SidClaw governance integration for LangChain.js — policy evaluation, human approval, and audit trails

Anti-slop guardrails, specialized agents, and a live observability + control plane for AI-assisted coding. Watchtower (Python + SQLite, no setup) shows a live heartbeat, your sessions, and a needs-human approval queue — checkpoint, compact, fork, close, o

Guardrails for AI agents — budget limits, kill switches, and human approval gates.

Policy-as-code authorization for AI SDK tool calls, powered by [Open Policy Agent](https://www.openpolicyagent.org/).

Sandclaw Builder plugin — Docker-based code builds via Confidante with human approval

Returns from a pool of 15m human-readable IDs

Independently verify AxioRank audit receipts, agent-commerce conformance seals, agent reputation credentials, and coding-session seals offline. Merkle inclusion proofs, Ed25519 signed tree heads, delegation provenance, human-approval signatures, witness c

Human-approval UX for AI agents and CLIs: explain risky actions in plain language before a human approves them.

AI workflow orchestration with human approval gates. Self-hosted, open source.

Enterprise approval workflow plugin for Agorio SDK — require human approval before high-value transactions

An AI agent CLI that clones a messy student/hackathon repo, detects its stack, generates Docker + docker-compose configs, shows a service-graph diagram for human approval before running anything, then builds/runs the containers with a self-healing retry l

Manages requests that require user approval

Faramesh governance plugin for OpenClaw — policy-based Allow/Ask/Deny for every tool call, human approval workflows, and full audit logging.

Approval Tests Library - Capturing Human Intelligence

The open-source company brain that powers a closed loop — model-free, over MCP. Your AI tool (Claude, Cursor, Copilot) answers from your docs with citations or refuses; record how-work-gets-done as skills, govern real actions with human approval + an audi

Component testing utils for Vue 3.

Human-readable error messages for Ajv (Another JSON Schema Validator).

Server-side email runtime, agent tools, and AppKit plugin.

The seatbelt for MCP agents — one command wraps your MCP servers with Strix governance: writes require human approval, reads pass, every action produces a signed receipt.

Interven JS/TS SDK — Approvals + Audit for AI Agents. Scan tool calls through policy + risk scoring. Block, redact PII, or route to human approval via Slack.