Guardana
Customizable security gates for AI systems
What it does
Guardana is an open-source AI security framework built to adapt to your system. Use 47 built-in checks or add your own YAML/Python rules, evaluators and targets for application-specific risks. Scan artifacts, probe models, agents and MCP servers, analyze real execution traces and block releases on security regressions. Run it locally, in pytest or CI/CD — no mandatory cloud, account or telemetry.
Open-source AI security verification. 51 checks across model artifacts, live endpoints, MCP servers and real execution traces — identity, credentials, scopes, approvals, memory and side effects. Then add the rules only your team can know about, without forking.
Guardana scans model artifacts, probes live endpoints and MCP servers, and grades the execution traces your agents already produced — identity, credentials, scopes, approvals, memory and side effects. 51 checks to start; you add the ones only your team can know about. Built to be the thing a pipeline blocks on: a cost you know in advance, a run you can compare against last week, and an unanswered question that never reads as a pass. or pip install guardana-cli — Apache-2.0, runs fully offline. config.json names a Hub kernel repo transformers imports on load Static checks are deterministic — no model, no network, no false-positive theatre. Dynamic checks talk to a live endpoint and are…from guardana.dev
Does the same job
all alternatives →
- WPWe post-trained a model that pen tests instead of refusingJun 2026 · argusred.com · ▲93
Anthropic and OpenAI's publicly available models are explicitly guard-railed so that they refuse offensive tasks. And their cyber-focussed models are gated for enterprises. This leaves SMEs and mid market open to major vulnerabilities. AI can be used as both an adversarial and defensive tool in the world of cyber. A worst case outcome is if only the adversaries have access. Meanwhile, most existing AI cyber tools are just wrappers. The problem is that they still have all the guardrails on from the foundation model where they will inherit its refusals. For this project we've post-trained a…
- AegisoraAug 2026 · aegisora-ai.vercel.app · ▲93
The narrow control plane for AI agent tool and API calls.
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 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