agentset
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
What is agentset?
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
Overview of agentset
What it is
Agentset is an open-source platform for building, evaluating, and shipping production-ready RAG (Retrieval-Augmented Generation) and agentic applications. It provides end-to-end tooling including ingestion, vector indexing, evaluation and benchmarks, a chat playground, hosting, and a developer-friendly API. The platform is built with TypeScript, Next.js, AI SDK, Prisma, Supabase, and Trigger.dev.
Key features
- Turnkey RAG: ingestion, chunking, embeddings, and retrieval
- Model agnostic: works with your choice of LLM, embeddings, and vector database
- Chat playground with message editing and citations
- Production hosting with preview links and custom domains
- API plus typed SDKs and OpenAPI specification
- Built-in multi-tenancy
Use cases
Agentset is designed for developers and teams who need to build and deploy RAG-based applications in production. Use cases include creating document question-answering systems, research assistants, knowledge base chatbots, and any application that requires retrieval-augmented generation with citations and multi-tenant support.
Getting started
To get started with Agentset Cloud, sign up at https://app.agentset.ai/login (free tier with 1,000 pages and 10,000 retrievals, no credit card required). For self-hosting, follow the guide at https://docs.agentset.ai/open-source/prerequisites. For local development:bash# 1) Copy env and fill required valuescp .env.example .env# 2) Install dependenciesbun install# 3) Run database migrations (from the repo root)bun db:deploy# 4) Start the appbun dev:web
License and pricing
The license is MIT. Pricing is open source; Agentset Cloud offers a free tier with 1,000 pages and 10,000 retrievals.
Based on the project's public README and repository metadata.