tool-approval

Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalating to the user.

Self-hosted WeChat bridge for Claude Code and Codex, with Claude tool approval and bidirectional file relay.

Runtime guardrails for AI agent MCP tools. Blocks dangerous tool calls at runtime with a default-deny policy proxy.

Aielia — the everyday AI assistant built with Build A Harness. Runs a full 11-layer agent harness (world model, control-state gate, 9-layer verification, recovery, learning) on every turn, and stops for approval before it sends an email or runs a shell command. Try it: buildaharness.com/try

The form renderer for MCP tools, A2A agents, and human-in-the-loop AI. One component. Any JSON Schema. Beautiful forms. Under 1ms.

[READ ONLY] Tool approval guard middleware for Laravel AI agents.

Three-tier intelligent permission gate for AI agents — automated approval with hash-based trust, AI evaluation, and full audit ledger

Provider-free before/after reproduction for Vercel AI SDK WorkflowAgent signed tool approvals and replay enforcement.

Runtime risk guard for OpenClaw: hook-based tool interception, approval workflows, prompt injection defense, and auditable local security controls.

Minimal shell over Claude: Blazor UI + Claude Agent SDK sidecar with browser-based tool approval (Allow/Deny on every tool call). No injected prompt, no governance - fork it to build your own workflow.

Provider-free OpenAI Agents SDK RunState lab for tool approval, cross-process resume, rejection, idempotency, and streamed-resume persistence.