Security●●●Banger
OnGarde – Runtime content security proxy for self-hosted AI agents
Transparent proxy blocks agent leaks to LLM APIs without touching agent code.
Solve My ProblemSlick
antimaterial
213mo ago
Back to browse
GitHub Repository
Open Source Reliability Harness: Make your agents follow rules. One line of code to enforce, trace, and improve.
123 starsPython
Open Bias – proxy that enforces agent behavior at runtime
by algomaniac·Apr 28, 2026·21 points·4 comments
AI Analysis
●●SolidSolve My ProblemShip It
Local proxy enforcing markdown rules on LLM output before it hits production.
Strengths
- •Zero-config setup with automatic rule synthesis from a simple RULES.md file.
- •Works with any LLM provider by acting as a standard OpenAI-compatible proxy.
- •Intervenes on off-policy behavior like discount limits before user sees it.
Weaknesses
- •Proxy pattern adds a network hop compared to native provider guardrails.
- •Rule enforcement relies on a secondary evaluator model which adds cost.
Category
Target Audience
Developers deploying AI agents in production environments
Similar To
Guardrails AI · LLM Guard · Portkey
Similar Projects
Security●●Solid
Burrow – Runtime Security for AI Agents
Natural language policies block risky agent actions before they execute.
Solve My ProblemSlick
saranshrana
302mo ago
Security●●Solid
Agent Armor, a Rust runtime that enforces policies on AI agent actions
Eight-layer governance pipeline for agents when LangChain just executes blindly.
Big BrainShip It
edoardobambini-
422mo ago
Security●●●Banger
I made a local proxy for AI tool calls to keep my API keys safe
Finally, a way to use MCP tools without hardcoding API keys in every prompt.
Solve My ProblemSlick
jsherer
521mo ago
Security●●Solid
Agent Armor, a Rust runtime for enforcing policies on AI agent actions
Zero-trust governance for AI agents before they execute shell, file, or database actions with full audit trails.
Bold BetShip It
edoardobambini-
752mo ago
Security●●●Banger
AI Coding Agent Guardrails enforced at runtime
Blocks dangerous AI agent commands like rm -rf before execution in under 2ms.
Solve My ProblemSlick
cavalrytactics
501mo ago