Is the technology a company claims actually real? DDE reads the codebase to verify technical claims with `file:line` evidence, catches AI-washing with zero false-positive noise, benchmarks against 6 regional markets × 7 charts & a 30-item matrix, and generates a 24-page consulting-grade PDF in 14 languages — all from your IDE.
+ Parallel Atlas 4-Axis (35% Crypto Core)
+ 30-Item × 10-Co. Capability Matrix
With Data Provenance Box & Source Appendix
Runs inside your existing IDE AI subscription
Due Diligence Engine (DDE v0.6.3 / commit 780e3cd & aac4c77, 156-test audited) is an open-source CLI tool that turns the AI agent in your IDE (Claude Code, OpenAI Codex CLI, Google Gemini CLI, Antigravity, GitHub Copilot Agent Mode — supporting Claude Haiku 5.5 → Sonnet 5.5 → Fable 5.1, Gemini 4 Argon, and Astra gpt-6.1-sol / GPT-5) into a principal-level technical due diligence analyst. Beginning with STEP 0 live web research on 2026 competitors, funding rounds, and CVEs, it audits the target codebase with `file:line` evidence, eliminates false-positive Red Flag noise, and outputs a 24-page consulting-grade PDF (in 14 languages) with 7 competitive charts × 6 markets and a 30-item capability matrix (`○/△/×/?`) to `~/Downloads`.
Generic AI code reviewers stop at checkbox compliance ('Has auth? ✓ Has HTTPS? ✓'). DDE inspects actual cryptographic primitives (Signal Protocol, PQXDH + ML-KEM-1024, libsignal/BoringSSL FFI vs. self-rolled crypto), concurrency models, and live 2026 market sources.
Eliminates stale training-cutoff analysis. Before inspecting the repo, the agent searches 2026 competitor acquisitions, shutdowns, funding rounds, CVEs, and regulatory shifts. Every matrix cell carries source URLs + verification dates, surfaced in the PDF Data Provenance Box.
"data_freshness": {
"web_search_performed": true,
"search_date": "2026-10-22",
"queries_executed": 14,
"sources_cited": 28
}In v0.6.2, heuristic false positives (git rebase timestamp diffs, high-velocity commits, documentation buzzword counts) are silently discarded and blocked by _filter_red_flags. Only genuine code-level security gaps, race conditions, and logic bugs with exact file:line and fix plans appear.
{
"severity": "HIGH",
"file_path": "src/crypto/session.rs:142",
"title": "Nonce reuse risk on concurrent retry",
"description": "Use atomic counter or ChaCha20Poly1305 random nonce..."
}Third-party badges (SOC2, ISO, HIPAA) are reference-only and never scored. DDE audits 4 claim-vs-code consistency checks plus 6 code-measured capabilities: Cryptographic depth, Concurrency model, I/O patterns, Caching architecture, Scalability, and ML implementation depth.
Claim vs Code (4): Pitch accuracy / Feature completeness
Code Measured (6): Crypto FFI / Concurrency / I/O / Cache / Scale / MLEvery deck says "AI-powered." Few can prove it. Manual diligence is slow and expensive, while legacy static heuristics drown teams in false positives.
Marketing language exaggerates capabilities the codebase does not support. DDE cross-checks every claim directly against `file:line` implementation evidence.
Reading a codebase, mapping architecture, benchmarking 6 regional markets, and compiling a 24-page PDF takes days of senior engineering time per deal.
An objective 5-dimension rubric (20% each) and Atlas 4-Axis baseline (55% Security) anchor valuation and risk decisions in code evidence rather than founder narrative.
Every report delivers both the balanced 5-Dimension Standard Score (equal 20% weights) and the parallel Atlas 4-Axis Engineering Philosophy (55% weighted toward deep cybersecurity engineering).
API Wrapper vs. Genuine IP
Distinguishes thin third-party API wrappers from defensible proprietary algorithms, protocols, and custom engineering.
Stack Modernity & Cryptographic Edge
Evaluates 2026-grade language safety, runtime efficiency, post-quantum primitives (ML-KEM-1024), and modern toolchain maturity.
PoC Demo vs. Production Grade
Inspects error handling, edge cases, migrations, state machines, and automated test coverage to separate demos from production code.
Structural Integrity + Integrated Security (v0.3)
Evaluates security posture as an inseparable foundation of production architecture alongside modularity, fault isolation, and scalability.
