rohansx/wardn
credential isolation for AI agents. Agents never see real API keys - structural guarantee, not policy.
Integrates with Claude Code, Cursor, and other AI agents via an MCP server on stdio transport, exposing only placeholder tokens through tools like `get_credential_ref` and `list_credentials`. Uses an HTTP proxy (localhost:7777) that transparently swaps placeholders for real AES-256-GCM encrypted keys at the network layer, then strips them from responses before returning to agents. Supports per-agent credential access control, rate limiting, and key rotation while keeping plaintext credentials isolated in a vault locked behind Argon2id derivation.
Stars
26
Forks
2
Language
Rust
License
MIT
Category
Last pushed
Mar 26, 2026
Monthly downloads
22
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/rohansx/wardn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
quantifylabs/aegis-memory
Secure context engineering for AI agents. Content security · integrity verification · trust...
kahalewai/dual-auth
Dual-Auth provides AGBAC dual-subject Authorization for AI Agents and Humans using existing IAM...
The-17/agentsecrets
Zero-knowledge secrets infrastructure built for AI agents to operate, not just consume.
lelu-auth/lelu
The authorization layer for AI Agents
onecli/onecli
Open-source credential vault, give your AI agents access to services without exposing keys.