Two AIs argue. One verdict.

Real numbers, not benchmarks. Audison audited httpx v0.28.1 (14,000+ Stars) across 10 security-critical functions using EmpiricalVerifier (AST static analysis — a utility distinct from Audison's multi-model adversarial audit).

¹ _get_client_nonce was an AST false positive (indirect variable assignment untraceable), excluded after manual review. One UNCERTAIN excluded: _build_auth_header same-name ambiguity, a tool limitation, not code uncertainty. Full report →

pip install audison && audison scan .

 Audison Scan — 维度4 数据完整性实证验证
 扫描目录  D:\HANAKO\audison
 发现文件  104 个源文件 / 审查函数  83 个
 CONFIRMED     0  (真阳性)
 REFUTED      43  (假阳性)
 UNCERTAIN    40  (需人工复核)

A single model can't discover its own blind spots. Same training data, same biases — one person grading their own homework. Audison makes two models argue: one audits, another attacks from 5 adversary perspectives, a third cross-validates. Consensus comes from surviving attack, not from agreeing to agree.

Same AI-generated auth code, four reviewers:

Input Code
    │
    ▼
[ Brain One ]  ──── Primary audit (security, correctness, logic)
  (GPT-4o)
    │
    ▼
[ Opponent Brain ] ──── 5 adversarial perspectives attack findings
  (Claude Sonnet)
    │
    ▼
[ Brain Two ]  ──── Cross-verification: consensus → confirmed,
                     disagreement → UNCERTAIN (not hidden)
    │
    ▼
[ TrustReport ]  ──── Verdict + Confidence + Findings + SHA-256 chain

pip install audison
audison scan .              # EmpiricalVerifier: AST static analysis
audison audit .             # Full multi-model adversarial audit

# Set API keys (two providers recommended for cross-arbitration):
export OPENAI_API_KEY="sk-..."
export ANTHROPIC_API_KEY="sk-ant-..."

audison/
├── src/audison/
│   ├── engine/              # TrustEngine — standalone audit layer
│   ├── brains/              # Brain One, Brain Two, Opponent Brain
│   ├── core/                # Caching, context, session management
│   └── utils/               # LLM client (8 providers), token counter
├── tests/unit/              # 186 unit tests
├── reports/                 # Audit reports
├── docs/                    # API, integrations, getting started
├── pyproject.toml
└── LICENSE

Apache License 2.0 — Copyright 2026 盛鑫

AI proposes. AI challenges. You decide.

Try it live: playground.html  |  GitHub Pages

详细文档见 docs/ — API 详解、MCP Server 配置、GitHub Action、LangChain/CrewAI 集成等。