops most support agents from shipping: a model that is helpful ninety-five percent of the time is not safe to put in front of customers. It manages behaviour through explicit, context-matched guidelines rather than one long prompt.
12 results