# FailproofAI/failproofai

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.  40 built-in policies, a local dashboard, no account required with a generous free cloud plan

Repository: https://github.com/FailproofAI/failproofai
Canonical: https://ross.abutalabs.com/products/failproofai
Homepage: https://befailproof.ai
Language: MDX
License: NOASSERTION
License Family: other
Topics: claude-code, reliability, agent-reliability, hooks, agent-failure, ai-agent, codex, llm, llm-failures, npm-package, agent-harness, agent-observability, agent-tracing, enforcement, evals, guardrails, hermes, llm-observability, observability, openclaw
Last push: 2026-08-26T15:41:22+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 10
- inputs: {"age_days": 150, "days_push": 7, "days_rel": 14, "gap_med": 0.0, "n_releases_24m": 27}
- flags: young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1508, forks 404 (observed 2026-08-28T04:04:55.671561+00:00)

## What it is
Failproof AI is an open-source observability and enforcement layer for AI agent harnesses like Claude Code, Codex, Hermes, and OpenClaw, capturing every run and blocking dangerous tool calls in real time via hooks and a sub-millisecond Rust daemon. It ships as an npm CLI with a local dashboard, 40 built-in policies, a Python SDK for custom agents, and an optional cloud plan for teams.

## Use cases
- observe and trace every AI agent run, tool call, and model call
- block dangerous tool calls like rm -rf or force pushes before they execute
- detect agent failure modes like infinite loops, hallucinated tools, and context drift
- audit agent sessions and cluster recurring failures into ranked issues
- add guardrails and policy enforcement to coding CLIs and chat gateways
- run agent reliability monitoring locally with no account
- add observability to unattended agents running behind chat gateways or cron

## When to choose
- you run agents in supported harnesses (Claude Code, Codex, Cursor, Gemini CLI, Hermes, OpenClaw, etc.) and need runtime enforcement, not just logging
- you want local-first tracing and auditing with a free tier and no account required
- you need fail-closed policy enforcement with sub-millisecond latency in the tool-call path

## When to avoid
- your agent runs in an unsupported runtime and you need enforcement, not just SDK-based tracing
- you need a fully permissive MIT license for commercial redistribution (it is MIT + Commons Clause)
- you need Windows support today (setup supports Linux and macOS only)

## Facets
- artifact type: cli-tool
- maturity: active
- function: monitoring, tracing, alerting, logging, security, cli, agent-framework, analytics
- domain: large-language-models, developer-tools, monitoring, security
- platform: cli, self-hosted, cloud
- tags: agent-observability, policy-enforcement, guardrails, claude-code, codex, agent-harness, llm-observability, evals, rust-daemon, fail-closed, ai-agents, automation, linux, macos, nodejs, docker

## Member repositories
- FailproofAI/failproofai (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:55.671561+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:31.004852+00:00, confidence not recorded.
  - readme: https://github.com/FailproofAI/failproofai (fetched 2026-08-28T04:04:55.671561+00:00, sha 4a5792e45f52)
  - homepage: https://befailproof.ai (fetched 2026-08-29T11:37:04.067210+00:00, sha df0d411b4289)
  - site_page: https://docs.befailproof.ai (fetched 2026-08-29T11:37:04.076541+00:00, sha 89782fee610e)
  - site_page: https://befailproof.ai/pricing (fetched 2026-08-29T11:37:04.078308+00:00, sha 50c684634ca9)
  - site_page: https://befailproof.ai/blog/add-observability-to-hermes-agent (fetched 2026-08-29T11:37:04.079902+00:00, sha aedb9865c107)
  - site_page: https://befailproof.ai/blog/sub-millisecond-agent-enforcement (fetched 2026-08-29T11:37:04.081560+00:00, sha 173b66b8abb1)
- Data as of 2026-08-30T08:39:29.467469+00:00.