Automatic, model-driven permission review for OpenCode
Claude Code-style auto approval layer for DeepSeek Harness: deterministic rules + two-stage classifier, circuit breaker, fail-to-human. Shadow mode day one.
DeepSeek Harness 自动审批插件：在 workspace-write 沙箱之上叠加确定性规则 + LLM 安全审批，自动模式不放宽沙箱、fail-closed。 Safe auto-approval for DeepSeek Harness — deterministic rules + LLM review on top of the workspace-write sandbox. Auto mode without ever granting full-access.
PR blast radius analyzer: a 0-1 risk score for every pull request so AI-reviewed, low-risk PRs auto-approve into the merge queue. GitHub Action, CLI, Claude Code plugin, MCP server.
Auto-Approval & Security Guardrail for Google Antigravity (agy), powered by local Shieldstral 3B.
Let OpenCode run unattended, securely. An isolated System One or LLM reviewer answers permission prompts. Risky calls go back to the agent with a reason, and unclear ones come to you.
OpenCode plugin that uses an LLM to assess bash command risk and auto-approve low-risk permission requests with an auditable decision history.
AI-powered compliance and governance system that analyzes policies, documents, and workflows to detect regulatory risks and generate actionable compliance reports.
A professional, serverless Telegram Auto Approval Bot built with Cloudflare Workers. Instantly approves join requests and sends a private welcome message. Fast, free, and secure.
To associate your repository with the auto-approval topic, visit your repo's landing page and select "manage topics."