Enterprise RAG
The enterprise AI platform for your own data: cited answers, tool-using agents, and visual workflow automation — connect 24+ sources, keep everything behind your firewall, and trace every answer from the exact passage to the permission that allowed it.
Apache-2.0 · runs anywhere, from a laptop to an air-gapped cluster
01Capabilities
Everything between a raw document and a trustworthy answer — built in, not bolted on.
Lexical BM25 written from first principles, dense semantic vectors, reciprocal-rank fusion and a reranking stage — so the right passage wins whether your people search in keywords or in questions.
keyword
semantic
fused + reranked
Access control is evaluated inside every vector and keyword query — never post-filtered, never left to a prompt. What a user can't read can't be retrieved.
Every claim carries a citation. Anti-hallucination modes, a faithfulness self-check, and honest abstention when the corpus doesn't contain the answer.
SharePoint, Confluence, Jira, Slack, GitHub, Google Drive, S3, Azure Blob, GCS, SQL databases and more — on scheduled sync with resumable backfills.
PDFs — including scanned ones via OCR — Office files, images, audio, and YouTube videos: paste a link and the transcript lands in the index with timestamps, so answers cite the exact moment in the video.
Claude, any OpenAI-compatible endpoint, vLLM or Ollama. Or skip the setup: paid plans bundle ERAG-hosted models.
A per-query trace shows retrieval scores, fusion, reranking and the final prompt — exactly why every answer happened.
Golden questions, LLM-judge scoring and concrete tuning recommendations, so retrieval quality is measured — not assumed.
Retention policies, right-to-be-forgotten, PII redaction, audit export to your SIEM, and SCIM user provisioning.
Deduplication, vector quantization, sharded indexes and distributed ingestion keep costs flat as the corpus grows.
02The platform
Turn your governed knowledge into assistants, automations, and insight — all behind your firewall, under your policies.
Configure assistants with a persona and a knowledge scope, then grant them tools — they reason and act: search, run workflows, call external MCP servers, fetch data, send email. Give an agent its own address and your team can just email it.
Build AI automations on a canvas from 35+ typed nodes — triggers, retrieval, models, logic, data, actions and governance. Start them on a schedule, an incoming webhook, an email, or a new document.
Every document auto-tagged at ingest — entities, roles, departments, dates, type — so a document pile becomes a queryable, permissioned knowledge graph you can filter and reason over.
A full conversational surface over any knowledge base, plus a live analytics view of usage, answer quality, cost, and content coverage across your workspace.
Connect agents to external Model Context Protocol servers over HTTP and their tools become available in the reasoning loop — extend the platform without forking it.
Single sign-on (OIDC & SAML 2.0), SCIM provisioning, TOTP multi-factor, encryption at rest for documents and secrets, per-document access control enforced inside retrieval, content moderation, session revocation, a complete audit trail, and data-residency controls.
04Plugins
First-party plugins extend ERAG into full products — powered by the same AI that has read your documents.
Atlas plans a complete project from one sentence, then runs it — standups, risk radar, exec reports, replanning. Scrum, Kanban, Waterfall & hybrid. $49/mo for the whole workspace.
The zero-input CRM: emails log themselves, stages move on cited evidence, silent deals surface in hours, and Cadence ghostwrites the follow-up. $79/mo for the whole workspace.
Describe an internal tool in plain English and the AI builds it — a working app wired to your knowledge bases, CRM, ERP, Projects and workflows. Sandboxed, governed, no code. $39/mo.
More plugins are on the way — each one a full product on the ERAG platform.
03Deployment
One codebase, Apache-2.0 licensed, from first prototype to regulated production.
The zero-dependency dev profile runs with no external services — clone, seed, ask.
Local models via vLLM or Ollama, local storage — nothing leaves the room.
Scale out with sharded indexes and distributed ingestion workers, under your own keys.
04Pricing
One number to think about: how much you index. Unlimited questions, unlimited users.
Estimated monthly cost
$99.50/mo
at $1.99 per GB per month
Includes ERAG-hosted models with 2M AI tokens per GB each month — heavy use continues at $1.50/1M. Or bring your own keys.
Start with 50 GB