mathematic-inc/earl
Secure CLI proxy for AI agents — HCL-defined operation templates with OS keychain secrets, MCP integration, and prompt injection protection
This tool helps developers and AI agents securely interact with external services. It takes command-line inputs or agent requests and uses predefined, human-written templates to execute operations like querying GitHub or running SQL commands, returning the results safely. It's designed for software engineers building or using AI agents that need to access APIs, databases, or other services without compromising sensitive credentials or risking prompt injection.
105 stars.
Use this if you are a developer building AI agents and need a secure way for them to interact with external APIs or services, ensuring secrets are protected and operations are controlled by human-defined templates.
Not ideal if you are an end-user without programming knowledge, as it requires template creation and CLI usage.
Stars
105
Forks
4
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/mathematic-inc/earl"
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.
stephnangue/warden
An identity-aware egress gateway that replaces cloud credentials with zero-trust access,...
onecli/onecli
Open-source credential vault, give your AI agents access to services without exposing keys.