yoetz
Active·★ 14·Apache-2.0·Updated 2026-10-22
Yoetz is a local-first, open-source system designed to verify if AI agents truly complete their assigned tasks by recording and checking structured work evidence. It provides honest, coverage-bounded receipts detailing what was verified and what remains open, ensuring transparency in agent-assisted development workflows.
#Agent Validation#Work Evidence#Local Policy Checks#Task Integrity#Developer Tools#AI Oversight#Code Review
01
Features
01Provides honest, coverage-bounded receipts detailing verified work and remaining gaps.
02Operates as a local-first, zero-egress system ensuring privacy and offline functionality.
03Integrates optional AI-powered review with strict privacy controls.
04Records structured work evidence and performs policy-based local integrity checks.
05Offers a full-screen terminal interface and integrates with any MCP agent.
02
Compatibility
Python
Runtime
Verified via docs
MacOS
OS
Verified via docs
Linux
OS
Verified via docs
WSL 2
OS Layer
Verified via docs
uv
Package Manager
Verified via docs
npm
Package Manager
Verified via docs
03
Quick start
1
$ uv tool install --managed-python --python 3.14.6 yoetz
04
Use cases
↳Verifying the actual completion and adherence to requirements of AI agent tasks.
↳Ensuring the integrity and correctness of code changes during agent-assisted refactoring.
↳Providing auditable receipts for developer workflows, particularly in automated or agent-driven environments.
↳Monitoring and validating the execution of obligations and claims made by AI agents.
↳Establishing a transparent record of work verification for quality assurance or compliance.
05
Alternatives
palico-ai★ 343
Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework
mastermind★ 13
Local Rust codegraph and verifiable workflow for AI coding agents — project maps, change and test impact, MCP queries, and diff-backed implementation audits.
gentle-ai★ 7.9k
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Spec-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.
code-pathfinder★ 143
AI-Native Static Code Analysis for modern security teams. Built for finding vulnerabilities, advanced structural search, derive insights and supports MCP
Comments
Log in to leave a comment
No comments yet. Be the first!