8 projects
agent-audit-gateway
An HTTP audit gateway for AI agent tool calls: transport + bearer auth + rate limit in front of a fail-closed audit engine (research prototype / AI-assisted development).
frt-agent-firewall
Fail-closed MCP tool-call firewall with a tamper-evident hash chain. Give your AI agent's MCP tools a local firewall.
agent-route-grid
An audited routing layer for multi-agent teams: zone-based routing policy, workspace isolation, and a hash-chained decision trail (research prototype / AI-assisted development).
agent-mcp-check
One-shot black-box security check for MCP servers. Malformed probes, method-not-found, unknown-tool, fail-closed grading, hash-chained trail.
agent-ctx-guard
Verifiable context compression for agent sessions. Compression is a process; verifiability is the result.
agent-context-clinic
AI session context health check CLI. How close is your agent session to memory loss? Zero-dependency.
agent-audit-cli
Fail-closed audit CLI for AI agent tool calls: adjudicate one request, verify the hash-chained trail (WorkBuddy Connector edition).
agent-call-audit
Dependency-free guardrail layer for agent tool calls with a tamper-evident audit trail