Run Claude Code autonomously inside your Docker Compose stack (OSS)
Claude Code's --dangerously-skip-permissions flag lets agents run without interruption, but it needs a sandboxed environment to be safe. dangerously is an open source tool that spins up an isolated container and runs Claude Code inside it — file system changes are restricted to your project directory. The new version detects your docker-compose.yml and spins up your full service stack alongside Claude Code, so the agent can test against real dependencies — databases, queues, whatever your app needs. npm install -g dangerously
Run Claude Code autonomously inside your Docker Compose stack (OSS) launched on April 3, 2026 with 8 votes, #1,409 of 21,248 launches that month and more than 75% of that year's launches.
What it does
Run Claude Code autonomously with --dangerously-skip-permissions in an isolated Docker container. - sayil/dangerously
Run Claude Code autonomously in an isolated Docker container. Claude Code's --dangerously-skip-permissions flag lets agents act without interruption — but Anthropic warns you to only use it inside a sandboxed environment. dangerously spins up that sandbox for you. macOS users: The first time you run dangerously , you'll be prompted to complete a one-time OAuth setup (Claude Code on macOS stores credentials in the Keychain which Docker containers cannot access). Just follow the prompts — it takes 30 seconds and you'll never need to do it again. If you need to update your token (e.g., you pasted the wrong one), run: dangerously Claude Code launches inside an isolated Docker container. File…from github.com
Does a similar job
all alternatives →
Auto Mode by Claude CodeMar 2026 · claude.com · ▲509Let Claude make permission decisions on your behalf
Continuous Claude – run Claude Code in a loopNov 2025 · github.com · ▲170Continuous Claude is a CLI wrapper I made that runs Claude Code in an iterative loop with persistent context, automatically driving a PR-based workflow. Each iteration creates a branch, applies a focused code change, generates a commit, opens a PR via GitHub's CLI, waits for required checks and reviews, merges if green, and records state into a shared notes file. This avoids the typical stateless one-shot pattern of current coding agents and enables multi-step changes without losing intermediate reasoning, test failures, or partial progress. The tool is useful for tasks that require many…
A Claude Code plugin that catch destructive Git and filesystem commandsDec 2025 · github.com · ▲61A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code
A context-aware permission guard for Claude CodeMar 2026 · github.com · ▲127We needed something like --dangerously-skip-permissions that doesn’t nuke your untracked files, exfiltrate your keys, or install malware. Claude Code's permission system is allow-or-deny per tool, but that doesn’t really scale. Deleting some files is fine sometimes. And git checkout is sometimes not fine. Even when you curate permissions, 200 IQ Opus can find a way around it. Maintaining a deny list is a fool's errand. nah is a PreToolUse hook that classifies every tool call by what it actually does, using a deterministic classifier that runs in milliseconds. It maps commands to action types…

runCLAUDErun2025 · runclauderun.com · ▲112I built runCLAUDErun because I got tired of manually running the same Claude Code tasks every day. It's free and it runs locally. What it does: It's a macOS app that schedules your local Claude Code to run on any schedule you want - daily, weekly, or custom cron expressions. My use case: Every night at 11pm, it automatically summarizes my Obsidian daily notes. But, it can schedule any Claude task - code reviews, data processing, report generation, web research, file organization, etc... Technical details: - Native macOS app (Electron + React) - Uses launchd for scheduling (proper macOS…
More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art

PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com

Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com


I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay
Life & fun · Apr 2026 · sam-burns.com

With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app