InsForge – Open-source agent-native alternative to Supabase
Hi HN, we just released InsForge: an open-source, agent-native alternative to Supabase/Firebase designed from the ground up for AI coding agents like Cline, Cursor, and Claude Code. We're building Supabase's features in an AI-native way, enabling agents to build and manage full-stack applications autonomously. (GitHub: https://github.com/InsForge/InsForge) With coding agents, coding is actually the easy part now. You can build a working prototype for your idea in a few hours and run it locally. But to make it production-ready, you still have a long list of things to…
What it does
In the maker’s words, at launch
Hi HN, we just released InsForge: an open-source, agent-native alternative to Supabase/Firebase designed from the ground up for AI coding agents like Cline, Cursor, and Claude Code. We're building Supabase's features in an AI-native way, enabling agents to build and manage full-stack applications autonomously. (GitHub: https://github.com/InsForge/InsForge) With coding agents, coding is actually the easy part now. You can build a working prototype for your idea in a few hours and run it locally. But to make it production-ready, you still have a long list of things to do manually, which might take a week or so: 1. Get API keys for external services 2. Set up authentication 3. Configure a database and storage 4. Add payments 5. Set up a custom domain 6. Deploy on Vercel And none of these is really "coding." It's just you switching tabs, opening dashboards, copying tokens, pasting configs. The interesting part is your agents know exactly what to do. They can walk you through every step - "go to this URL, click that button, paste this key" - but they can't actually do it themselves. Why can't you just do it for me? Because all of these backend/devops platforms and services were built for humans, not for agents. So we built InsForge. We built an MCP Server as middleware and redesigned the backend API to give agents persistent context, so they can: 1. Learn how to use InsForge during the session (re-check documentation if needed) 2. Understand the current backend structure before making changes, so configurations are more accurate 3. Make changes, debug, check logs, and update settings on their own Example: you type "help me build an Instagram clone social media app" in your Cursor/Claude Code, then it will communicate and configure the entire backend on InsForge: - Auth: Google + email/password login - Database Tables: users, posts, comments, likes, profiles - File Storage Buckets: avatars, post-images And then it will write the fullstack application without you doing anything. You stay in your IDE or agent interface, focus on writing prompts and QA-ing the result, and let your agent handle the rest. This is an early release, and we'd appreciate feedback from the community. Try it out and let us know what breaks or what features you'd want to see. We're trying to make prompt-to-production a reality! P.S: In the coming weeks (by the end of August), we'll be launching a few new features: - Cloud Hosting Platform - Serverless Functions - Site Deploy We'll be around in the comments!
Does the same job
all alternatives →- IOInsForge – Open-source Heroku for coding agentsMay 2026 · github.com · ▲62
Hi HN, I'm Hang, cofounder of InsForge (YC P26). InsForge is an open-source Heroku for AI coding agents: a backend platform designed for coding agents to deploy, operate, and debug end-to-end. Open source under Apache 2.0 (https://github.com/InsForge/InsForge). Quick demo here (https://youtu.be/7Bax5qz0IfM). We started InsForge because we just wanted our Claude Code to handle all the backend / infra stuff for us, instead of us jumping between dashboards doing manual config, or copy paste logs and docs back to agents. We first tried creating a folder…
- NONous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI2024 · github.com · ▲155
Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
Supafork – Share and Fork Sessions Across Harnesses5d ago · supafork.com · ▲15Supafork is the AI Agent Native Version Control system, Git built for autonomous agents. Super-fast forks, instant branches, S3-backed agent filesystems, and full env control. Faster than Mesa, more agent-native than Archil. Track every change your agents make. Now the source of truth for your agent
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca