RAG

Langchain-Chatchat

RAG · Multi-model (GLM-4, Qwen2, Llama 3, etc. via Xinference/Ollama/LocalAI/FastChat)

7.4

Self-hostable RAG and agent framework that wires LangChain to any local open-source LLM and a knowledge base.

Agentset

RAG · Multi-model (Claude, OpenAI, Google, xAI, Cohere, Mistral, DeepSeek)

7.3

Production-ready RAG infrastructure with agentic search, citations, and model-agnostic plumbing.

Epsilla

RAG · Multi-model

7.3

Agent-as-a-Service platform with managed RAG and a no-code builder for vertical enterprise AI.

Pathway

RAG · Multi-model

7.3

Live data framework for production RAG and streaming ETL pipelines in Python.

Rayyan

RAG

7.3

AI-assisted systematic review platform for screening, deduplicating, and extracting data from large literature corpora.

Cognee

RAG · Multi-model (Claude, OpenAI, others)

7.2

Open-source graph-memory layer that gives AI agents persistent, queryable context across sessions.

Emergent Mind

RAG · Undisclosed

7.2

AI-curated arXiv discovery layer that summarizes frontier papers and aggregates social discussion around them.

FinChat (Fiscal.ai)

RAG · Multi-model (proprietary finance-tuned copilot)

7.2

AI copilot for equity research that reads filings, transcripts, and KPI tables across 100,000+ public companies.

Graphiti

RAG · Multi-model

7.2

Open-source temporal knowledge graph framework for building agent memory that updates in real time.

OneKE

RAG · Multi-model (OneKE-13B, LLaMA3, Qwen2.5, GPT, DeepSeek-R1)

7.2

Open-source multi-agent framework for schema-guided knowledge extraction from documents.

Perplexity AI

RAG · Multi-model (Sonar, GPT-4 class, Claude, Gemini)

7.2

Conversational answer engine that cites its sources by default.

WeKnora

RAG · Multi-model

7.2

Tencent's open-source RAG framework that turns raw documents into a queryable knowledge base, ReAct agent, and self-maintaining wiki.

BGE (BAAI General Embedding)

RAG · BGE / bge-m3 / bge-reranker

7.1

Open-source embedding and reranker models from BAAI that anchor a huge share of production RAG stacks.

Elicit

RAG · Claude Opus 4.5

7.1

AI research assistant that searches, screens, and extracts data from 138M+ academic papers at scale.

FutureHouse Platform

RAG · Multi-model

7.1

Multi-agent AI research stack for scientists, with retrieval over 175M+ papers, patents, and trials.

LangExtract

RAG · Multi-model (Gemini, GPT-4/4o, Ollama-hosted local models)

7.1

Google's open-source Python library for LLM-driven structured extraction from unstructured text, with source-grounded outputs.

OpenDataLoader PDF

RAG

7.1

Open-source PDF parser built for RAG pipelines, with reading-order detection, table extraction, and bounding-box citations.

PostgresML

RAG · Multi-model (Llama, Mistral, open-source embeddings)

7.1

PostgreSQL extension that runs embeddings, vector search, and LLM inference inside your database.

Rivestack

RAG · OpenAI embeddings (auto-embeddings)

7.1

Managed Postgres with pgvector on dedicated NVMe, pitched as a cheaper RAG backend than Pinecone or Supabase.

SiteGPT

RAG · GPT-4 (per testimonials; not publicly specified)

7.1

Custom GPT-powered support chatbots trained on your website content and docs.

SiteSpeakAI

RAG · Multi-model

7.1

Custom-trained chatbot that turns your website, docs, and PDFs into a multilingual support and lead-gen agent.

UltraRAG

RAG · Multi-model (MiniCPM-Embedding-Light, AgentCPM-Report, BYO LLM)

7.1

Low-code, YAML-driven RAG pipeline orchestrator with a visual UI for building and demoing retrieval systems.

alphaXiv

RAG · Multi-model

7.0

AI reading layer over arXiv with grounded Q&A, auto-summaries, and line-by-line discussion on every preprint.

GaliChat

RAG

7.0

No-code AI chatbot builder that trains on your website content for support and lead capture.