Le catalogue réel des outils pour IA

Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.

Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.

Epistemic guard for AI coding: tracks uncertain values and blocks writes until verified.

Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization.

Supply-chain guard for AI coding agents: verify packages, check vulns/malware, detect typosquats.

Local-first architecture guardrails and project context for JS/TS AI coding agents.

Local-first PHI detection for source code, LLM prompts, logs, and analytics

Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards.

Git-aware safe file ops for AI agents: delete anything except git-tracked source code.

Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.

Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.

Context intelligence for AI coding agents: navigation, impact, memory, guarded edits.

Trust score for AI-generated code: scan repos, guard agent file writes, get a 0-100 score.

Acoustic deepfake detector and voice biometrics auditor.

Premium agentic endpoint for deepvoice-guard-mcp.

FX protection for SMEs — price Guards, live spot/forward rates, settlement dates, and more.

CDN and edge computing latency monitor analyzing network hops.

Deterministic JSON Schema validation with exact violations and conservative type normalization.

Policy review and purchase discovery for AI-agent commerce actions.

Premium agentic endpoint for agentic-ip-reputation-guard-mcp.