The full agentic research engine. Open source. BYOK.
$ git clone https://github.com/aurolabs-ai/aurum.git
$ cd aurum && npm install
$ export OPENAI_API_KEY=sk-...
$ node bin/aurum.js "your question"
Every report runs through the full agentic pipeline. The agent plans, searches reactively, writes, reviews its own work, and delivers a brief with confidence.
Parses your question, identifies domain, selects template, generates targeted search queries.
Executes queries in parallel. Extracts data points with source URLs. Tags every finding with A/B/C source tier.
Maps evidence against planned sections. Identifies coverage gaps, weak areas, missing perspectives.
Generates targeted queries for gaps. Seeks contradicting evidence. 5-20 rounds, reactive to what it finds.
Section-by-section writing using only verified evidence. Every claim traced to its source.
Self-review catches unsourced claims, vague language, repetition. Issues fixed inline.
Adversarial reviewer scores the report on 5 dimensions. Weak sections get new research and rewrite.
One sentence that changes your decision. Confidence on the Sherman Kent scale. The report is the proof.
No hallucinated references. Every data point links back to its origin. Source URLs verified before the report is saved.
Not one blind search pass. The agent searches reactively -- filling gaps, seeking contradictions, pursuing leads it discovers.
Institutional sources (government, academic, wire services) ranked above blogs and SEO content. You see the grade on every source.
An adversarial reviewer scores the report on sources, depth, actionability, rigor, and information density. Threshold: 85+.
One sentence that answers your question. Confidence scored on the intelligence community's probability scale. The 10,000 words are the proof.
You pay OpenAI directly. No subscription. No markup. Most cost is web search calls plus writing tokens. Your keys, your machine.
Each template structures the agent's search strategy, section layout, and source priorities for a specific type of research.
Explores future scenarios with probability assessments. Maps drivers, wildcards, and second-order effects across multiple timelines.
--template scenario-analysis
Market sizing, competitive landscape, regulatory environment, and trend analysis. Institutional data sources prioritized.
--template market-research
Deep competitive analysis: product positioning, pricing, funding, team, technology stack, market share, and strategic trajectory.
--template competitor-audit
Aurum Depth uses deep reasoning models with 170+ sources. Full Director loop, extended search rounds, and multi-model verification. EUR 499 per report via Pro.
Try Pro