# agentset-ai/agentset

The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

Repository: https://github.com/agentset-ai/agentset
Canonical: https://ross.abutalabs.com/products/agentset
Homepage: https://agentset.ai
Language: TypeScript
License: MIT
License Family: permissive
Topics: embeddings, rag, ai, agentic-rag, ai-agents, ai-sdk, chatbots, genai, llms, memory, memory-management, vercel-ai-sdk
Last push: 2026-07-16T13:11:34+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 35, longevity 38
- inputs: {"age_days": 541, "days_push": 48, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2075, forks 186 (observed 2026-08-28T04:06:10.705680+00:00)

## What it is
Agentset is an open-source RAG-as-a-service platform that handles document ingestion, chunking, embeddings, retrieval, and agentic search with built-in citations. It ships with TypeScript and Python SDKs, a chat playground, an MCP server, and can run on Agentset Cloud, self-hosted, or on-premise.

## Use cases
- add rag to my app without building the pipeline myself
- parse and index pdfs and other documents for ai search
- build a chatbot that answers questions over my knowledge base with citations
- self-host a rag platform on my own infrastructure
- connect my knowledge base to claude via mcp
- evaluate and benchmark retrieval accuracy before shipping
- ingest 22+ file formats including docx xlsx and pptx

## When to choose
- you want production-grade RAG without hand-tuning chunking, embeddings, and reranking
- you need built-in citations, multi-tenancy, and metadata filtering out of the box
- you want flexible deployment: managed cloud, BYO infrastructure, or on-premise
- you prefer typed SDKs and an OpenAPI spec for integration

## When to avoid
- you need a simple local embedding library rather than a full hosted platform
- your project requires no external service or cloud dependency at all
- you need deep customization of every retrieval stage and would rather assemble your own stack with LangChain or LlamaIndex

## Facets
- artifact type: service
- maturity: active
- function: rag, search-engine, vector-database, llm-inference, mcp, chatbot, etl
- domain: large-language-models, developer-tools
- platform: python, self-hosted, cloud
- tags: rag-as-a-service, embeddings, document-ingestion, citations, agentic-search, multi-tenancy, typescript, openapi, chat-playground, retrieval-augmented-generation, ai-agents, search, nodejs, web-server

## Member repositories
- agentset-ai/agentset (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.705680+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:56:16.309733+00:00, confidence not recorded.
  - readme: https://github.com/agentset-ai/agentset (fetched 2026-08-28T04:06:10.705680+00:00, sha 107a9f2fb45c)
  - homepage: https://agentset.ai (fetched 2026-08-29T10:36:49.003454+00:00, sha 6f27f83c333d)
  - site_page: https://docs.agentset.ai/get-started/introduction (fetched 2026-08-29T10:36:49.012722+00:00, sha 27c9171cffe7)
  - site_page: https://docs.agentset.ai/changelog (fetched 2026-08-29T10:36:49.016879+00:00, sha 23b647866a1c)
  - site_page: https://agentset.ai/about (fetched 2026-08-29T10:36:49.018543+00:00, sha 3b76ef8bcc62)
  - site_page: https://agentset.ai/pricing (fetched 2026-08-29T10:36:49.014749+00:00, sha 3bf6a97ba4e8)
- Data as of 2026-08-30T08:39:29.467469+00:00.