3.73K
total weekly downloads
14 packages
agentguard-burn
AgentGuard Burn: see where your Claude Code and Codex tokens went, and stop runaway sub-agents. Runs locally; nothing is uploaded. Short name for @agentguard-run/burn.
@agentguard-run/burn
Local session usage and runaway-agent circuit breaker. Explain tokens, cache rewrites and API list cost, track pace, warn on heavy turns, and gate agent fan-out with signed receipts. Developer command ranking requires explicit --rank.
@agentguard-run/mcp
AgentGuard MCP server: local spend caps, kill-switch style blocking, and Ed25519-signed provenance receipts for AI agent actions. Zero data plane: prompts never pass through this server.
@agentguard-run/spend
AgentGuard spend and license SDK: local policy, spend caps and signed decision receipts for AI agents. The license and seat client behind the AgentGuard plugin for Claude Code, Codex and ChatGPT Work.
@agentguard-run/trace
Signed tamper-evident audit trails and DAG trust chains for AI agent execution. Ed25519 receipts chain across turns and agents. Cannot be altered post-execution, even by the infrastructure operator.
@merchantguard/agentguard-cb
Open-source CE 3.0 evidence SDK for Stripe disputes. MIT licensed. No LLM in the evidence pipeline.
@merchantguard/agent-sdk
Compliance infrastructure for AI agents - GuardScore, 14 vertical coaches, alerts, PSP matching
@merchantguard/dispute-defender
Typed, deterministic helper library for assembling Visa Compelling Evidence 3.0 chargeback-evidence payloads in the shape required by the Stripe Disputes API. Static templates only, no LLM-generated narrative, Ed25519 hash-chained audit log. Ships with a
@merchantguard/guard
The compliance layer for payments & AI agents. One install — GuardScore, 14 AI coaches, alerts, PSP matching, Mystery Shopper, on-chain identity.
@merchantguard/guardbot-skills
Compliance passports for AI agents - OpenClaw skill for GuardBot verification
@merchantguard/guardscan
Security scanner for AI agent skills — 102 patterns, 17 categories, payment/PCI compliance, prompt injection detection. Local by default, no code leaves your machine.
@merchantguard/mystery-shopper
Probe AI agents before you trust them — 10 automated probes for security, reliability, ethics, and efficiency. Independent certification by MerchantGuard.
@merchantguard/probe-handler
Handle all 10 MerchantGuard Mystery Shopper probes with one function. Drop-in /probe endpoint for AI agents seeking Diamond certification.
@merchantguard/sentinela
Conversational Intent Firewall for AI agents. Screen WhatsApp, Telegram, and chat messages for prompt injection, social engineering, and fraud in <10ms.