AgentLog
cognis-digital/agentlog
Replay & auditoria de agentes IA com OTel GenAI semantic conventions
Ver no GitHubMCP server para replay e auditoria de workflows agentic usando convenções semânticas OpenTelemetry GenAI. Detecta problemas de segurança em agentes e fluxos de IA, exportando achados em múltiplos formatos (tabela, JSON, SARIF, HTML) pronto para integração em pipelines e ferramentas de scanning.
Instalação
npx convez-ai cognis-digital/agentlog1 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
- Auditoria de segurança em workflows com agentes LLM
- Detecção de vazamento de dados sensíveis (PII) em traces de IA
- Integração em pipelines CI/CD para scanning de segurança agentic
- Conformidade e governance de cadeia de suprimento MCP
Veredito

Ferramenta especializada e bem arquitetada para auditoria de segurança em agentes IA, com suporte a múltiplos formatos de saída e integração MCP nativa. Alvo específico para times de security & governance que trabalham com LLMs e workflows agentic em produção.
README
A tradução para o português deste README ainda está na fila.
AGENTLOG — Agentic workflow replay & audit with OTel GenAI semantic conventions
Part of the Cognis Neural Suite by Cognis Digital Cognis Open Collaboration License (COCL) v1.0 · domain:
ai-security
Agentic workflow replay & audit with OTel GenAI semantic conventions.
AI Security & Governance — securing LLMs, agents, and the MCP supply chain.
Why
Security and intelligence teams need agentic workflow replay & audit with OTel GenAI semantic conventions without standing up heavyweight infrastructure. agentlog is single-purpose, scriptable, CI-friendly, and self-hostable: point it at a target, get prioritized findings in the format your workflow already speaks (table, JSON, SARIF, HTML), and wire it into agents over MCP when you want it autonomous.
Install
pip install cognis-agentlog
# or, from this repo:
pip install -e ".[dev]"
Quick start
agentlog --version
agentlog scan demos/ # run against the bundled demo
agentlog scan demos/ --format sarif --out r.sarif --fail-on high
agentlog scan demos/ --format html --out report.html
agentlog mcp # expose as an MCP server (Cognis.Studio / Claude Desktop / Cursor)
Built-in demo scenarios
Each scenario folder includes a SCENARIO.md describing the situation and the findings to expect.
Output formats
- Table (default) — human-readable terminal summary
- JSON — machine-readable findings for pipelines
- SARIF — drops into GitHub code-scanning / IDE problem panes
- HTML — shareable report with severity rollups
How it fits the Cognis Neural Suite
agentlog is one of 52 tools in the Cognis Neural Suite. Every tool ships an MCP server, so Cognis.Studio agents can call them as scoped capabilities.
Sibling tools in ai-security: aegis, promptmirror, ledgermind, adversa, guardpost, hallumark, aicard, biascope, mcpharden, ragshield
Architecture & roadmap
- Design notes:
docs/ARCHITECTURE.md - Planned work:
ROADMAP.md
Contributing
PRs, new detections, and demo scenarios are welcome under the collaboration-pull model. See CONTRIBUTING.md and SECURITY.md.
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.
Responsible use
This is dual-use security software. Use it only against systems, data, and identities you own or are explicitly authorized in writing to test, and in compliance with applicable law.
About
Cognis Digital — Wyoming, USA · Making Tomorrow Better Today: Advanced Cybersecurity, AI Innovation, and Blockchain Expertise.