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

Usage — step by step

1. Install the CLI (Python 3.9+):

   pip install deepcheck      # or: pip install .   from a checkout

2. Inspect an image — the inspect subcommand runs synthetic-media + C2PA analysis on a JPEG/PNG:

   deepcheck inspect photo.jpg

   The default table view prints the verdict, a synthetic_score (0=authentic .. 1=synthetic), C2PA provenance, and weighted signals.

3. Emit machine-readable output for tooling:

   deepcheck inspect photo.jpg --format json > report.json

4. Read the result via the exit code: 0 = analysis ran and verdict is likely-authentic, 1 = a finding (suspicious / likely-synthetic), 2 = usage/IO error. Parse the JSON for the verdict and synthetic_score fields, e.g. jq .verdict report.json.

5. Gate a media-intake pipeline in CI — fail the job when an asset is flagged:

   deepcheck inspect uploaded.png --format json || echo "deepcheck flagged uploaded.png"

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.

↑ back to top

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/)

↑ back to top

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)

↑ back to top

Example

$ deepcheck scan .
  [HIGH    ] DEE-001  example finding             (./src/app.py)
  [MEDIUM  ] DEE-002  another signal              (./config.yaml)

  2 findings · risk score 5 · 38ms

↑ back to top

Architecture

flowchart LR
  IN[input] --> P[deepcheck<br/>analyze + score]
  P --> OUT[report]

Loading

↑ back to top

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 json into 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

↑ back to top

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.

↑ back to top

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.

↑ back to top

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)

↑ back to top

Related Cognis tools

• claimtrace — Misinformation provenance tracer — earliest-known appearance graph
• electionlens — Influence-operations pattern monitor for election periods
• narrativediff — News bias & framing diff across 50+ outlets per event

Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 engram

↑ back to top

Contributing

PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.

⭐ If deepcheck saved 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.

---

_{Cognis Digital · one of 170+ tools in the Cognis Neural Suite · Making Tomorrow Better Today}