RepoRadar
Leave a Tip
Item detail

Mindburn-Labs/helm-ai-kernel

HELM AI Kernel is an Apache-licensed local firewall for agent actions that sits between Claude Code, Codex, MCP tools, shell commands, and model requests, then enforces allow, deny, or escalate decisions with signed receipts.

Open source →Back to radar
Score8.3
Popularity62.0
Riskconditional
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum6.0
Maturity7.8
Open-source/build8.4
Evidence7.2
Workflow potential9.8
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for teams that want a concrete control boundary for agent actions instead of relying on prompt-only guardrails.

Who should use it

security-conscious engineering teamsAI platform teamsregulated environments testing coding agentsdevelopers adding policy checks around MCP tools

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

HELM AI Kernel sits directly in the execution path for tools and model requests, so validate policy behavior and receipt verification on non-critical workflows before trusting it as a production control boundary..

Evidence links

Closest alternatives / related signals

agent-securitymcppolicy-enginedeveloper-toolsaudit