15 open-source alternatives ranked by real activity

Open-source Vellum alternatives

A curated, ranked list of the 15 best open-source alternatives to Vellum.

The best open-source alternative to Vellum is n8n. If that doesn't suit you, other good options are Dify, Langfuse, RAGFlow and Langflow.

Commercial alternatives to Vellum include Braintrust, LangSmith, Portkey and Galileo. See all 17.

Vellum alternatives are mainly AI infrastructure tools, but some are also AI tools and workflow automation tools. 14 of them shipped code in the last 30 days, 15 can be self-hosted, and 10 use a permissive licence.

Last updated November 13, 2026 · ranked by GitHub stars, growth and recent commits

n8n

A fair-code workflow automation platform that mixes a visual canvas with custom code and AI agent features, for teams connecting apps and automating processes.

GitHub stars
210k
Last commit
today
Latest release
n8n@2.47.5
Self-hosted
Yes
Hosted version
Available
n8n.ion8n homepage screenshot

n8n is a workflow automation platform for connecting apps, moving data between them and triggering actions without writing a full integration from scratch. Workflows are built on a visual canvas, and when a step needs more logic you can drop in JavaScript or Python and use npm packages. It is often compared with Zapier and Make, but the source is public and it can run on your own infrastructure.

Recent versions put a lot of weight on AI. You can build multi-step agents and LLM workflows that call OpenAI, Anthropic, Google or open-source models, add human approval steps, and inspect what happened afterward. The project advertises over a thousand integrations and a large library of ready-made workflow templates, and you can extend it with your own nodes.

n8n is distributed under a fair-code model: the Sustainable Use License, plus a separate enterprise license for additional features. The code is always visible and can be self-hosted, for example with Docker, but it is not an OSI-approved open-source license, so commercial redistribution is restricted. A managed cloud edition is available if you would rather not run it yourself.

Key features

  • Visual workflow canvas with branching logic
  • JavaScript and Python code steps with npm packages
  • Multi-step AI agents with human approval
  • Over 1,500 integrations plus reusable templates
  • Connects to OpenAI, Anthropic, Google or local models
  • Role-based access and audit trails
  • Self-hosting with Docker or managed cloud

Pricing: Free self-hosted Community Edition. Hosted plans cost 20€ (Starter), 50€ (Pro) and 667€ (Business) per month billed annually, scaled by workflow executions; Enterprise is custom. Free trial available.

Dify

An LLM application platform for building AI workflows, RAG pipelines and agents on one canvas, deployable in the cloud, a private VPC or self-hosted.

GitHub stars
161k
Last commit
today
Latest release
1.19.0
Self-hosted
Yes
Hosted version
Available
dify.aiDify homepage screenshot

Dify is a platform for building applications on top of large language models. Instead of wiring together prompts, retrieval code and model APIs by hand, teams assemble AI workflows, knowledge pipelines and agents in a shared visual workspace, then move them from prototype to production without changing stacks.

The product covers a workflow studio for agentic flows, a knowledge pipeline that prepares searchable knowledge bases for retrieval-augmented generation, model management across many providers, and a marketplace of tools, models and integrations. Observability integrations such as Opik, Langfuse and Arize Phoenix help trace and debug runs once an app is live.

Dify comes in a few editions: a community edition you deploy yourself with Docker, a hosted cloud service, and an enterprise edition for private deployments. The repository carries a custom license rather than a standard one, so check its terms before offering Dify as a service to others.

Key features

  • Visual workflow studio for agentic apps
  • Knowledge pipelines for retrieval-augmented generation
  • Model management across many LLM providers
  • Marketplace of tools, models and integrations
  • Observability integrations such as Langfuse
  • Deploy on cloud, VPC or Docker

Pricing: Free Sandbox on Dify Cloud and a free self-hosted Community edition. Cloud Professional costs $590 and Team $1590 per workspace per year; Enterprise is custom.

Langfuse

An open-source LLM engineering platform for tracing, evaluating and improving AI applications, with prompt management, datasets and a playground, self-hosted or cloud.

GitHub stars
37k
Last commit
today
Latest release
v4.79.0
Self-hosted
Yes
Hosted version
Available
langfuse.comLangfuse homepage screenshot

Langfuse is an open-source LLM engineering platform that helps teams develop, monitor, evaluate and debug AI applications together. You instrument your app, and Langfuse records traces of LLM calls and surrounding logic such as retrieval, embeddings and agent actions, so complex runs and user sessions can be inspected and debugged.