Pitch Deck & Website Claims vs. Code Reality
Cross-examines public marketing claims ('AI-powered', 'E2EE', 'Zero-Knowledge') against actual repository implementation to expose AI-washing.
Strong investment candidate
Viable with conditions
Significant concerns
High risk
Do not invest (or Critical Deal-Breaker)
Generates 7 consulting frameworks across 6 global regions, plus an 8th chart: a ~30-item × 5–10 competitor Implementation Capability Matrix dynamically tailored to the target's industry with 3–5 line competitor selection rationales.
Vision × Execution
Market Growth × Relative Share
Competitive Position × Technical Moat Depth
Security Implementation × Privacy Readiness
Data Protection × Audit Transparency
Downside Risk × Upside Potential
R&D Velocity × ARR Traction (3D Bubble)
Uses the 4-state Japanese tech rating standard (○ / △ / × / ?) with primary source URLs and verification dates on every cell.
Publicly documented & verified in code, whitepapers, or specs
Asserted in marketing, but not independently verifiable
Explicitly absent in documentation or architecture
Cannot be determined from public evidence (preferred over guessing)
| Category / Capability | Target | Comp. A | Comp. B | Comp. C | Provenance (sources + last_verified) |
|---|---|---|---|---|---|
Core Cryptography Hybrid Post-Quantum Key Agreement (PQXDH / ML-KEM-1024) | ○ | ○ | × | △ | [2026-10-22] Verified FIPS 203 ML-KEM-1024 + X25519 FFI implementation |
Metadata Privacy Sealed Sender / Zero-Knowledge Routing | ○ | ○ | × | × | [2026-10-22] Verified sender certificate encapsulation across relays |
Data Governance Cryptographic Message Retirement (Tombstone Zeroize) | ○ | △ | × | ? | [2026-10-22] Verified Ed25519-signed Tombstone & cache zeroization |
Audit Transparency Public Source Code & Automated Security CI | ○ | ○ | × | × | [2026-10-22] Verified public GitHub repository & CodeQL/osv-scanner CI |
* In live PDF reports, the ~30 capability items and 5–10 top competitors are dynamically selected for the target's industry (Messaging, Fintech, Medical, Gaming, SaaS, IoT), with all cited URLs listed in the Source Appendix.
Typeset in black and Atlas Blue (#5271FF), combining executive synthesis, code-level evidence, global market charts, and a cryptographic purge certificate (~22–24 pages depending on findings).
5-dim horizontal bars, 5-dim radar chart, Data Provenance Box (search date, query & source counts, or training-cutoff warning), and business + technical synthesis.
Evidence-backed SWOT grid, per-dimension enablers, 1/3/5-year projections with confidence, immediate/medium/long-term roadmap, and investment thesis.
Genuine code defects only (file:line + fix plan) and the 10-item technical audit (4 claim-vs-code + 6 code-measured).
Regional positioning charts, 3–5 line rationale per competitor (HQ, market position, why chosen), and the ○△×? capability matrix.
Performance / Stability / Lightweight / Security Strength bars plus a plain-language executive glossary (MFA, SOC2, libsignal, PQXDH).
Engineering rebuild time/cost estimation, complete URL Source Appendix (added in v0.6.0), and cryptographic workspace purge certificate.
A repeatable, evidence-first technical assessment — applying the same rubric and source provenance across every deal.
Cross-checks pitch and README claims directly against `file:line` evidence in the codebase to separate real engineering from assertions.
Eliminates legacy heuristic noise (git rebase timestamps, buzzword counts) and flags only real implementation gaps with `file:line` and remediation steps.
Produces a 0–100 score and A–F grade across 5 equally weighted dimensions (20% each), alongside the Atlas 4-Axis philosophy (55% Security across 5 layers).
Generates 7 competitive chart types across 6 regional markets (Global, US, EMEA, Japan, SEA, LATAM) plus a 30-item capability matrix (`○/△/×/?`).
Executes STEP 0 live web research for 2026 competitors, funding rounds, CVEs, and regulations before reading code, attaching source URLs and `last_verified` dates.
Hardened with 156 passing tests (`780e3cd` / `aac4c77`, all 36 audit defects eradicated): SecureLoader (Zip Slip/Symlink/FIFO block + in-place 3-pass shred), `ip.is_global` + DNS rebinding pinning (`_pinned_dns_context`), XML sanitization, and Zero-Drift SSOT invariants.
