Agent that refuses to run commands without human approval
In light of recent news about an agent deleting a production database, I thought now would be a good time to share this. As the use of AI tools in production is becoming more common, sadly so will the high profile incidents like the one mentioned. Fewshell is a terminal agent specifically designed to avoid this. There is no setting to enable command auto-approval. This is by-design, so that the user never has to second-guess or worry about accidentally having it enabled. Originally my intention was to build an AI mobile terminal to make typing shell commands easy. But with so many…
Agent that refuses to run commands without human approval launched on April 30, 2026 with 12 votes, #1,176 of 21,248 launches that month and more than 90% of that year's launches.
In plain words
Fewshell is a terminal agent that requires explicit human approval before executing any shell commands. Designed as a safety-focused alternative to autonomous agents, it eliminates the risk of accidental command execution in production environments by removing auto-approval settings entirely. The tool helps users leverage AI assistance for terminal tasks while maintaining full control over what actually runs on their systems.
written from the facts on this page · September 2026
From the sources
Contribute to few-sh/fewshell development by creating an account on GitHub.
A collaborative, self-hosted mobile+desktop SSH copilot for on-calls, devops, MLOps, AI researchers, sysadmins and self-hosting enthusiasts. Fewshell is an attempt to solve this without sacrificing security, privacy and safety . It is not meant to be a coding agent or an autonomous AI assistant. There are many powerful open source and commercial agents for this. You can configure some to do the same or similar tasks as Fewshell, but it usually takes extra effort. It is not packed with features or many customizable options. It's intended to do one thing and do it well. Constrained by-design to allow easy setup and reduce the risk of accidentalfrom github.com
In the maker’s words, at launch
In light of recent news about an agent deleting a production database, I thought now would be a good time to share this. As the use of AI tools in production is becoming more common, sadly so will the high profile incidents like the one mentioned. Fewshell is a terminal agent specifically designed to avoid this.…
Does a similar job
all alternatives →
PreloopJan 2026 · preloop.ai · ▲121Hey HN, I’m Yannis, co-founder of Preloop. We’ve built a proxy for the Model Context Protocol (MCP) that lets you add human approval gates to your AI agents without changing your agent code. We’re building agents that use tools (Claude Desktop, Cursor, etc.), but we were terrified to give them write-access to sensitive systems (Stripe, Prod DBs, AWS). We didn't want to rewrite our agents to wrap every tool call in complex "ask_user" logic, especially since we use different agent runtimes. We built Preloop as a middleware layer. It acts as a standard MCP server proxy.You point your agent to…
I built a firewall for agents because prompt engineering isn't securityJan 2026 · github.com · ▲7Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
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