Prompt management lets you centrally version and iterate on prompts, with caching on server and client so that changes do not add latency to your app. Evaluation features cover LLM-as-a-judge, code evaluators, user feedback, manual labeling and custom pipelines through the API and SDKs. Datasets provide test sets and benchmarks, there is an LLM playground for trying prompts, and integrations exist for OpenAI, LangChain and LlamaIndex. It is built on the ClickHouse database, and the Langfuse team has been part of ClickHouse since January 2026.

You can use Langfuse Cloud or self-host it, which the maintainers say takes minutes. The repository license is listed as 'Other' because it combines open-source and enterprise components, so check the terms. It suits teams shipping production LLM features who need visibility into quality, latency and cost.

Key features

  • Tracing of LLM calls, retrieval and agent actions
  • Prompt versioning with caching
  • LLM-as-a-judge and custom evaluations
  • Datasets for tests and benchmarks
  • Interactive LLM playground
  • Integrations with OpenAI, LangChain and LlamaIndex

Pricing: Core has a $29 monthly base that includes 100k units, then $8 per 100k units with volume discounts. Hobby and Pro tiers exist but their prices are not shown in the text; Enterprise is by sales.

RAGFlow

An open-source retrieval-augmented generation engine that combines document understanding with agent capabilities to give LLMs grounded context.

GitHub stars
94k
Last commit
yesterday
Latest release
v1.0.0
Licence
Apache-2.0
Self-hosted
Yes
Hosted version
Available
ragflow.ioRAGFlow homepage screenshot

RAGFlow is an open-source engine for retrieval-augmented generation (RAG). It combines RAG with agent capabilities to give large language models a context layer built from your own documents, so applications can answer from real data. It is released under the Apache-2.0 license and, per the repository, is currently at a 1.0.0 release candidate.

It extracts knowledge from unstructured documents with complicated formats using deep document understanding, and offers pre-built agent templates. Recent updates mentioned in the README include website ingestion through sitemaps, Google BigQuery data sources with incremental sync, knowledge compilation that generates wikis, graphs, trees and mind maps, and agentic RAG with multiple thinking modes.

You can try the managed cloud service or deploy it locally by following the local deployment guide. The project provides documentation, a roadmap and a Discord community. It suits developers and enterprises building document question answering and knowledge-based assistants who want control over their data pipeline.

Key features

  • Deep document understanding for unstructured files
  • Retrieval-augmented generation workflows
  • Pre-built agent templates
  • Agentic RAG with adjustable thinking modes
  • Website ingestion through sitemaps
  • Knowledge compilation into wikis and graphs
  • Google BigQuery data source sync

Pricing: Free plan with 500 credits per month. Starter shows $59 and Pro $259 per month (a lower unlabeled price of $29 and $129 likely applies with annual billing); Enterprise is quoted and can be deployed on-premises.

Langflow

A visual platform for building and deploying AI agents and workflows, with Python-customizable components and built-in API and MCP server support.

GitHub stars
157k
Last commit
yesterday
Latest release
v1.13.2
Licence
MIT
Self-hosted
Yes
langflow.orgLangflow homepage screenshot

Langflow is an open-source platform for building AI-powered agents and workflows. Developers assemble flows in a visual authoring interface and can then deploy each flow as an API or export it as JSON for use in Python applications. It is written in Python and released under the MIT license.

The visual builder is paired with source-code access, so any component can be customized in Python, and an interactive playground lets you test and refine flows step by step. Langflow can orchestrate several agents with conversation handling and retrieval, works with the major LLMs and vector databases, and can expose flows as an MCP server so they become tools for MCP clients. Observability integrations include LangSmith and LangFuse.

You can install the Python package locally with uv, after which it serves the app at a local address, or use Langflow Desktop for Windows and macOS, which bundles its dependencies. It suits developers and AI teams prototyping retrieval and agent workflows who want both a drag-and-drop canvas and the freedom to write code.

Key features

  • Visual builder for agents and workflows
  • Python source access to customize components
  • Interactive playground for testing flows
  • Multi-agent orchestration with retrieval
  • Deploy flows as APIs or export as JSON
  • MCP server mode exposing flows as tools
  • Observability integrations such as LangFuse

Pricing: Free and open source under the MIT license.

