acilox · Deewakar 0 open-source reference implementations

The systems behind AI-native products,
built end-to-end.

Open-source reference implementations of the systems modern products actually run on — AI-native marketplaces, agent copilots, enterprise integrations, and data platforms. Deployable, real, small enough to read end-to-end.

0
Production reference implementations
0
Practice areas, from AI products to data
MIT
Open source, fork & deploy
5+
From idea to shipped production

16 production references — one per pattern that matters

Every repository below is a working reference implementation of a pattern that actually ships — small enough to read end-to-end, complete enough to deploy with real credentials. Open the case studies to see the architecture, the engineering decisions, and the trade-offs.

🤖 AI Copilots & Automations 8 repos

🧾

Invoice Intelligence Hub New

Self-hosted EMEA accounts-payable automation that replaces $100K/yr SaaS. Ingest → extract → rules → AI confidence → human review → 27-country VAT → BI, in one auditable transaction.

LLM (Llama)HITLEMEA VATUBL / PEPPOLFastAPI
📄

Vendor & Contract Intelligence Hub

Vendor and contract documents into structured, evidenced, risk-scored decisions. Replaces $100K/yr SaaS (Vendr, Ironclad) with a self-hosted policy engine, human-in-the-loop queue, and immutable audit log.

LLMPDF/DOCXPolicy EngineHITLFastAPI
🛰️

Implementation Intelligence Hub New

Autonomous agent that reads every onboarding signal — Slack, Jira, email, calls, docs, CRM — and produces evidence-cited briefs, calibrated slip-risk forecasts, and review-ready customer emails. Catches slips before they happen, with every claim grounded in a verifiable source.

Custom Agent LoopMulti-modal RAGEvidence-CitedSlip ForecastingHITL + Audit
🛡️

Vigil New

AML alert-triage and SAR-drafting agent that scores every alert on a continuous suspicion scale, cites each typology claim to the exact transaction behind it, and drafts a regulator-ready SAR — clearing false positives while never letting a true positive slip. The agent proposes; a compliance officer disposes and files.

Continuous Suspicion ScoreTypology DetectionEvidence-CitedRecall-Protected (FN = 0)Officer-Filed SAR
🛎️

Frontline New

AI front-desk for the trades that turns an inbound call or text into a booked, dispatched job — triaging the problem, quoting a transparent price band from the business's own price book, and assigning the nearest qualified tech by an explainable scorer, with a non-skippable safety-escalation branch that never mistakes a gasket for a gas leak.

Whole-Word Safety TriageCited Price BandsExplainable DispatchTyped ServiceScopeHITL Owner-Ping
🛍️

Aftercare New

Post-purchase resolution agent that reads an inbound "where's my order / this arrived cracked / I want a refund", pulls the real order and carrier facts, cites the governing policy clause, and resolves the case end-to-end — tracking answer, exchange, carrier claim, save-the-sale offer, or refund — with a scored return-abuse guardrail and a human gate on anything that moves money.

Intent + Facts FirstEvidence-Cited DecisionsScored Abuse GuardrailSave-the-SaleTyped CaseScope
⚖️

Casewise New

Legal client-intake and matter-triage agent that qualifies a lead, runs a recall-first conflict check, tracks the statute-of-limitations clock from a content-hashed rule pack, and books or routes the matter — with every outbound gated on a TCPA consent ledger so the firm never contacts anyone without provable permission.

Recall-First Conflict CheckTCPA Consent LedgerContent-Hashed SOL ClockCited Tier ScoringTyped MatterScope
🩺

Authora New

Healthcare prior-authorization agent that de-identifies the chart, decomposes the payer's own policy into criteria, judges each one met / unmet / unknown against cited clinical evidence, and assembles a submission-ready packet — predicting approval probability on a calibrated scale, drafting the appeal when a denial is overturnable, and gating everything behind a clinician attestation.

Safe-Harbor De-identificationCriteria DecompositionEvidence-Cited (no uncited "met")Calibrated Approval ProbabilityTyped AuthScope

Core focus areas

The kinds of problems these systems are built to solve — across AI products, integrations, automation, and data.

Open source, end to end.

Every repository is MIT-licensed — fork it, lift the patterns, and ship it in your stack. The case studies above walk through the architecture and the decisions; the code is all on GitHub.