DDE itself operates zero third-party servers and zero telemetry. Choose the exact execution boundary that matches your security policy.
$ dde prompt --pdfDDE locally generates a structured prompt. Code reading and PDF generation happen inside your existing IDE AI agent session (Claude Code, Codex, Gemini CLI, Antigravity, Copilot, Cursor).
DDE makes zero outbound calls. Your AI agent runs STEP 0 live web searches for public competitor & CVE data.
$ dde analyze . --skip-aiSource code is analyzed 100% locally in memory/temp workspace and never sent to any AI model or external service.
In v0.6.3 (780e3cd / aac4c77), --skip-ai strictly disables API key auto-loading and blocks all outbound network requests.
$ dde analyze owner/repoUses your own API keys to cross-verify across up to 3 providers via the unified SSOT registry (BYOK_DEFAULT_MODELS / PROVIDER_MODEL_COSTS): Anthropic (Claude Haiku 5.5 → Sonnet 5.5 → Fable 5.1), Google (Gemini 4 Argon), and OpenAI (Astra gpt-6.1-sol / GPT-5).
Configured for zero-retention API endpoints (store=False, with fail-closed enforcement on GoogleProvider). Strips user:token@ credentials from GitHub URLs and immediately dereferences PATs after single in-memory use.
Eradicated all 36 audit defects across 35+ modules with GPT-6-Astra (xhigh) & Gemini 4 Argon, unified the SSOT model/cost registry, and locked permanent verification with 156 automated tests (tests/test_audit_regressions.py + tests/test_zero_drift_invariants.py).
Blocks Zip Slip traversal, symlinks, and FIFO special files during archive ingestion, and strips user:token@ credentials from GitHub URLs. Preserves .git during analysis for commit forensics, then performs in-place "r+b" 3-pass zero-fill shredding with strict os.walk(onerror=...) failure propagation and Windows NTFS user-only ACL locking.
Site verification (site_analyzer.py) enforces ip.is_global to block RFC 6598 CGNAT (100.64.0.0/10), private, loopback, and cloud metadata IPs as well as unsafe redirects, using reentrant DNS pinning (_pinned_dns_context) to prevent time-of-check to time-of-use (TOCTOU) DNS rebinding attacks.
Applies _esc_text across all dynamic PDF fields (ImplementationMatrix, sources, RedFlags) to prevent ReportLab XML parser crashes. Protects Latin digits and ASCII punctuation with Helvetica in Arabic (ar) and Thai (th) to prevent missing-glyph tofu boxes (□) across 24-page PDFs, enforces Jinja2 autoescape=True, and guarantees idempotent Score.compute().
Unifies __version__, BYOK_DEFAULT_MODELS, and PROVIDER_MODEL_COSTS (Astra gpt-6.1-sol $2/$10, gpt-6-astra $5/$25, gpt-5 $1.25/$10, Haiku >100k tiered rate) in config.py SSOT. Enforces fail-closed store=False on GoogleProvider, supports async def AST analysis, and locks 156 CI tests via test_zero_drift_invariants.py.
DDE generates a structured audit prompt that any file-reading, shell-running AI agent can execute. No DDE-specific plugin or account required.
Install from the public repository with a single pip command and run `dde doctor` to verify your Python environment and AI CLI tools.
Run `dde prompt --pdf --lang en` in your AI IDE terminal against a local repo or public URL. Your existing AI subscription runs the audit at zero extra cost.
In STEP 0, the agent researches 2026 competitors, funding, and CVEs live on the web, then audits the codebase across the 5-dimension rubric and 30-item matrix.
A 24-page consulting-grade PDF in 14 languages lands in `~/Downloads` — complete with 0–100 score, A–F grade, 7 charts, and sourced rationales.
New in v0.6.3: paste Method A directly into your AI agent chat for fully automated install + audit + PDF generation, or run Method B in your terminal. Bundled Noto fonts render 14 PDF languages out of the box.
✓ Your current locale is natively supported for localized PDF output (14 languages).