Promptfoo

Open-source CLI and library for evaluating prompts, agents, and RAG apps, and for red-teaming LLM applications to find security weaknesses.

GitHub stars
27k
Last commit
today
Latest release
0.125.1
Licence
MIT
Self-hosted
Yes
promptfoo.devPromptfoo homepage screenshot

Promptfoo is an open-source command-line tool and library for testing applications built on large language models. Developers describe test cases and checks in declarative configuration files, run them against one or more models, and review the results, which replaces manual trial and error with repeatable evaluations. It is written in TypeScript and released under the MIT license.

Beyond quality testing, Promptfoo includes red teaming and vulnerability scanning for AI systems, probing prompts, agents, and retrieval-augmented generation (RAG) pipelines for security and safety weaknesses. It can compare models from providers such as OpenAI, Anthropic, Azure, Bedrock, and Ollama side by side, and it works with any LLM API or programming language. Its documentation also covers a code-scanning feature that reviews pull requests for LLM-related security and compliance issues.

The project is designed to run locally: the maintainers state that evaluations execute on the developer's own machine, so prompts only leave it when a chosen model provider receives them. It can be installed with Homebrew or pip, or run without installing via npx, and it plugs into CI/CD so checks run automatically on each change. The README notes that Promptfoo is now part of OpenAI while remaining open source and MIT licensed.

Key features

  • Declarative test configs for prompts and models
  • Side-by-side comparison of multiple LLM providers
  • Red teaming and vulnerability scanning for AI apps
  • Evaluations run locally on your own machine
  • CI/CD integration for automated checks
  • Pull request code scanning for LLM risks
  • Live reload and result caching
  • Shareable results and security reports

Pricing: The Community edition is free forever. Enterprise and On-Premise plans have custom pricing arranged through a demo or by contacting the vendor.

LlamaIndex

LlamaParse is a document processing platform that converts PDFs, scans, and Office files to markdown or JSON, and extracts structured data.

GitHub stars
53k
Last commit
2 days ago
Latest release
v0.14.25
Licence
MIT
Hosted version
Available
developers.llamaindex.aiLlamaIndex homepage screenshot

LlamaParse is a document processing platform from LlamaIndex. It provides APIs to parse PDFs, scans, and Office files into markdown or JSON, and to extract structured data in a user-defined schema. The platform also includes features for classifying, segmenting, and indexing documents.

It offers SDKs for Python, TypeScript, Go, and Java, and can be accessed via a single API key. The platform includes a web UI for extraction and supports batch processing, polling, and latency management for production use.

Key features

  • Parse converts PDFs, scans, and Office files to markdown or JSON
  • Extract returns JSON in a user-defined schema
  • Classify, Split, and Index cover sorting, segmenting, and retrieval
  • SDKs for Python, TypeScript, Go, and Java
  • Web UI for extraction
  • Supports batch processing, polling, and latency management

Arize Phoenix

Arize Phoenix is an open-source AI observability platform for tracing, evaluating and experimenting with LLM applications.

GitHub stars
12k
Last commit
yesterday
Latest release
@arizeai/phoenix-cli@1.22.0
Self-hosted
Yes
Hosted version
Available

Phoenix is built for experimentation, evaluation and troubleshooting of LLM apps. It traces an application's runtime using OpenTelemetry-based instrumentation, runs LLM-based evaluations of responses and retrieval, and keeps versioned datasets and experiments for comparing changes to prompts, models and retrieval.

Beyond tracing, it has a playground for comparing models and replaying traced calls, prompt management with version control and tagging, PXI, an agent built in for debugging traces, and a remote MCP server so tools such as Claude Code and Cursor can query traces, datasets and experiments. It is vendor and language agnostic, with support for frameworks like LangGraph, CrewAI, LlamaIndex and DSPy and providers such as OpenAI, Anthropic and AWS Bedrock.

Phoenix is open source and self-hosted. Install with pip install arize-phoenix and phoenix serve, run it with uvx, or deploy container images on Docker or Kubernetes through the Helm chart. For a managed platform, Arize sells Arize AX, and the same OpenTelemetry and OpenInference instrumentation works with both.

