标签：#tools

Hire AI employees that live in your Slack, Teams, Telegram Discussion | Link

Installs your API into a customer's codebase in one command Discussion | Link

Turn photos into 3D Gaussian Splats on your Mac Discussion | Link

Review AI edits like stacked PRs at generation time. Discussion | Link

Session reports for Claude Code & Codex to improve your code Discussion | Link

Cloudflare Tunnels, managed from your menu bar Discussion | Link

The problem Every time I started a session with Claude Code I had to re-explain my entire project. What framework I use. How my folders are structured. What naming conventions I follow. What decisions I have already made. Every. Single. Session. It was slowing me down and I knew there had to be a better way. What I built I built stackbrief. One command scans your repo and opens a local visual dashboard showing your full codebase intelligence. npx stackbrief scan It opens a dashboard at localhost:3000 showing: Interactive code map of your architecture Dependency version comparison against npm Convention detection (naming, async patterns, error handling) Context health score MCP server so Claude Code pulls context automatically How it works stackbrief reads every file in your project and builds a structured understanding of it. It detects your framework, architecture pattern, modules, dependencies, and coding conventions. It then writes a CLAUDE.md file to your project and starts an MCP server on port 3001. Claude Code picks this up automatically before every session. No more explaining your project from scratch. AI chat that actually knows your code The dashboard has an Ask your codebase section. Unlike generic AI chat, this assistant has read every file in your project. Ask it about your own architecture and get answers specific to your code. Works with Ollama (free, fully local), Claude, OpenAI, or any OpenAI-compatible provider including Groq, Mistral, and local runners like LM Studio and AnythingLLM. Zero config, fully local No cloud. No telemetry. No account required. Everything runs on your machine. npx stackbrief scan That is it. The dashboard opens automatically. Try it GitHub: https://github.com/ragavtech/stackbrief Built with Node.js and TypeScript. Open source, MIT license. Would love to hear what you think.

File manager for Linux homelab and NAS-style servers Discussion | Link

Teach your AI to build document templates Discussion | Link

Ship AI that stays on-brand Discussion | Link

Screen recording studio for Windows Discussion | Link

I read a lot of PDFs at night, especially on my phone. And honestly, PDFs are not great for that. Most of them still feel like digital paper: white background, fixed layout, and tiny text. Dark mode helps a bit, but many tools only change the page color. The bigger problem for me was mobile reading. When the text is too small, I have to pinch zoom, move the page left and right, zoom out again, then repeat the same thing on the next paragraph. After doing that too many times, I thought: Why can’t I just read the PDF text like an article? So I built a small free tool: PDF Dark Mode It has two reading modes. Page color mode This keeps the original PDF layout, but makes the page darker and easier to read at night. I use this for scanned PDFs, tables, image-heavy documents, or files where the original layout matters. Text reading mode For selectable PDFs, the tool can extract the text and show it in a cleaner reading view. You can adjust the font size, line height, font family, and theme. This is the part I personally wanted most, because it makes mobile reading much more comfortable. Instead of constantly pinch-zooming a fixed PDF page, the PDF starts to feel more like a normal article. Privacy The tool runs locally in the browser. Your PDF is not uploaded to a server, and refreshing the page clears the current session. Try it You can try it here: PDF Dark Mode I built it for my own night reading, but I’d love to hear feedback from anyone who reads PDFs on mobile. Also, if you ever need to convert a dark PDF back to a light version, I made a related tool for that too: PDF Light Mode

Make your product bug-free Discussion | Link

All your messaging apps in one window — with private AI Discussion | Link

Save it once, never lose it again Discussion | Link

After using Claude Code, Codex, and Pi Agent for months, I wondered: how many AI agents are on my machine? I built a scanner. Here's what it found: Framework Active Archived Claude Code 192 191 Codex CLI 37 0 Pi Agent 8 sub-agents 12 scripts MCP Servers 8 - Total 448+ The Waste Duplicate calls : Same prompt → 3 agents (8-18% waste) Overqualified models : Simple tasks on expensive models (15-25% waste) Cache fragmentation : No shared prompt cache (12-20% waste) Zombie agents : Archived still indexed (2-8% waste) → 30-50% of AI API spend is wasted. The Fix AMA — Agent Management Agent bash pip install ama-core && ama scan && ama start Scans all agents across frameworks Smart routing (simple task → cheap model) Lifecycle management Local dashboard at localhost:8765 Free calculator: ama-agent-store.vercel.app/calculator MIT licensed. Feedback welcome!

Screenwriting and playwriting for movies, television, stage. Discussion | Link

Cold email infrastructure on autopilot without Gsuite Discussion | Link

host your html, share the link, and get comments Discussion | Link

Six months into running my SaaS, my "feedback system" was three browser tabs, a starred Gmail folder, and a sticky note on my monitor that said "check Discord." That was the whole system. It held together until the day I found a three-paragraph email from a paying user — a genuinely detailed feature request with a real use case — sitting unread for 24 days. His last line was: "Happy to pay more if you can support this." I replied the same afternoon I found it. His reply: "Switched last week, thanks anyway." That was the moment I stopped treating feedback management as a nice-to-have. Why the usual fixes didn't fix anything I tried the obvious things first. I want to document them because I see a lot of people cycling through the same failed solutions. Notion database 🪦 Built a beautiful one. Color-coded tags, priority columns, status tracking. It lasted 11 days before nobody — including me — was maintaining it. The friction of "open Notion, find the right database, fill in six fields" is invisible when you're designing the system and fatal when you're in the middle of a support conversation. Airtable form 🪦 Better entry point, still disconnected from where users actually were when they had feedback. Nobody bookmarks your Airtable form. They DM you on Discord and you think "I'll add that later" and you don't. Canny — this one actually worked, for a while I genuinely liked Canny. Clean interface, users could upvote requests, I could see what was popular. It felt like a real system. Then our user count grew and the pricing tier jumped. I was looking at $99/month for a feedback board for a product still finding its footing. That's not a moral judgment on Canny — it's a fair product — but for a bootstrapped indie dev, it started feeling like a tax on momentum. The deeper problem with all three solutions was the same: they were inboxes, not loops. User submits → enters the void → user never knows if anyone saw it → user assumes nobody did → trust erodes → churn. I had bui