MemoPop AI
Multi-agent investment memo orchestrator.
Turn a company name into an institutional-quality investment memo with 33 specialized AI agents, premium data sources, full citation trails, and firm-specific branded exports.
Why This Exists
Chats with Prompts Won't Make You Great
Asking ChatGPT to "write an investment memo" produces generic, uncited, surface-level output. Real investment memos require structured research from authoritative sources, firm-specific evaluation criteria, and analytical rigor that no single prompt can deliver.
VC Analysis Takes Days
A quality investment memo takes 2-5 days of research, writing, and revision -- time most emerging managers don't have. Most of that work is pulling Crunchbase data, sizing TAM from Statista, cross-referencing team backgrounds, finding relevant charts, sourcing content from experts... tasks AI agents can do in minutes.
Proprietary Thinking Matters
Every fund evaluates deals differently. Hypernova weighs technical defensibility differently than Avalanche weighs market timing. Generic AI can't reflect your IC's actual decision framework. Scorecards and firm-scoped templates make your proprietary criteria the backbone of every memo.
The Pipeline
Not a chatbot. A coordinated pipeline of specialized agents, each producing research analyst artifacts that serve as a source of truth, provide full retraceability, and act as a fallback for future iterations.
Deck or Dataroom Analysis
Thorough dataroom object identification and deconstruction. Pull KPI timelines, key charts, properly identify slide messages, and extract primary source information. Classify 12+ document types with confidence scoring.
Web Research
Multi-query research via Perplexity Sonar Pro with section-specific @source targeting. Crunchbase, PitchBook, Statista, CB Insights.
Outline Loading
Proprietary document structure loaded before writing begins. Guiding questions, vocabulary and phrasing, dos and don'ts -- your firm's voice and analytical framework baked into every section.
Section Writing
Individual sections drafted by specialized writing agents shaped by the loaded outline. Each section processed independently to avoid timeouts.
Multi-Agent Enrichment
Trademark links, social profiles, citations, competitive context. Each enrichment agent works on section files, not assembled content.
Fact Checkers and Source Verifiers
Three-step extract → verify (Perplexity) → correct (Claude) pipeline. Full traceability for every claim.
Scorecard Evaluation
Firm-specific evaluation criteria applied after writing. Team velocity, market timing, defensibility -- whatever your IC actually debates. Scores and flags feed back into revision.
Validation for Iteration and Quality Assurance
Quality scoring against analytical standards. Threshold of 8/10 for auto-finalization. Detailed improvement suggestions below threshold.
Branded, Multi-Format Exports
Branded HTML/PDF in light and dark modes. Firm-scoped configs for colors, fonts, logos. One-pager summaries.
33 Specialized Agents.
A Pipeline, Not a Prompt
One prompt can't write an investment memo. MemoPop orchestrates 33 specialized agents -- deck analyzers, web researchers, section writers, citation enrichers, fact-checkers, scorecard evaluators -- coordinated by LangGraph into a transparent, section-by-section pipeline. Every step produces inspectable artifacts.
Premium Source Targeting.
Perplexity Sonar Pro with @source Intelligence
Every memo section targets the right authoritative sources: @crunchbase for funding data, @pitchbook for valuations, @statista for market sizing, @cbinsights for competitive intel, @linkedin for team profiles. 80-90% authoritative sources, zero SEO spam. Citations are inline, globally renumbered, and consolidated.
Multi-Tenant by Design.
Firm-Scoped Architecture for Private Deal Intelligence
Each VC firm gets isolated configs, branded templates, scorecard criteria, and deal data -- all within a shared open-source codebase. Hypernova's evaluation framework stays separate from Avalanche's. Private data stays private. Branded exports in light and dark modes, HTML and PDF.
Your Criteria, Not Generic AI.
Scorecards That Codify How You Actually Evaluate Deals
Generic AI output lacks firm-specific perspective. Scorecards turn your implicit evaluation criteria into structured YAML templates -- team velocity, market timing, defensibility, capital efficiency -- whatever your partners actually debate in IC meetings. The AI generates analysis that reflects your investment thinking, not boilerplate.
One Command to Start
$ memopop
╭─────────────────────────────────────────────────────────╮
│ │
│ Investment Memo Orchestrator │
│ v0.5.3 · 33 agents · Powered by Claude + Perplexity │
│ │
╰─────────────────────────────────────────────────────────╯
? What would you like to do?
❯ 📝 Generate a new investment memo
📄 Generate a one-pager summary
📤 Export an existing memo (HTML / PDF / Word)
🔧 Improve a specific section
🔄 Integrate content from versions
📊 Run a specific agentNo flags, no file paths. The interactive CLI auto-discovers firms, deals, and versions.
Open Source. Bring Your Own Keys.
MemoPop runs on your machine with your API keys. Claude for analysis and writing, Perplexity Sonar Pro for cited research, or DuckDuckGo as a free fallback. Your deal data stays yours.
Not a GitHub Vibe Coder?
Hit us up. We can turn around a draft same day, sometimes in 10-15 minutes.