Approval Workflow Python Packages

squidbrake

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

obstat

An auditable decision record for agent tool calls. The clearance is written down before the call runs.

agentbell

Push notifications and phone approvals for AI coding agents — free, stdlib-only, no server or account.

netbox-change-control

Policy-driven change control and mandatory review for NetBox branches

raposa-mcp

MCP server for Raposa Aval: request_human_approval — a named person approves or rejects, silence is not consent, hash-chained audit log. Local (uvx) or remote at dcescrypt.com/api/mcp

aegize

Infrastructure for autonomous AI agents: identity, policy, permissions, approval workflows, and audit.

interject

A durable ask() primitive: stop a program, ask a human, resume days later on another machine.

langchain-sidclaw

The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-demo

chowki

chowki — durable execution for LLM agents: crash recovery, step memoization, human approval gates, secret redaction, and token budgets. Decorators, not infrastructure. No server, SQLite-backed.

phantasmpy

Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

holdpoint

A durable approval queue for agent actions: pause the call, let a human review or patch it, then run it exactly once. Zero dependencies, SQLite persistence, immutable audit.

precheck-guardian

A pre-execution approval gate for AI agents: preview the plan, see per-step risk, approve/reject/edit before anything runs. Framework-agnostic, zero core deps.

squadcue

Local-first mission control for your AI agent workforce — run CLI agents like employees (SquadCue)

planseal

Cryptographic approval for saved Terraform and OpenTofu plans

raposa

Python and TypeScript clients for Raposa Aval — human approval for AI agents with a signed, hash-chained audit trail (pip install raposa · npm i raposa-sdk)

agentic-sentinel

🛡️ Zero-trust governance for AI agents. Intercept, approve, and audit LLM actions with one decorator. Fail-secure by default.

nodsend-ai

Human approval infrastructure for AI agents. One API call. A human decides. You get a signed webhook.

toran-sdk

Runtime human-approval gatekeeper for AI agents. Framework-agnostic, sub-millisecond, self-hosted.