HRAG

HRAG

hRAG is a self-hosted hybrid Retrieval-Augmented Generation (RAG) platform that combines Postgres BM25, vector search, and optional cross-encoder reranking to produce grounded, streamed answers with open citations. It targets teams and operators who want reproducible, benchmarked enterprise document search and the ability to run the full stack locally or on modest cloud infra.

HRAG is recruitment & hr software teams evaluate for recruitment & hr. Use this page to review pricing, integration signals, and the best alternatives before you commit.

Paid Enterprise 70/100
#86 in Recruitment & HR (86 tools)
Just launched
Data reviewed Aug 20, 2026

Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.

Review official source →

Quick Overview

Best for: Recruitment & HR

What it does

Recruitment & HR software for decision-makers comparing workflow fit and alternatives.

Best fit

Recruitment & HR

Pricing snapshot

Paid from €116 per month (reported cost for the entire five-node Hetzner cluster described on the site)

Next step

Compare HRAG with similar tools before you shortlist it.

Compare this tool before you shortlist it

Review alternatives, pricing posture, and workflow fit side by side.

HRAG

hRAG (hybrid Retrieval with Receipts) is a self-hosted hybrid RAG platform designed for reproducible, grounded answers over large enterprise-style document corpora. It runs retrieval (BM25) and vector search inside Postgres, supports an optional cross-encoder reranker, and streams answers with open citations so each bracketed source opens to the exact backing chunk. The product is aimed at teams and operators who want to run and reproduce benchmarks, keep data isolated via Postgres row-level security, and deploy the stack on modest infrastructure (the authors report a five-node Hetzner cluster at €116/month). The site provides a public 512K-document playground (no login) and instructions plus MIT-licensed repos to build and run the platform yourself.

Self-hosted hybrid RAG on a €116/month cluster — Postgres, BM25, vectors, a reranker, and a public benchmark score for every claim.

Own this listing?

Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.

Claim this listing for $29

Key Features

BM25 inside Postgres

Uses Postgres text search (pg_textsearch) with real IDF ranking and Block-Max WAND to achieve fast lexical retrieval without maintaining a separate search cluster (88ms over 2M chunks reported).

Hybrid vector + lexical fusion

Combines vector and lexical retrieval with a weightedFusion approach; authors report a 0.3 vector weight produced better results than equal weighting.

Optional cross-encoder reranker

A separate service reads query and chunk together to reorder retrieval windows; reported to improve benchmark score (+3.9) but adds latency (example: ~16 seconds on 2 vCPUs) and ships as an optional checkbox.

Grounded answers and refusal behavior

Empty retrieval results in a refusal without calling the model; on benchmark 'info-not-found' questions the system returns correct refusals where others hallucinate.

Streaming citations

Sources arrive before the first token so every citation bracket in an answer opens to the exact chunk that backs it; streaming of sources is emphasized.

Tenancy via Postgres row-level security

Per-tenant isolation is enforced by Postgres transactions and row-level security so sandbox and benchmark corpora cannot access each other.

Small-model, cost-conscious setup

Advocates for small embedders (118M) and budget answerers to reduce cost; authors publish receipts and per-answer cost claims (tenths of a cent).

Open source & reproducibility

All code MIT; benchmark runs, raw results, and negative results are published in the repo so numbers can be verified.

Pricing

Free Tier Available

Public 512K-document playground available to everyone with no login; private sandboxes require Google or GitHub sign-in and are limited (10 documents, 20 pages each)

Self-hosted five-node cluster (example)

€116 per month (reported cost for the entire five-node Hetzner cluster described on the site)
  • Postgres with vectors and BM25
  • Four services: ingest, embed, rerank, answer
  • Reproducible benchmark score and receipts

Use Cases

Enterprise document search

Search and answer across simulated or real company documents (Slack threads, emails, wikis, tickets) with tenant isolation and grounded citations.

Benchmarking and reproducible evaluation

Run and reproduce EnterpriseRAG-Bench (512K documents) submissions and inspect raw results and receipts to validate retrieval and answer quality.

Self-hosted deployments for cost control

Operators who want predictable, low-cost deployments can run the five-node Hetzner setup or adapt the provided repos to their infrastructure.

Private sandboxing and development

Developers and teams can use private sandboxes (Google/GitHub sign-in) with controlled document and token budgets to test on their own data.

Integrations

Postgres (pg_textsearch + vectors)

Primary storage and retrieval engine for BM25, vectors, text, and tenant row-level security.

Google / GitHub sign-in

Used to create private sandboxes for users who want to test with their own documents.

Hugging Face (leaderboard)

Public leaderboard and benchmark runs are published on Hugging Face (leaderboard referenced on the site).

Benefits

Reproducible, benchmarked retrieval with published receipts and raw results for verification
Low operational cost claims (authors report a five-node Hetzner cluster at €116/month and per-answer costs of tenths of a cent)
Strong data isolation via Postgres row-level security and tenant transactions, plus grounded streamed citations to trace answers to sources

Limitations

Cross-encoder reranker increases latency substantially (example: ~16 seconds on 2 vCPUs) and is therefore optional rather than default
Private sandbox limits: 10 documents of up to 20 pages each and a daily token budget
Site logs visits (IP, browser, country) to understand the audience (details and opt-out guidance in the repo), which may be a privacy consideration

Frequently Asked Questions

What am I actually chatting with?
The public playground is the EnterpriseRAG-Bench corpus of 512,000 simulated company documents (Slack, email, wikis, tickets); what you see on the playground is the exact corpus used for the benchmark.
Can I bring my own documents?
Yes — sign in with Google or GitHub to get a private sandbox (10 documents, 20 pages each) with a daily token budget; row-level security keeps your documents isolated.
How good is it, honestly?
Officially scored #9 on EnterpriseRAG-Bench (overall 44.74) with published per-category numbers and raw results; authors encourage verification by inspecting committed raw runs.
Why should I trust these numbers?
Every run's raw results are committed to the repo and the benchmark team re-scored the submission with near-identical retrieval results (example: recall 69.65 vs 69.6).
Can I run this myself?
Yes — the site provides articles that walk through every deployment step and MIT-licensed repos that build the platform from scratch.