Install https://github.com/Atlas-Associates-Inc/Due-diligence-engine (python3 -m pip install -U --no-cache-dir git+https://github.com/Atlas-Associates-Inc/Due-diligence-engine.git), run dde prompt --pdf on this project, and execute the entire generated prompt (STEP 0 live web research, full code audit, JSON generation, and PDF rendering) end-to-end to save the consulting PDF report to ~/Downloads/.python3 -m pip install -U --no-cache-dir git+https://github.com/Atlas-Associates-Inc/Due-diligence-engine.git && dde prompt --pdfdde doctordde prompt --pdf --url https://example.comWorks out of the box in any AI agent capable of reading files and running shell commands.
Boutique consulting depth with local-first privacy at zero added software cost.
| Dimension | DDE (v0.6.3) | Manual DD Consulting | Generic AI Code Review | SaaS DD Platforms |
|---|---|---|---|---|
| Added Cost | $0 (uses your IDE AI) | $$$$ (consultant fees) | Per-token API fees | $$$$ (enterprise subscription) |
| Code Privacy | Local / IDE sandbox (0 DDE servers) | Manual NDA & repo sharing | Uploads code to vendor | Stores code in vendor cloud |
| Deliverable | 24-page consulting PDF (14 langs) | Bespoke report | Inline PR comments | Web dashboard |
| Data Freshness | Live web search (2026) + URLs | Depends on analyst | Training cutoff only (stale) | Vendor refresh cycle |
| Crypto & Security Depth | PQXDH / ML-KEM-1024 / FFI audit | Depends on consultant | Surface checklist | Surface checklist |
| Competitive Benchmarks | 7 charts × 6 markets + 30-item matrix | Manual research (weeks) | None | Limited |
| Red Flag Precision | Code-verified only (file:line + fix) | High (slow) | High false-positive noise | Heuristic rule noise |
| Setup & Turnaround | 1 command / ~10–20 min | 2–4 weeks | Minutes (partial) | Days (onboarding) |
Whether you're making an investment call, taking an objective look at your own engineering, or benchmarking competitors — evidence from the code, fast.
VCs, growth funds, and M&A teams: screen technical risk and the truth behind the claims across your whole pipeline before a deep dive.
Run DDE on your own codebase to see strengths, weaknesses, and technical debt through a third-party lens — to prioritize fixes or prepare for a raise.
Benchmark competitors' tech stack and implementation depth from public repos and market data, and understand your own position with evidence.
Yes. DDE (v0.6.3) is open source under the Apache 2.0 license. In the recommended `dde prompt` mode, it uses the AI subscription you already have in your IDE (Claude Code, Codex CLI, Gemini CLI, Antigravity, GitHub Copilot Agent Mode), so there is no API key setup and no extra cost.
DDE has zero proprietary servers and zero telemetry. Data boundaries depend on the 3 execution modes: (1) `dde scan --skip-ai` is 100% air-gapped offline with zero network calls; (2) `dde prompt` runs inside your IDE's AI sandbox and performs live web searches only for public competitor, funding, and CVE data; (3) `dde scan` (BYOK) sends up to 50 files directly to your chosen provider API. On exit, SecureLoader zero-overwrites temporary files.
Any agent that can read files and run shell commands. It is verified with Claude Code, OpenAI Codex CLI, Google Gemini CLI, Antigravity, and GitHub Copilot Agent Mode (supporting Claude Fable 5.1 / Sonnet 5.5 / Haiku 5.5, Gemini 4 Argon via `google-genai>=2.30.1` Interactions API, and OpenAI Astra `gpt-6.1-sol` / GPT-5), and also works with Cursor, Windsurf, and Aider.
A 24-page consulting-grade PDF in 14 languages (`--lang en|ja|es|fr|de|pt|nl|it|id|zh|ko|vi|th|ar`) saved to your Downloads folder, featuring an overall 0–100 score, letter grade (A–F), 7 competitive charts across 6 regional markets, a 30-item implementation capability matrix (`○/△/×/?` with source URLs and `last_verified` dates), and zero-false-positive Red Flags (`file:line` + remediation).
AI-washing is marketing a product as proprietary AI when the codebase is only a thin API wrapper or hardcoded heuristic. DDE cross-checks pitch and README claims directly against AST, crypto, inference pipelines, and tests — eliminating noisy metadata heuristics so every flag points to real code evidence.
Install once, run from any AI IDE, and verify the code and source evidence for yourself. Free and open source (Apache 2.0).