Adrian
The open-source runtime security toolkit for your agents
What it does
Adrian is the first open-source security monitoring toolkit that analyses not just what your agent does, but what it thinks. Based on research from OpenAI and DeepMind, Adrian installs with just 2 lines of code and applies security monitoring to your AI agents. When your agent starts looping, gets compromised, becomes misaligned or generally starts misbehaving you get notified on Slack or Discord. Adrian is free, forever, and even supports running entirely locally on your system.
Does the same job
all alternatives →
Lukan AI Agent, IDE and workstation.Apr 2026 · ▲92The open-source AI workstation for coding, ops, and life
- AUAgency – Unifying human, AI, and other computing systems, in Python2023 · github.com · ▲106
Hello hackernews! I'm excited to share a new open source python library I just released for creating AI agent-integrated systems. The name is `agency`. It differs from other agent libraries, most importantly in that it's intended to address a distinct part of the overall problem, that of agent integration. It is not an agent toolchain like LangChain and others. `agency` is a framework intended for safely integrating agents with computing systems and humans in a way that all parties can easily understand and communicate with each other. I've spent a lot of time on the readme which contains a…
- EYEnter your domain and my open-source agent will hack it2025 · github.com · ▲14
I built an open-source AI agent for security testing to find and fix vulnerabilities in your code. I’ve noticed how bad security vulnerabilities have gotten with everyone shipping AI code slop, so I wanted to build something that allows for vibe-coding at full speed without compromising security. Traditional security tools aren’t effective, and manual pen-testing can’t keep up with the rapidly growing AI code This tool runs your code dynamically, finds vulnerabilities, and validates them through actual exploitation. You can either run it against your codebase or enter your (or someone…
- OSOpen-source playground to red-team AI agents with exploits publishedMar 2026 · github.com · ▲30
We build runtime security for AI agents. The playground started as an internal tool that we used to test our own guardrails. But we kept finding the same types of vulnerabilities because we think about attacks a certain way. At some point you need people who don't think like you. So we open-sourced it. Each challenge is a live agent with real tools and a published system prompt. Whenever a challenge is over, the full winning conversation transcript and guardrail logs get documented publicly. Building the general-purpose agent itself was probably the most fun part. Getting it to reliably use…
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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com