DeepCheck
cognis-digital/deepcheck
Detector de mídia sintética leve, auto-hospedável e pronto para CI/agentes
Ver no GitHubDetector lightweight de mídia sintética com validação C2PA integrada. Executa análises de integridade de informação — proveniência, detecção de conteúdo sintético e análise narrativa — sem infraestrutura pesada, via MCP ou CLI.
Instalação
npx convez-ai cognis-digital/deepcheck1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Validar autenticidade de imagens e mídia em pipelines CI/CD
- Detectar conteúdo sintético e deepfakes em fluxos de verificação
- Integrar análise de proveniência em agents IA via MCP
Veredito

Ferramenta sólida e focada para detecção de mídia sintética. Excelente para quem precisa validar C2PA e autenticidade em produção, com suporte nativo a MCP e saídas estruturadas (JSON/SARIF) — ideal para automação e CI/CD.
README
A tradução para o português deste README ainda está na fila.
DEEPCHECK
Lightweight synthetic-media detector with C2PA validation
Information Integrity — provenance, synthetic-media, and narrative analysis.
pip install cognis-deepcheck
deepcheck scan . # → prioritized findings in seconds
Contents
- Why deepcheck? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
Why deepcheck?
Lightweight synthetic-media detector with C2PA validation — without standing up heavyweight infrastructure.
deepcheck is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.
Features
- ✅ Extract C2Pa
- ✅ Validate C2Pa
- ✅ Analyze Image
- ✅ Result To Json
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
Quick start
pip install cognis-deepcheck
deepcheck --version
deepcheck scan . # scan current project
deepcheck scan . --format json # machine-readable
deepcheck scan . --fail-on high # CI gate (non-zero exit)
Example
$ deepcheck scan .
[HIGH ] DEE-001 example finding (./src/app.py)
[MEDIUM ] DEE-002 another signal (./config.yaml)
2 findings · risk score 5 · 38ms
Architecture
flowchart LR
A[Input: file / dir / API] --> B[Collectors]
B --> C[Rules / Analyzers]
C --> D[Scorer]
D --> E{Reporters}
E --> F[Table]
E --> G[JSON / SARIF]
E --> H[MCP tool -. drives .-> AI agents]
Use it from any AI stack
deepcheck is interoperable with every popular way of using AI:
- MCP server —
deepcheck mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
deepcheck scan . --format jsoninto any agent or LLM - LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
- CI / scripts — exit codes + SARIF for non-AI pipelines
How it compares
| Cognis deepcheck | contentauth | |
|---|---|---|
| Self-hostable, no account | ✅ | varies |
| Single command, zero config | ✅ | ⚠️ |
| JSON + SARIF for CI | ✅ | varies |
| MCP-native (AI agents) | ✅ | ❌ |
| Polyglot ports (JS/Go/Rust) | ✅ | ❌ |
| Open license | ✅ COCL | varies |
Built in the spirit of contentauth/c2pa-rs, re-framed the Cognis way. Missing a credit? Open a PR.
Integrations
Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (deepcheck mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.
Install — every way, every platform
pip install "git+https://github.com/cognis-digital/deepcheck.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/deepcheck.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/deepcheck.git" # uv
pip install cognis-deepcheck # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/deepcheck:latest --help # Docker
brew install cognis-digital/tap/deepcheck # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/deepcheck/main/install.sh | sh
| Linux | macOS | Windows | Docker | Cloud |
|---|---|---|---|---|
scripts/setup-linux.sh | scripts/setup-macos.sh | scripts/setup-windows.ps1 | docker run ghcr.io/cognis-digital/deepcheck | DEPLOY.md (AWS/Azure/GCP/k8s) |
Related Cognis tools
claimtrace— Misinformation provenance tracer — earliest-known appearance graphelectionlens— Influence-operations pattern monitor for election periodsnarrativediff— News bias & framing diff across 50+ outlets per event
Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 hermes
Contributing
PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.
⭐ If
deepchecksaved you time, star it — it genuinely helps others find it.
License
Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.