Aegis
Verify security-sensitive code changes before they merge
What it does
Aegis is trust infrastructure for software and AI agents. It keeps findings, evidence, remediation, independent verification, policy, and security memory separate so security-sensitive changes can be reviewed with proof, not optimism. Start with a browser-local Snapshot, then move into Attack Graph, Threat Model, Secure Fix, Fix & Prove, Trusted Analysis, and policy-backed decisions across VS Code, GitHub Actions, and local workflows.
Aegis independently verifies security-sensitive software changes today, and is evolving toward trust infrastructure for software and AI agents.
Today, Aegis independently verifies security-sensitive software changes: what was claimed, what evidence supports it, what was authorized, and whether the resulting change actually held. Install the extension, open your code, and run a scan. Community works without creating a website account. Install Aegis from the VS Code Marketplace. No web signup is required to start with Community. Open a file, select code, and run Fast Scan. Workspace and dependency scans broaden coverage when you need them. Aegis connects findings to evidence, attack paths, threat reasoning, and verification state so you can see why a claim should be trusted. Paid and provider-backed analysis is optional. GitHub…from aegistrustlayer.com
Does the same job
all alternatives →- AegisoraAug 2026 · aegisora-ai.vercel.app · ▲93
The narrow control plane for AI agent tool and API calls.
- AAAegis – A framework for AI-governed software development2025 · github.com · ▲5
Hey HN – I built a framework called Aegis to govern AI-assisted software development. The core idea is that AI-generated code should follow the same rules as human code: versioned, validated, observable. Aegis enforces this through blueprint-based development, drift detection, and runtime compliance systems. It’s designed for teams using tools like Copilot, Kilo, or Lovable to build production systems with confidence. This isn’t a library — it’s a way to architect AI-native engineering workflows. Would love feedback, questions, and critiques. Especially curious if others are facing similar…
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, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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