Permission

DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside under sandbox/read-only modes; follows a live permission switch without restart. Verified on real hardware (full -> workspace-write -> read-only -> full). Crafted on an estimated 0.27 USD of model spend.

Set up Claude Code once. Your whole company gets it. Self-hosted Claude Code and Codex with your company files, team skills, MCP and per-person folder permissions.

The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 50+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.

An LLM programming assistant engine built with Go, supporting WebSocket, multi-turn dialogues, tool calling, permission control, and skill extension.

Create reusable bots powered by Claude Code, Codex, or OpenCode. Run them locally across your repositories with persistent threads and permissions you control.

⚡ Lara Dashboard - CMS by Laravel - All In One solution to start your Laravel Application from Basic to Enterprise. Manages Users, Roles, Permissions, Modules, Settings, Translations, Contents, Monitoring and every actions of your Laravel application. Complete solution for Laravel application with Tailwind, Livewire, Rest API, Unit-Tests and more.

AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️

The open-source workspace for people and AI agents. Docs, databases and realtime collaboration with an MCP server in the same binary, so agents work in the same workspace on the same permissions. One Go binary, one SQLite file, self-hosted.

Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models.

Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI, Telegram or More.

Local-first AI action assistant for operators: memory, skills, tools, and permission gates to turn work into controlled action.

Udemy & Hotmart course downloader, YouTube downloader (yt-dlp GUI, 1,800+ sites) + desktop app for AI agents: Claude Code, Codex, Gemini CLI, Ollama. Permissions, undo, jobs, loops until tests pass, MCP server, 156 tools, course player. Free and open source for Windows, macOS and Linux. No terminal. Your files stay on your computer.

An open-source PHP CMS for building custom websites and APIs. Extend it with modular Apps and Themes, use its REST API, and connect AI agents through a built-in MCP server and permission-based access controls.

Agent skill for harness engineering — memory, permissions, context engineering, multi-agent coordination. Distilled from Claude Code, with Codex CLI and Gemini CLI on the roadmap. EN/ZH. Install via npx skills add.

Safely run OpenCode, Codex, Claude Code with full permissions.

A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes.

Open-source GrokBot alternative built on DeepSeek Harness. Build your personal bot team: multiple personal agents with persistent memory, identities and permissions, extensible through DSH plugins.｜基于 DeepSeek Harness 的开源 GrokBot 平替：有长期记忆的个人 AI Bot 团队，支持多 Bot 协作、身份权限与插件生态扩展。MIT.

🐤 Less permission fatigue, more momentum. Dippy knows what’s safe to run and keeps Claude on track when plans change.

Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.

Safely run OpenCode, Codex, Claude Code with full permissions.

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

AI coding agent with one Python core and three front-ends — headless CLI, Textual TUI, and an Electron desktop. Works with any OpenAI-compatible API, with risk-tiered permissions, event-sourced replayable sessions, and a fail-closed OS-level sandbox.

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.