Getting Started

  1. 1 Visit the public 512K-document playground (no login) to try the live system immediately
  2. 2 Sign in with Google or GitHub to create a private sandbox (limited to 10 documents, 20 pages each, daily token budget)
  3. 3 Follow the articles and the MIT-licensed repos which walk through every deployment step and benchmark reproduction to build the platform yourself

Support

docs

Articles on the site walk through deployments and benchmark reproduction step-by-step.

repository

MIT-licensed repos contain the code, benchmarks, raw results, and receipts to build and run the platform.

playground

Public 512K-document playground to test the live system and reproduce benchmark behavior without signing in.

API

Available: No

Compare HRAG with similar tools

See how it stacks up against alternatives

Related Tools

View all 86 →
Contact for pricing
OJCP

OJCP

OJCP (Open Job Context Protocol) is an open standard that defines how AI agents discover, evaluate, and apply to job opportunities via interoperable, privacy-preserving schemas and MCP-native tools, targeted at employers, ATS vendors, job boards, staffing agencies, and agent platforms.

Recruitment & HR
Enterprise-ready High-growth
Freemium
JobEasyApply vs Simplify (2026)

JobEasyApply vs Simplify (2026)

JobEasyApply is a fully autonomous AI job-application copilot that finds LinkedIn Easy Apply jobs, scores them against your resume using vector embeddings, generates unique AI answers to recruiter questions, and submits applications automatically via a Chrome extension.

Recruitment & HR
High-growth
Free
Resumecheck

Resumecheck

Resumecheck is an AI-powered resume improvement platform that analyzes resumes, suggests corrections and rewrites, and generates tailored cover letters and emails to help candidates get more interviews.

Recruitment & HR
Contact for pricing
clado

clado

Clado is an enterprise people-search and profile-enrichment platform (Atlas) that uses massively parallel LLM agents to search and enrich profiles across 800M+ people, providing email and social-profile enrichment for recruiting, sales, and VC workflows.

Recruitment & HR
Enterprise-ready High-growth
Free
Someli

Someli

Someli is an AI-powered employee advocacy and personal branding platform that helps companies scale influence by generating personalized content, managing distribution, and measuring impact to increase reach, engagement, and trust.

Recruitment & HR
Free
Interactive-cv

Interactive-cv

Interactive CV is an AI-powered platform that creates ATS‑optimized, job‑specific resumes, generates personalized cover letters, simulates interviews with real-time feedback, and provides an application tracker and analytics to help candidates and recruiters improve hiring outcomes.

Recruitment & HR
Contact for pricing
Springworks

Springworks

Springworks is an HR software suite for hiring, background verification, and employee engagement that helps companies speed up recruitment, automate verification and improve team engagement across distributed workforces.

Recruitment & HR
Paid
Mockmaster

Mockmaster

Mockmaster is an AI-driven interview practice app that generates tailored mock technical interviews, provides personalized feedback and spaced-repetition study tools to help software engineers prepare for roles across experience levels and top tech companies.

Recruitment & HR

Budget-Friendly Alternatives

Freemium
JobEasyApply vs Simplify (2026)

JobEasyApply vs Simplify (2026)

JobEasyApply is a fully autonomous AI job-application copilot that finds LinkedIn Easy Apply jobs, scores them against your resume using vector embeddings, generates unique AI answers to recruiter questions, and submits applications automatically via a Chrome extension.

Recruitment & HR
High-growth
Free
Wealthwaggle

Wealthwaggle

Wealth Waggle is an AI-driven career platform that provides resume and LinkedIn optimization, AI chat career coaching, mock interview practice, and personalized career planning to help job seekers, career pivoters, students, and professionals increase interview callbacks and visibility.

Recruitment & HR
Free
Workhunty

Workhunty

Work Hunty is a job-application productivity web app that helps job seekers apply faster, generate cover letters with ChatGPT, track application history, and capture jobs via a Chrome extension.

Recruitment & HR
Freemium
saywise

saywise

Saywise is a platform for AI-native builders to showcase projects, publish rich profiles that are readable by humans and AI agents, and get discovered by startups and recruiters seeking AI-native talent.

Recruitment & HR
High-growth
Freemium
Soon

Soon

Soon is an AI-powered employee scheduling platform for operations teams that provides auto-scheduling, intraday management, and demand forecasting to improve coverage, fairness, and compliance.

Recruitment & HR
High-growth
Freemium
Screenz

Screenz

Screenz is an AI-driven hiring platform that runs structured, role-specific candidate interviews, scores applicants against role criteria, and incorporates post-hire check-ins to improve future shortlists and retention. It is built for hiring teams and enterprises seeking faster, more consistent screening and evidence-backed candidate rankings.

Recruitment & HR
Freemium
Rezi

Rezi

Rezi is an AI-powered resume platform that helps job seekers write, tailor, score, and optimize ATS-compatible resumes, cover letters, and interview preparation with templates, keyword targeting, and an AI resume agent.

Recruitment & HR
Freemium
Resumetrick

Resumetrick

Resume Trick is an online resume, CV, and cover letter builder that provides templates, downloadable resumes (PDF/TXT), and AI-assisted writing to help users create job application documents quickly on any device.

Recruitment & HR

Explore Related Categories