RepoAlerts
SponsorGet alerts

Balanov/verdict

Library

Get alerts like thisView on GitHubShare on X

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 2 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 2 days ago.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A 197 KB local classifier that reads a CLI tool call's command, exit code, stdout and stderr and labels the outcome as success, failure, blocked or unknown. Advisory only; it runs on CPU with no Python dependencies.

Who it's for

Developers building coding agents, CI runners or tool-using systems that need to check CLI outcomes beyond exit codes

How to use it

Install

python -m pip install .

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up Balanov/verdict in my project. Follow its README: https://github.com/Balanov/verdict. Explain each step and check it is safe before running anything.

Star curve

234From 0 to 234 stars between 2 Nov 2026 and 5 Nov 2026.

On the radar

3 Nov 2026: #54
Best place #54, on 3 Nov 2026. In the top 100 on 1 of the last 19 days.

Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.

Records

  • Best place on RepoAlerts: #54, on 3 Nov 2026

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![Balanov/verdict on RepoAlerts](https://repoalerts.com/badge/Balanov/verdict.svg)](https://repoalerts.com/repo/Balanov/verdict?ref=badge)
Share on X
  • Balanov/shim

    A small Go CLI harness for talking to AI models from a terminal. It connects local and hosted model APIs, MCP servers and Agent Skills, and routes natural-language requests to allowlisted commands wit

    AgentAI agentsGo · 451 stars · +451 this week · 2 days old

  • taskless/cli

    A CLI and agent skill that turns corrections given to a coding agent into rules enforced on every change, using ast-grep, Vale, or runtime checks. Rules run locally in editors, for any agent, and in C

    CLI toolAI agentsTypeScript · 270 stars · +262 this week · 249 days old

  • Balanov/uncut

    A minimal headless coding agent harness in Go, shipped as one static binary with four tools. It sends the full conversation on every model call, never truncates file contents or command output, and ex

    AgentAI agentsGo · 601 stars · +601 this week · 3 days old

  • aicodeking/leanrea

    A single 8 KB agent skill file that gives AI coding agents routing rules and ready-to-run plain CLI commands for reverse engineering binaries, Electron apps and bundles, instead of an MCP server. It r

    AI skillAI agentsPython · 3,999 stars · +560 this week · 19 days old

  • winnin/farol

    A CLI and GitHub Action that runs after an AI code review and rates the risk of merging a pull request. It ranks the riskiest files, maps what the changes reach through the call graph, reports diff co

    CLI toolAI agentsTypeScript · 174 stars · +15 this week · 14 days old · HN 60 pts

  • alleyxd/AnyDecide

    A Python library and HTTP service that turns a local language model into a decision API. Typed questions (choice, score, yes/no) are answered in one batched forward pass by reading next-token probabil

    LibraryModels & inferencePython · 41 stars · 27 days old