Agentset
Agentset is an open-source platform for building, evaluating, and shipping production-ready RAG and agentic applications. It provides end-to-end tooling including ingestion, vector indexing, evaluation, chat playground, hosting, and a developer-friendly API. It is for developers who need a turnkey RAG solution with flexibility in choosing LLMs, embeddings, and vector DBs.
✨ Key features
- Turnkey RAG: ingestion, chunking, embeddings, retrieval
- Model agnostic: works with your choice of LLM, embeddings, vector DB
- Chat playground with message editing and citations
- Production hosting with preview links and custom domains
- API + typed SDKs, OpenAPI spec
- Built-in multi-tenancy
🎯 Use cases
- Build a RAG-powered chatbot with custom data
- Evaluate and benchmark retrieval pipelines
- Deploy agentic applications with hosting and custom domains
- Create multi-tenant AI applications
- Prototype and test chat interactions with citations
📦 Installation
🧰 Requirements: Requires Bun runtime for local development; cloud version requires sign-up at app.agentset.ai.
cp .env.example .envbun installbun db:deploybun dev:web🚀 Usage
# Start the web app in development mode
bun dev:web
❓ FAQ
What are the prerequisites for self-hosting Agentset?
The README points to a complete guide at https://docs.agentset.ai/open-source/prerequisites for self-hosting prerequisites.
How do I run database migrations?
Run bun db:deploy from the repo root to apply database migrations.
Can I use Agentset with my own LLM and vector DB?
Yes, Agentset is model agnostic and works with your choice of LLM, embeddings, and vector DB.
Is there a free tier for Agentset Cloud?
Yes, Agentset Cloud offers a generous free tier with 1,000 pages and 10,000 retrievals, no credit card required.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.