Back to browse
GitHub Repository

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

8 starsPython

DOS – a referee between AI agents that doesn't believe their "done"

by anthonysarkis·Jun 18, 2026·2 points·0 comments

AI Analysis

●●●BangerBig BrainZero to OneSolve My Problem

Git-based verification catches AI agents lying about shipped features.

Strengths
  • Scoreboard validates approach on 15 real AI-built repos including CrewAI and AutoGen.
  • Exit code gating means false claims block CI/CD pipelines automatically.
Weaknesses
  • Narrow scope covers git verification only, not broader agent orchestration.
  • Early project with 8 stars needs more real-world production validation.
Category
Target Audience

Developers using AI coding agents

Similar To

LangChain · AutoGen · CrewAI

Similar Projects

Security●●Solid

AIP – An open protocol for verifying what AI agents are allowed to do

OAuth + TLS for AI agents—eight-step verification pipeline, but adoption depends on framework integration.

Big BrainSolve My Problem
theaniketgiri
124mo ago
Gaming●●Solid

Multi Agent World Cup Simulator

Four-agent match simulation with in-browser TTS commentary via WebGPU.

Crowd PleaserCozy
tantara
107d ago