StackMap
Subscribe

failproofai vs statewright

Observability plus policy enforcement for agent harnesses: records every run across 12 harnesses (Claude Code, Codex, Cursor, Hermes…) and blocks dangerous tool calls with 39 built-in policies. — versus — State-machine guardrails for AI agents: define workflow phases once and only that phase's tools unlock — enforced across Claude Code, Codex, Cursor, opencode and Pi. Rust.

The curated verdict

Both gate what an agent may call. Statewright unlocks tools by workflow phase (state machine); Failproof AI blocks by policy on the call itself (what, where, with what). Phase guardrails vs content guardrails.

failproofaistatewright
Stars2.1k490
Forks44421
LanguageMDXRust
LicenseNOASSERTIONNOASSERTION
Last activityyesterday14 days ago
Topicssecurity, codingcoding, orchestration
Curated connections55

failproofai — the curator's take

The one to install the day an agent first runs `rm -rf` or force-pushes: hooks into ten coding CLIs plus the Hermes and OpenClaw gateways, records sessions to a local dashboard on :8020, and enforces policies *before* the tool call runs — sanitize API keys, block .env reads, sudo, terraform/kubectl, destructive SQL, direct pushes to main. Custom policies are a JS file in .failproofai/ that returns allow/deny/instruct; packs are versioned GitHub repos. NOT a tracing platform for agents you built from code (the Python SDK gives tracing but enforcement needs a hook in your runtime), and note the source-available licence and optional cloud — local works without an account.

statewright — the curator's take

'Agents are suggestions, states are laws' — gating the TOOL space per phase is the right enforcement layer, and their small-model results (2/10 → 10/10 on a 5-task SWE-bench subset) suggest constraints can substitute for scale. When NOT: it's SaaS-keyed — sign-up required, NOASSERTION license; the enforcement client is open but the service isn't. The benchmark is 5 tasks, not 2294, and hard-blocked tools also block legitimate improvisation.