failproofai

<div align="center"> <img src="https://d2wq11aau0arks.cloudfront.net/failproof/fa_updated_full.svg" alt="failproof ai" width="220" />

<a href="https://trendshift.io/repositories/69722?utm_source=trendshift-badge&amp;utm_medium=badge&amp;utm_campaign=badge-trendshift-69722" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/69722/daily?language=TypeScript" alt="FailproofAI%2Ffailproofai | Trendshift" width="250" height="55"/></a>

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

Observability and enforcement for every harness your agents run in. Wherever your agents run, we see it — and we can say no. Failproof hooks 12 agent harnesses — coding CLIs like Claude Code and Codex, chat gateways like Hermes, self-hosted assistants like OpenClaw — capturing every run and blocking dangerous tool calls before they execute. 39 built-in policies. Zero latency. Runs locally.

</div> <p align="center"> <img src="readme-arch-hq.gif" alt="Failproof AI in action" width="800" /> </p>

---

Supported harnesses

Twelve harnesses in two classes — ten coding CLIs, and two chat and assistant gateways (Hermes, OpenClaw). One policy API and one session history across all of them. What a policy can block is per-harness: stopping a tool call before it runs is verified on all twelve, turn-end gates on eight. The per-harness matrix lists the events each one honours.

Agents that run in none of them report through the Python SDK, which gives you tracing, sessions and audits. Enforcement there needs a hook in your own runtime — talk to us and we'll map it.

<!-- A 6-column table instead of inline <img> runs: table columns never re-wrap, so the grid stays 2×6 at any window width (scrolling on very narrow screens instead of collapsing into ragged orphan rows). --> <table align="center"> <tr> <td align="center" width="96"> <a href="https://claude.com/claude-code" title="Claude Code"> <img src="assets/logos/claude.svg" alt="Claude Code" width="56" height="56" /> </a> </td> <td align="center" width="96"> <a href="https://learn.chatgpt.com" title="OpenAI Codex"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logos/openai-dark.svg" /> <img src="assets/logos/openai-light.svg" alt="OpenAI Codex" width="56" height="56" /> </picture> </a> </td> <td align="center" width="96"> <a href="https://github.com/features/copilot/cli" title="GitHub Copilot CLI"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logos/copilot-dark.svg" /> <img src="assets/logos/copilot-light.svg" alt="GitHub Copilot" width="56" height="56" /> </picture> </a> </td> <td align="center" width="96"> <a href="https://cursor.com" title="Cursor Agent CLI"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logos/cursor-dark.svg" /> <img src="assets/logos/cursor-light.svg" alt="Cursor Agent" width="56" height="56" /> </picture> </a> </td> <td align="center" width="96"> <a href="https://opencode.ai/" title="OpenCode"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logos/opencode-dark.svg" /> <img src="assets/logos/opencode-light.svg" alt="OpenCode" width="56" height="56" /> </picture> </a> </td> <td align="center" width="96"> <a href="https://pi.dev/" title="Pi (pi-coding-agent)"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logos/pi-dark.svg" /> <img src="assets/logos/pi-light.svg" alt="Pi" width="56" height="56" /> </picture> </a> </td> </tr> <tr> <td align="center" width="96"> <a href="https://hermes-agent.nousresearch.com/" title="Hermes (hermes-agent)"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logos/hermes-dark.svg" /> <img src="assets/logos/hermes-light.svg" alt="Hermes" width="56" height="56" /> </picture> </a> </td> <td align="center" width="96"> <a href="https://openclaw.ai/" title="OpenClaw (openclaw gateway)"> <img src="assets/logos/openclaw.svg" alt="OpenClaw" width="56" height="56" /> </a> </td> <td align="center" width="96"> <a href="https://factory.ai/" title="Factory Droid (droid)"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logos/factory-dark.png" /> <img src="assets/logos/factory-light.png" alt="Factory Droid" width="56" height="56" /> </picture> </a> </td> <td align="center" width="96"> <a href="https://devin.ai" title="Devin CLI (Cognition)"> <img src="assets/logos/devin.svg" alt="Devin CLI" width="56" height="56" /> </a> </td> <td align="center" width="96"> <a href="https://antigravity.google" title="Antigravity CLI (agy)"> <img src="assets/logos/antigravity.svg" alt="Antigravity CLI" width="56" height="56" /> </a> </td> <td align="center" width="96"> <a href="https://goose-docs.ai/" title="Goose (codename goose)"> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logos/goose-dark.svg" /> <img src="assets/logos/goose-light.svg" alt="Goose" width="56" height="56" /> </picture> </a> </td> </tr> </table>

Install

npm install -g failproofai
failproofai config                             # wire up your agents and the daemon
failproofai policies add FailproofAI/policies  # choose what to enforce
failproofai                                    # dashboard on localhost:8020

Setup wires the hooks and picks no policies — that second command is what puts guardrails on the machine, and any pack is typed the same way (failproofai policies add <owner>/<repo>; policies show <owner>/<repo> reads one first). Run failproofai config with no terminal — CI, a container, an agent driving it — and it applies rather than asking. On a machine that has never been set up, any other command runs the same wizard first; disable that with FAILPROOFAI_NO_FIRST_RUN=1.

Until a pack arrives, the only thing enforcing is block-failproofai-commands, which is always on and cannot be switched off or paused: an agent that can pause enforcement can switch off every other policy.

---

What it stops

| Policy | What it blocks | |---|---| | block-env-files | Reads of .env and other secret files | | warn-repeated-tool-calls | The agent looping on the same call | | block-sudo | Privilege escalation | | warn-destructive-sql | DROP, TRUNCATE, unbounded DELETE | | block-terraform / block-kubectl | Unreviewed changes to live infrastructure | | block-rm-rf | Recursive file deletion | | block-force-push / block-push-master | git push --force, direct pushes to main |

Every one of these gates the call before it runs, so they hold on all twelve harnesses. The first four apply to any agent that can call a tool; the last three are the developer favourites — coding CLIs are the harness class we cover deepest. The sanitize-* family is separate: it runs after a tool returns, so it reports a secret in tool output rather than keeping it out of the context.

→ All 39 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:

| Decision | Effect | |---|---| | 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 |

→ Write a policy

---

Observability

Enforcement is one half. The other half is seeing what the agent actually did.

Run failproofai with no arguments and it serves a dashboard on localhost:8020 reading the run history already on your machine — no account, no signup, nothing leaving the box. You get the session list, the sequence of model calls, tool calls and hook decisions inside each run, what was blocked and what the policy told the agent, and an offline audit (failproofai audit) that scans your history for risky patterns and suggests policies to stop them.

→ Local dashboard · Read a trace · Local audit

Failproof AI Observability is the hosted side of the same data model, for teams running agents across a fleet: every run from every harness in one place, an execution graph with parallel sub-agents on their own lanes, p50/p95/p99 latency for models, tools and hooks, per-model cost and context-window tracking, error tracking, SQL over your own traces with shareable dashboards, evaluations scored by your own service, scheduled audits that turn recurring failures into evidence-backed findings, and alerts routed to Slack, email or a signed webhook. Self-hosting in your own cluster is available on the Enterprise plan.

→ Sessions · Audits · Book a demo

---

Documentation

| Start | | |---|---| | Quickstart | Install, connect a harness, see the first run | | Concepts | How the hook system works | | Supported harnesses | All 12, and what each one can enforce |

| Observe | | |---|---| | [Sessions](https://docs.befailproof.ai/s