imbue-ai/vet

Find issues worth your attention.

What it solves

Vet is a verification tool designed to ensure that code changes and the behavior of coding agents are correct and aligned with the user's intent. It prevents bugs and mismatches between what a user requested and what an agent actually implemented.

How it works

Vet snapshots the repository and the code diff, optionally incorporating the user's goal and the agent's conversation history. It then uses Large Language Models (LLMs) to run checks, filtering and deduplicating the findings to produce a final list of issues.

Who it’s for

It is intended for developers and teams using AI coding agents (such as Claude Code, Codex, or OpenCode) or those who want an automated way to review pull requests in CI/CD pipelines.

Highlights

  • Agent Integration: Can be installed as a skill for coding agents, allowing them to proactively run verification checks after making changes.
  • Flexible Deployment: Works as a CLI tool, a GitHub Action for PR reviews, or an agent skill.
  • BYO-Model: Supports any OpenAI-compatible provider via custom JSON configuration and maintains a community model registry.
  • Customizable Checks: Users can modify the 통해 guide text for specific issue codes via a guides.toml file to tailor the verification process.
  • Privacy-Focused: Open source and requires no account or data collection; requests are sent directly to the inference provider.

Related

  • Project
    gitmono-dev/mega

    A Rust-based, Git-compatible monorepo engine designed to provide AI coding agents with the full codebase context and infrastructure needed for petabyte-scale software engineering.

  • Project
    ant-intl/Falcon-TST

    A family of large-scale time series foundation models, including univariate and multivariate versions, for efficient and accurate forecasting.

  • Project
    relari-ai/continuous-eval

    continuous-eval is a Python library for modular, data‑driven evaluation of LLM‑powered pipelines. It provides a catalog of retrieval, generation, code, and agent metrics, lets you attach those metrics to individual pipeline modules, runs them on a dataset, and can enforce regression tests. Custom LLM‑as‑a‑judge metrics are also supported.

  • Project
    rsmdt/the-startup

    A multi-agent AI framework for Claude Code that implements a spec-driven development workflow to turn ideas into shipped code via structured planning and parallel specialist agents.