Agent that refuses to run commands without human approval
Details
- External ID
- 47957127
- Source
- HN
- Company
- —
- Product
- Agent that refuses to run commands without human approval
- Website domain
- github.com
- Launched
- April 30, 2026
- Cohort
- —
- Upvotes
- 12
- Upvotes percentile
- 0.6446015424164524
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
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 mobile-enabled 'claw' agents being available, I decided to make Fewshell the opposite of an autonomous agent.Please star if you like, let me know what you think. Happy to answer questions.About me: I'm an ex Amazon Sr. SDE for Alexa AI, and currently am working in AI safety research for agentic RLVR. I use this tool to run and check on my lab experiments.
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Security
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- ai agent command approval system
- Manually corrected
- False
Could you build this?
Yes It is a CLI wrapper around LLM execution that intercepts proposed terminal commands and presents an interactive human-in-the-loop approval prompt before execution.
Discussion
5 comments analyzed.
Concerns raised: Sandboxing insufficient for agents needing legitimate write access (payments, DB), Per-command approval removes 90% of agent benefits, Approval prompts cause decision fatigue similar to dialog box clicking, Agents will inevitably make mistakes with production access, Risk of catastrophic failures if agent has too many permissions/tool integrations
Feature requests: Access control layer between permission grant and execution, Automatic thresholds/circuit breakers to trip on risky actions, Sandboxed/isolated environments with data replication instead of direct access
Competitors
Other products that read as similar to this one — 224 launches clear the similarity bar, closest 8 shown.
Attention rank: #87 of 225 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 157 days after the earliest competitor.
- I built a firewall for agents because prompt engineering isn't security · hn · 2026-01-19 · 7 upvotes · similarity 0.47
- Agentwall · ph · 2026-09-09 · 2 upvotes · similarity 0.45
- I spent 3 months making desktop automation stop lying to AI agents · hn · 2026-08-15 · 6 upvotes · similarity 0.45
- AILA · hn · 2026-02-16 · 5 upvotes · similarity 0.42
- AgentPort · hn · 2026-04-29 · 8 upvotes · similarity 0.42
- Clor · hn · 2026-06-02 · 11 upvotes · similarity 0.41
- Auto Mode by Claude Code · ph · 2026-03-25 · 514 upvotes · similarity 0.41
- Costanza · hn · 2026-05-06 · 5 upvotes · similarity 0.40
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.