railyard-dev/railguard
Safe runtime for Claude Code, built to be yours.
Intercepts Claude Code tool calls with sub-2ms decision-making using OS-level sandboxing (sandbox-exec/bwrap) to detect evasion attempts like encoded commands and piped exploits. Provides granular policy configuration (allowlist/blocklist/ask) across Bash, file operations, and persistent memory, with semantic rules as the first layer and kernel-level resolution as the second. Includes path fencing for sensitive directories, memory tampering detection via content hashing, and session replay for audit trails.
Stars
26
Forks
4
Language
Rust
License
MIT
Category
Last pushed
Mar 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/railyard-dev/railguard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...
ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...
vstorm-co/pydantic-ai-middleware
Middleware layer for Pydantic AI — intercept, transform & guard agent calls with 7 lifecycle...
mattijsmoens/sovereign-shield
AI security framework: tamper-proof action auditing, prompt injection firewall, ethical...
vstorm-co/pydantic-ai-shields
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...