Make Your Enterprise Knowledge
Agent-Readable

The retrieval infrastructure your teams and AI agents can trust

For builders

Ship retrieval in your product

Free tier. /parse, /extract, /search behind one API key.

# 4 lines to structured Markdown 
curl https://api.lighton.ai/v3/parse \ 
    -H 'Authorization: Bearer $LIGHTON_API_KEY' \ 
    -H 'Content-Type: application/json'\ 
    -D '{"document":"https://console-examples.lighton.ai/AFD-091005-062.pdf"}'

Start for free

Read the docs

FOR REGULATED ORGANIZATIONS

Deploy document intelligence inside your walls

VPC, on-prem, or air-gapped. SecNumCloud-ready. SSO, SCIM, audit logs built in.

Zero outbound calls

VPC / on-prem / air-gap

Per-server pricing

predictable TCO

Native ACL mirroring

Sharepoint, Drive, Confluence

Book a demo

In production at

Three endpoints.
Zero pipeline maintenance.

Parse a document. Extract any field. Retrieve with citations.
The same API key on Console, the same SDK on Enterprise.

LightOnOCR-2.
State-of-the-art parsing.

Turns scans, tables, handwriting, and multi-column layouts into structured Markdown. 20+ languages natively. The parsing engine behind every retrieval workflow.

83.2

OLMOCR-BENCH (SOTA)

€0.002

Per Page

20+

Native language

Open

Weights on HuggingFace

$ curl https://api.lighton.ai/v1/parse \    
    -H 'Authorization: Bearer $LIGHTON_API_KEY' \ 
    -H 'Content-Type: application/json'\ 
    -D '{"document":"https://console-examples.lighton.ai/AFD-091005-062.pdf"}'

Define the schema.
Get JSON back.

Pull any field, entity, or key-value pair you care about. Invoice numbers, lease end dates, claim IDs, contract clauses. You define the schema; LightOn returns structured JSON.

JSON Schema

In / Out

€0.004

Per Page

Async

Via Webhooks

Cited

Per Field

$ curl https://api.lighton.ai/v1/extract \    
    -H 'Authorization: Bearer $LIGHTON_API_KEY' \   
    -H 'Content-Type: application/json' \   
    -d ''{"document":"https://console-examples.lighton.ai/AFD-091005-062.pdf","schema":"<YOUR_JSON_SCHEMA>"}'

Grounded retrieval
with citations.

One query, three signals: dense, sparse, late-interaction. The index picks the right signal, not the developer. Every result ships with the source passage that produced it. Built on LateOn and NextPlaid, our open-source ColBERT family.

Multi-vector

Dense + Sparse + Li

€0.006

Per Query

<200ms

P50 Latency

ACL

At Chunk Level

$ curl https://api.lighton.ai/v1/search \
    -H 'Authorization: Bearer $LIGHTON_API_KEY' \
    -H 'Content-Type: application/json' \
    -d '{"query":"<YOUR_QUERY>"}'

RAG was built for chatbots.
LightOn is built for agents.

Agents do not ask nicely. They dump raw PDFs, garbled tables, and off-domain queries into the same thread. The retrieval layer has to handle the input it gets, not the input you wish you had.

Retrieval

Hybrid retrieval

Dense, lexical, and late-interaction signals on one query. The index picks the right signal, not the developer. Built on LateOn and NextPlaid, our open-source ColBERT family.

Trust

Grounded by default

Every answer ships with the exact passage that supports it. Retrieval and reasoning are separable. Auditable by design, not retrofitted.

Infra

LLM-agnostic

Bring your own model. Open-source, commercial, or private. No lock-in on the inference layer. Your security policy dictates where inference happens.

Protocol

MCP-native

Drop LightOn into any agent that speaks Model Context Protocol. Single agent, multi-agent system, or business application integration. Same API.

Scope

Workspaces and ACLs at chunk level

Multi-agent systems need scoped corpora. Each agent gets its own workspace, its own collections, its own permissions. Access control is enforced at the chunk, not at the document. An agent never sees a single token it should not see.

Imagine the Impact

How much faster could your teams move if they could instantly discover knowledge and surface insights?

Empower your organization to make data-driven decisions, move faster, and stay secure—without ever risking a data leak.

Counterparty Risk Analysis

Surface real financial exposure across subsidiaries and languages in minutes, with every number tied to a source document.

Search hundreds of contracts and purchase orders across entities and languages from a single question.

Separate panic estimates from contractually defensible numbers, backed by clause-level citations.

Confirm what does not exist: zero open commitments returned as evidence, not silence.

Read the story

Multi-Jurisdiction Contract Review

Identify which contracts actually hold up under legal scrutiny across languages, jurisdictions, and amendments.

Review supplier agreements across multiple legal systems and languages in a single query.

Surface clauses that look protective until exclusions or annexes reverse them.

Every conclusion tied to the source clause, with jurisdiction and amendment context.

Read the story

Regulatory Perimeter Mapping

Reconstruct the systems that fall inside a regulatory perimeter when the answer is spread across audits, inventories, and architecture diagrams that no one has reconciled.

Read pentest reports, OT matrices, security policies, and local audits as a single corpus.

Identify assets labeled "non-critical" that support critical operations in practice.

Surface gaps between official inventories and operational reality, with documented sources.

Read the story

Built for search

LightOn supports every modern enterprise search behavior

Chat Search

Conversational Search & Q&A

Users ask questions, not keywords. Switch instantly between retrieving a list of documents or getting a synthesized answer backed by precise, clickable citations.

Massive RAG

Massive Multimodal RAG

Analyze more than just text. The engine ingests millions of files and understands complex formats: images, technical diagrams, tables, and handwritten notes with high precision.

Tool Chaining

Agentic Reasoning Chains

Execute complex tasks, not just search. For multi-step requests (e.g., "Find info + Cross-reference HR + Generate graph"), the AI autonomously chains tools and sources to deliver a complete result.

Team Agents

Custom Specialized Agents

Create dedicated experts for every team. Empower users to build custom agents with specific prompts and restricted document scopes tailored to their role

Data Sync

Universal Data Synchronization

Connect all your knowledge silos. Seamlessly index and sync data from external sources (SharePoint, Drive, Confluence, File Servers). The platform keeps your knowledge base continuously up-to-date.

Access Control

Strict Governance & ACLs

Control exactly who sees what. We mirror native permissions (ACLs) from your sources and organize data into isolated workspaces. You guarantee strict data segregation and compliance across teams.

Deploy with confidence

Ensures strong, reliable security and administrative controls designed to fully protect your company’s most sensitive data

Single sign-on (SSO) with domain management

Role-based access with detailed permission settings

Support for SCIM (System for Cross-domain Identity Management)

Secure hosting confidentiality and integrity of your data

Cost control flat pricing for predictable costs, with flexible plans to adapt to your usage

Support and consulting expert guidance for successful implementation

BUILT ON OPEN RESEARCH

Our retrieval models are in your dependency tree.

Empower developers with a production-ready Multimodal RAG API running on your infrastructure. Integrate secure reasoning into your apps (CRM, ERP) without managing the complex AI stack.

50M

HuggingFace Downloads

916K

PYPI installs per mounth

2,345

GitHub Stars

3,845

HuggingFace Likes

Open-source models in production

LateOn

NextPlaid

PyLate