Heimdall
Verification gates for AI coding agents that require proven tests before merging
Visit runheimdall.dev ↗What is Heimdall?
Heimdall is a verification system that ensures AI coding agents produce tested, reviewable changes before they reach your codebase. It works as a Claude Code plugin and git pre-push hook, requiring agents to pass external oracle tests—tests they didn't write themselves—before opening pull requests. The maker says it was built with Claude Code.
Designed for teams, Heimdall coordinates parallel agents across developers' machines through a shared ledger and live presence wall. Team members auto-join by GitHub repo access, and each developer's triage becomes a shared learning corpus. Every change includes runnable evidence and honest attestation. The system uses Ed25519-signed requests, per-team secret partitions, and prevents self-merges—humans always retain final approval.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Heimdall automatically. Evidence: GitHub randomittin/heimdall; repo has AGENTS.md, CLAUDE.md. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces

Manage teams of AI agents to run your business from one dashboard

Persistent memory for AI agents across Claude Code, Cursor, and MCP clients