Checkpoint-AI
cognis-digital/checkpoint-ai
Auto-avaliação NIST/EU AI Act/ISO 42001 sem infraestrutura pesada
Ver no GitHubMCP server para auto-avaliação e geração de SSP (System Security Plan) conforme NIST AI RMF, EU AI Act e ISO 42001. Ferramenta leve, self-hostable e pronta para CI/CD que classifica risco, avalia conformidade e produz relatórios em múltiplos formatos (tabela, JSON, SARIF).
Instalação
npx convez-ai cognis-digital/checkpoint-ai1 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
- Avaliar conformidade de projetos IA contra frameworks regulatórios federais
- Gerar SSP e documentos de compliance automaticamente
- Integrar verificações de conformidade em pipelines CI/CD
Veredito

Ferramenta especializada e bem-estruturada para compliance em IA, com suporte nativo a MCP e outputs prontos para automação. Ideal para equipes em contexto federal/regulado que precisam de avaliação rápida e repetível sem overhead operacional.
README
A tradução para o português deste README ainda está na fila.
CHECKPOINT-AI
NIST AI RMF / EU AI Act / ISO 42001 self-assessment & SSP generator
Federal / Compliance — NIST, CMMC, FedRAMP, and SBIR/GSA workflows.
pip install cognis-checkpoint-ai
checkpoint-ai scan . # → prioritized findings in seconds
Contents
- Why checkpoint-ai? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
Why checkpoint-ai?
NIST AI RMF / EU AI Act / ISO 42001 self-assessment & SSP generator — without standing up heavyweight infrastructure.
checkpoint-ai 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
- ✅ Classify Eu Risk Tier
- ✅ Assess
- ✅ Load Assessment
- ✅ Load Assessment Dict
- ✅ Generate Ssp
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
Quick start
pip install cognis-checkpoint-ai
checkpoint-ai --version
checkpoint-ai scan . # scan current project
checkpoint-ai scan . --format json # machine-readable
checkpoint-ai scan . --fail-on high # CI gate (non-zero exit)
Example
$ checkpoint-ai scan .
[HIGH ] CHE-001 example finding (./src/app.py)
[MEDIUM ] CHE-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
checkpoint-ai is interoperable with every popular way of using AI:
- MCP server —
checkpoint-ai mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
checkpoint-ai 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 checkpoint-ai | usnistgov | |
|---|---|---|
| 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 usnistgov/OSCAL, 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 (checkpoint-ai 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/checkpoint-ai.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/checkpoint-ai.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/checkpoint-ai.git" # uv
pip install cognis-checkpoint-ai # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/checkpoint-ai:latest --help # Docker
brew install cognis-digital/tap/checkpoint-ai # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/checkpoint-ai/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/checkpoint-ai | DEPLOY.md (AWS/Azure/GCP/k8s) |
Related Cognis tools
cmmcmap— CMMC Level 2 practice mapper — stack-aware SSP skeleton generatorfedramplens— FedRAMP boundary visualizer & OSCAL-format SSP/POAM generatorsbirscout— SBIR/STTR topic discovery — DSIP + SBIR.gov + NIH digest with bid scoringgsafinder— GSA Schedule opportunity surveyor — SAM.gov + eBuy + FedConnectclearancepath— Personnel clearance hygiene tracker — SF-86, SEAD-3/4, training currency
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
checkpoint-aisaved 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.