convez.ai
AgenteDevOps & InfraestruturaIntermediário
FailproofAI

Failproof AI

FailproofAI/failproofai

Prevenção de falhas para agents de código com execução local

Ver no GitHub
BomPluginScore · de 0 a 100

Agent de resolução de falhas em tempo de execução para assistentes de código como Claude Code, OpenAI Codex e GitHub Copilot. Intercepta loops infinitos, ações perigosas e vazamentos de secrets antes que se tornem incidentes, operando localmente com latência zero.

Instalação

$npx convez-ai FailproofAI/failproofai

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
9,7 mil
Forks
579
Acompanhando
6
Saúde
75%
Último commit
há 22 horas
Versão
v1.0.14
Issues abertas
71
Contribuidores
9

Casos de uso

  • Prevenir loops infinitos em agents de automação de código
  • Detectar e bloquear ações perigosas antes da execução
  • Evitar vazamento de credenciais e secrets durante processamento
  • Monitorar behavior de agents Claude Code e Copilot

Veredito

Ferramenta especializada e bem-arquitetada para segurança de agents de código. Preenche uma lacuna crítica ao oferecer guardrails locais e zero-latência sem depender de serviços externos.

README

A tradução para o português deste README ainda está na fila.

npm CI Supply Chain Slack Docs License

Translations: 简体中文 · 日本語 · 한국어 · Español · Português · Deutsch · Français · Русский · हिन्दी · Türkçe · Tiếng Việt · Italiano · العربية · עברית

Runtime failure resolution for coding agents. Hooks into Claude Code and Codex. Catches loops, dangerous actions, and secret leaks before they become incidents. Zero latency. Runs locally.


Supported agent CLIs

Install hooks for one or any combination: failproofai policies --install --cli opencode pi gemini (or --cli claude codex copilot cursor opencode pi gemini). Omit --cli to auto-detect installed CLIs and prompt.


Install

npm install -g failproofai
failproofai policies --install   # or just run `failproofai` and accept the first-run prompt
failproofai

30 built-in policies activate immediately. Dashboard at localhost:8020. Disable the first-run prompt with FAILPROOFAI_NO_FIRST_RUN=1.


What it stops

PolicyWhat it blocks
block-push-masterDirect pushes to main / master
block-force-pushgit push --force
block-work-on-mainCommits, merges, rebases on main / master
block-rm-rfRecursive file deletion
sanitize-api-keysAPI keys leaking into agent context

→ All 30 built-in policies


Your own policies

Drop a file into .failproofai/policies/ — it loads automatically, no flags needed. Commit it and the whole team gets it on next pull.

import { customPolicies, deny, allow } from "failproofai";

customPolicies.add({
  name: "no-production-writes",
  match: { events: ["PreToolUse"] },
  fn: async (ctx) => {
    if (ctx.toolInput?.file_path?.includes("production"))
      return deny("Writes to production paths are blocked.");
    return allow();
  },
});

Three decisions available to every policy:

DecisionEffect
allow()Permit the operation
deny(message)Block it — message goes back to the agent
instruct(message)Let it through, but add context to the agent's next prompt

→ Custom policies guide


Session visibility

Every tool call your agent makes is logged locally. The dashboard shows what ran, what was blocked, and what the policy told the agent — so you're not guessing when something goes wrong. → Dashboard guide


Documentation

Getting StartedInstallation and first steps
Built-in PoliciesAll 30 policies with parameters
Custom PoliciesWrite your own
ConfigurationConfig scopes and merge rules
DashboardSession monitor and policy activity
ArchitectureHow the hook system works

License

MIT with Commons Clause — free for internal and personal use; commercial resale of failproofai itself requires a separate agreement. See LICENSE for the full text.


Contributing

See CONTRIBUTING.md. New policies, edge cases, and translations all welcome.

Build before you start. Run bun install && bun run build first. This repo runs failproofai's own hooks on itself, and they resolve the failproofai import against the compiled dist/ bundle — without a build you'll hit Cannot find package 'failproofai' hook errors. Rebuild after changing src/. See Build before the in-repo dev hooks will work.


Built by Nivedit Jain and Nikita Agarwal. befailproof.ai

Ver o original no GitHub

Bom para

Relacionados