AI · alternatives · 2026
24 alternatives to 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…
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… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Prices are shown for the 1 we have checked on their own sites, 1 of them free or with a free tier.
- 1
Preloop▲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…
Jan 2026 · preloop.ai · its alternatives →
- 2
Cyris▲98"Cyris is the orchestration layer your AI agents are missing. Whether you're a two-person startup or a 10,000-employee health system — connect agents from OpenClaw, Claude, GPT-4o, Ollama, EPIC, or any platform and have them coordinate, hand off, and escalate across your entire organization. Self-hosted. Auditable. Human-governed" Just a side project I've been working on, and was curious whether people would actually find something like this useful! I'd recommend checking out the sandbox as well.
Apr 2026 · cyrisai.dev · its alternatives →
- 3
Windows Terminal with native agent integration
Jun 2026 · github.com · its alternatives →
- 4
A CLI agent that keeps working when you close your laptop
Apr 2026 · devin.ai · its alternatives →
- 5
Grovefree tier, from $5/mo▲101One terminal for you and your AI agent
Sep 2026 · grove.publishstudio.one · its alternatives →
- 6
Hi 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…
Jan 2026 · github.com · its alternatives →
- 7
One terminal. Every agent. Total clarity.
May 2026 · github.com · its alternatives →
- 8
Avery▲16Create a deterministic agent that runs on your hardware
Jul 2026 · avery.software · its alternatives →
- 9
Midfleet▲8Make multi-agent work reliable at any scale
Aug 2026 · app.midfleet.ai · its alternatives →
- 10
Agentinel▲18Stop AI agents from installing malicious packages.
Jul 2026 · agentinel.habitwala.in · its alternatives →
- 11
Aether▲26Since coding agents like Claude Code and Codex came out, I've been pretty obsessed with them. It's hard not to when you're getting a 20x discount on inference. I've also been frustrated by them a lot. I hated walking around with my laptop lid open while connected to a hotspot on my phone, having to tediously accept commands so I don't lose my root directory, and running out of RAM when running multiple agents that were spinning up dev servers in different worktrees at once. A lot of people would say existing cloud agents are the solution to this, as none of the above problems apply to any…
Jul 2026 · runaether.dev · its alternatives →
- 12
- 13
Plug-and-Play terminal gatekeeper for LLM agents
Jan 2026 · github.com · its alternatives →
- 14
- 15IA
1. Headless mode Headless mode allows you to use the AI as a command-line utility for automation and scripting. In Claude Code you run it with the -p flag: claude -p, in codex - exec, opencode - run. 2. Ask human The traditional communication channel with the operator won't work in headless mode - we need to implement a dedicated tool. Here is an example of how this can be done https://github.com/sermakarevich/claude/tree/main/mcp/ask_hu... 3. Tasks queue Beads is a lightweight distributed graph issue tracker for AI agents, powered by Dolt. You can…
Jun 2026 · its alternatives →
- 16
- 17
ViaHuman▲5TL;DR: Mobile notifications for AI workflow approvals. Built it because running 5+ AI agents at once is chaos. The problem: This paragraph is the longest thing I've written by hand in weeks. Everything else? AI-generated across 5 browser tabs (GPT, Gemini, Claude) and multiple terminals running Claude Code. They're FAST. They're GOOD. But here's what nobody tells you: you become the bottleneck. I'd start 3 agents on different tasks, context switch between them, and lose track of which ones needed my input vs which ones were safe to auto-execute. Critical decisions got buried in terminal…
Jan 2026 · viahuman.xyz · its alternatives →
- 18
- 19
Gofer is a side-project I wrote at 15 because I was sick of these so-called CLI agents. Claude Code, Codex, Gemini CLI, they're all wonderful if you're coding. But for those just wanna automate their stuff, it's a dud. Gofer solves this by being terminal-first, meant to accomplish any task a command line can. It can also watch your desktop so you can avoid waiting for downloads to finish, and can text you via. Telegram! Happy to answer any questions :D! -J
2025 · github.com · its alternatives →
- 20
We were both genuinely impressed by Claude Code after it helped each of us fix nasty CI problems overnight. Doing those fixes manually would have taken days. After that experience, we each found ourselves struggling through Ctrl+Tab through multiple Claude Code windows in our terminals. While we enjoyed having agents working for us in parallel, context switching and cycling through each terminal tab was a real pain. So we thought: Can we design a TUI dashboard that manages a large swarm of agents in one place? Even better, can agents manage agents hierarchically, like how companies work?…
May 2026 · omar.tech · its alternatives →
- 21
That's a bold claim. But I genuinely feel like I might have actually solved computer use (demo: https://x.com/mdlahfir/status/2088109763783700827?s=20) For context, I've been building agent-desktop (Inspired by agent-browser by Vercel Labs), an automation CLI for desktop apps. It's like Playwright but for desktops, not just native, but for Chromium apps as well. Trust me, yes, Chromium apps whose accessibility tree is dense. MacOS is GA; I'm almost close to launching for Windows and Linux! So, how did I solve it? Basically interoperability. The biggest issue with…
Aug 2026 · github.com · its alternatives →
- 22
Hi HN. This is a script I have been using for some time for coding tasks, which I have polished a bit and published. The motivation behind this script was to have an agent with persistent session which I can use from the shell like a regular command. It _can_ also be scripted, although I don't use it in such a way. The script uses a minimal prompt, which just tells it to use standard unix tools to do everything. I was surprised at how well it worked, when using a good model. Qwen3-coder is on openrouter, and it works well with the minimal instructions. I also tested qwen2.5-coder with ollama…
2025 · github.com · its alternatives →
- 23
- 24
A pre-execution guard that stops your coding agent running destructive commands. One shell file, no dependencies. - vandith1/agent-guard
Aug 2026 · github.com · its alternatives →
Also compare
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →