Open-source AI workflows with read-only auth scopes
Hey HN! I'm Akshay, and I'm launching Seer - yet another AI workflow builder with granular OAuth scopes. GitHub: https://github.com/seer-engg/seer Demo video: https://youtu.be/cmQvmla8sl0 The Problem: We've been building AI workflows for the past year and kept running into the same issue: existing platforms (n8n, Langflow, Flowise) require full access to your Google services even for read-only operations. Want to summarize emails? You're also granting send permissions. Want to read docs? You're also granting edit permissions. If you want granular scopes,…
In plain words
Seer is an open-source AI workflow builder that allows users to automate tasks involving external services like Google with granular OAuth permission scopes. Unlike existing workflow platforms that require full access permissions, Seer lets users grant only the specific read or write permissions needed for each task. It is designed for developers who want to build AI workflows without over-provisioning access to their integrated services.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! I'm Akshay, and I'm launching Seer - yet another AI workflow builder with granular OAuth scopes. GitHub: https://github.com/seer-engg/seer Demo video: https://youtu.be/cmQvmla8sl0 The Problem: We've been building AI workflows for the past year and kept running into the same issue: existing platforms (n8n, Langflow, Flowise) require full access to your Google services even for read-only operations. Want to summarize emails? You're also granting send permissions. Want to read docs? You're also granting edit permissions. If you want granular scopes, the onus is on you to: - Create your own OAuth app with Google (1-2 weeks approval time) - Modify source code to support read-only scopes We saw this pattern repeated across Discord channels and GitHub issues - developers asking for better scope support, maintainers saying "you can configure it yourself." Our Solution: Seer ships with read-only auth scopes as the default for common operations. It's self-hostable, so your data never leaves your infrastructure. The demo shows a simple email summarization workflow (Gmail + LLM API), but the principle applies to any integration. Why This Matters: Security through least privilege isn't just best practice - it's essential when you're giving AI agents access to your production data. One compromised workflow shouldn't mean your entire Google Workspace is at risk. Questions for HN: 1. How are you currently handling OAuth scopes in your AI automation workflows? 2. Would you find value in a scope validator that audits your existing workflows? 3. What other integrations would you want to see with granular permissions? The only similar platform with granular scope support is Make.com, but it's closed-source. We think this should be the standard, not the exception. Would love your feedback!
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 · 26d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