Key features

  • OpenTelemetry-based tracing of LLM applications
  • LLM-powered evaluation of responses and retrieval
  • Versioned datasets for experiments and fine-tuning
  • Prompt playground with model comparison and trace replay
  • Prompt management with version control and tagging
  • Remote MCP server for coding agents
  • Setup command detects framework and wires up trace export

Sim

A collaborative workspace for building, deploying and monitoring AI agents and workflows, with 1,000+ integrations, built-in tables and knowledge, in cloud or self-hosted form.

GitHub stars
30k
Last commit
today
Latest release
v0.9.54
Licence
Apache-2.0
Self-hosted
Yes
Hosted version
Available
sim.aiSim homepage screenshot

Sim is a workspace for building, deploying and managing AI agents and workflows. You can build visually, conversationally or with code, connect more than a thousand integrations such as Slack, Notion, HubSpot, Salesforce and databases, and use any major LLM provider. The platform includes monitoring of runs, logs, schedules and workflow activity.

Beyond workflows, the same workspace also holds tables, files and knowledge. Tables act as a built-in database, files give the team and every agent one shared store, and knowledge bases serve as the agents' memory, ingesting files and structured data. The workspace is available in the browser and also as a desktop app for macOS 12 and later, for both Apple Silicon and Intel, which can be pointed at a self-hosted deployment.

Sim can be used as a cloud-hosted service at sim.ai or self-hosted, which requires Node.js 20 or newer and Docker. An interactive npx sim-setup wizard creates a deployment directory, provisions the database, generates secrets, writes the environment file and starts the services. The code is Apache-2.0 licensed and written in TypeScript with Next.js.

Key features

  • Visual, conversational and code-based agent building
  • 1,000+ integrations and major LLM support
  • Built-in tables, files and knowledge bases
  • Run, log and schedule monitoring
  • macOS desktop app
  • Interactive self-hosting setup wizard

Pricing: A free plan is available. Pro is $25 and Max $100 per user per month on monthly billing, with about 15% off annually; Enterprise is custom and sold through sales.

Agenta

Agenta is an open-source workspace where teams build, share and run AI agents and automations by chatting with them, with cloud and self-hosted options.

GitHub stars
4.9k
Last commit
today
Latest release
v0.128.12
Self-hosted
Yes
Hosted version
Available
agenta.aiAgenta homepage screenshot

Agenta is an open-source workspace for building and running agents that automate and support work. You create an agent by chatting with it: describe the task, connect the apps it needs and improve it through feedback. Agents can be used directly in chat, shared with teammates and set to run in the background for recurring work.

Repository topics point to agent building, orchestration, observability, MCP and an AI skills manager, as well as workflow automation. The project is written in TypeScript and offers documentation, a website and a managed Agenta Cloud, while the repository also supports self-hosting.

The repository license is shown as 'Other' on GitHub, so check the terms before commercial use. Agenta suits teams that want a shared place to create specialized AI coworkers connected to their existing tools, with a choice between a hosted service and running it on their own infrastructure.

Key features

  • Build agents through chat
  • Share agents with your team
  • Connect agents to work apps
  • Background runs for recurring tasks
  • Agent observability and MCP support
  • Cloud and self-hosted deployment

Pricing: Free Hobby cloud plan and a free self-hosted open-source edition. Pro costs $29 and Business $299 per month with unlimited users and billing based on agent runs; Enterprise is custom.

5 more Vellum alternatives

Commercial Vellum alternatives

Hosted, closed-source products that compete with Vellum. Showing 12 of 17.

See every Vellum alternative on its tool page

Vellum alternatives: questions

What is the best open-source alternative to Vellum?
n8n is the top-ranked open-source alternative to Vellum on Enlisted: A fair-code workflow automation platform that mixes a visual canvas with custom code and AI agent features, for teams connecting apps and automating processes. Other strong options are Dify, Langfuse, RAGFlow and Langflow.
What are the best commercial alternatives to Vellum?
Braintrust, LangSmith, Portkey, Galileo and PromptVault are among the hosted, closed-source alternatives to Vellum listed on Enlisted, which lists 17 in total. Compare their pricing and features on each tool page.
Are these Vellum alternatives free?
All 15 are open source, so the code is free to use under its licence, and all of them can be self-hosted on your own server or computer. 11 also offer a paid or managed cloud version if you'd rather not host it yourself.
How is this list of Vellum alternatives ranked?
By a score built from GitHub stars, star growth over the last 30 days and how recently the code changed. 14 of these projects shipped code in the last 30 days. Data is refreshed daily, and nobody can pay to move up.

People also look for alternatives to…

View all