Show HN: SelenAI – Terminal AI pair-programmer with sandboxed Lua tools https://ift.tt/S8BpZcv

Show HN: SelenAI – Terminal AI pair-programmer with sandboxed Lua tools I’ve been building a terminal-first AI pair-programmer that tries to make every tool call transparent and auditable. It’s a Rust app with a Ratatui UI split into three panes (chat, tool activity, input). The agent loop streams LLM output, queues write-capable Lua scripts for manual approval, and records every run as JSONL logs under .selenai/logs. Key bits: Single tool, real guardrails – the LLM only gets a sandboxed Lua VM with explicit helpers (rust.read_file, rust.list_dir, rust.http_request, gated rust.write_file, etc.). Writes stay disabled unless you opt in and then approve each script via /tool run. Transparent workflow – the chat pane shows the conversation, tool pane shows every invocation + result, and streaming keeps everything responsive. CTRL shortcuts for scrolling, clearing logs, copy mode, etc., so it feels like a normal TUI app. Pluggable LLMs – there’s a stub client for offline hacking and an OpenAI streaming client behind a trait. Adding more providers should just be another module under src/llm/. Session history – every exit writes a timestamped log directory with full transcript, tool log, and metadata about whether Lua writes were allowed. Makes demoing, debugging, and sharing repros way easier. Lua ergonomics – plain io.* APIs and a tiny require("rust") module, so the model can write idiomatic scripts without shelling out. There’s even a /lua command if you want to run a snippet manually. Repo (MIT): https://ift.tt/6jImOZM Would love feedback on: Other providers or local models you’d like to see behind the LLM trait. Additional sandbox helpers that feel safe but unlock useful workflows. Ideas for replaying those saved sessions (web viewer? CLI diff?). If you try it, cargo run, type, and you’ll see the ASCII banner + chat panes. Hit me with issues or PRs—there’s a CONTRIBUTING.md in the works and plenty of roadmap items (log viewer, theming, Lua helper packs) if you’re interested. https://ift.tt/6jImOZM November 16, 2025 at 12:58AM

Comments

Popular posts from this blog

Complete Guide to E-Commerce Business: Meaning, Models, and How to Start

Micro Niches: The Secret Weapon for SaaS Startups Struggling to Gain Traction

"From Micro Niche to Money Maker: How I Validated My E-Commerce Idea with AI (No Budget Needed)" Published: September 23, 2025 Keywords: Micro niche, AI validation, e-commerce, free tools, startup strategy Introduction Ever wondered if your e-commerce idea is worth pursuing? In this post, I’ll walk you through how I used free AI tools to validate a micro niche, build a lean store, and test demand—without spending a dime. If you’re stuck between ideas or afraid of wasting time and money, this guide is your shortcut to clarity. Step-by-Step Breakdown 1. Finding the Micro Niche Used ChatGPT to brainstorm underserved product categories. Cross-referenced with Google Trends and AnswerThePublic to check search interest. 2. Validating Demand Leveraged Perplexity AI to analyze competitors and market gaps. Ran polls using Typeform and Twitter/X to gauge interest. 3. Building the Store Created a free storefront using Shopify Starter and Canva for branding. Used Durable.co to generate landing page copy in minutes. 4. Driving Traffic Scheduled posts with Buffer across Instagram, Threads, and LinkedIn. Used Notion AI to draft blog content and email sequences. 5. Tracking Results Monitored engagement with Google Analytics and Hotjar. Adjusted product positioning based on feedback from Tally Forms. Key Takeaways Micro niches are goldmines when paired with smart AI validation. You don’t need a budget—just the right tools and strategy. Testing before investing saves time, money, and frustration. Thinking of launching your own store? Drop your niche idea in the comments and I’ll help you validate it with AI—free of charge!