CLRK, an open-source agent runtime with gVisor and MitM guardrails
TL;DR: we built a framework-agnostic agent runtime that uses gVisor for isolation and runs on k8s. It’s open-source under AGPLv3 Recently we’ve been working on a customer support “AI assistant” - essentially an interactive knowledge base/L1 support but with an option to touch resources that belong to a customer it’s talking to. We found existing tools to be lacking in these aspects: 1. Fully intercepted i/o. We wanted to trace out LLM calls as well as any other networking calls attempted by the harness so that guardrails and audit trails apply to all current and future systems…
What it does
In the maker’s words, at launch
TL;DR: we built a framework-agnostic agent runtime that uses gVisor for isolation and runs on k8s. It’s open-source under AGPLv3 Recently we’ve been working on a customer support “AI assistant” - essentially an interactive knowledge base/L1 support but with an option to touch resources that belong to a customer it’s talking to. We found existing tools to be lacking in these aspects: 1. Fully intercepted i/o. We wanted to trace out LLM calls as well as any other networking calls attempted by the harness so that guardrails and audit trails apply to all current and future systems uniformly. Nobody’s agent can accidentally make raw database calls or send PII data to an overseas LLM provider. 2. Coherent API and framework agnostic. There’re a lot of frameworks out there that do similar things in slightly different way and most we found had telemetry, guardrails and other tooling tightly bound into the framework. We wanted something with an infrastructure-first approach because we think it’s a more flexible way to compose such systems. 3. k8s compatible runtime. We run part of our stack on k8s and know it well so we wanted to take advantage of this if we could. We searched for an existing solution, but especially with Daytona going closed sourced recently, there were no options we could find that were open-source and met our needs, so we built one. A more in-depth design writeup can be found here: https://apoxy.dev/blog/enter-clrk Questions, FRs, hot takes or funny insults are welcome!
Does the same job
all alternatives →
Cloudways Managed AI Agents17d ago · cloudways.com · ▲84Skip the setup and run OpenClaw & Hermes, fully managed
- ARAgents, run any coding agent on your subscription not API costsMay 2026 · agents-cli.sh · ▲6
Hi HN. I'm the founder of Phoenix Labs (ex TikTok, Applied AI) and we're open sourcing our internal tooling today which is like a toolchain / meta-harness for CLI agents useful for really scaling eng and creative work. We are a very small team who's building a very ambitious product so we had to find ways to squeeze every ounce of efficiency that we could get our hands on. Harness strengths of different models (Claude, GPTs) and CLI-harnesses (Claude Code, Codex), safe/robust browser integration to speed up UX/QA testing, teams cli to speed up security reviews and parallelize…
- IBI built a firewall for agents because prompt engineering isn't securityJan 2026 · github.com · ▲7
Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…
- ACAI Coding Agent Guardrails enforced at runtimeApr 2026 · sigmashake.com · ▲5
Hello, looking for some users interested using a devtool that allows developers to centrally manage AI Coding Agent tools that supports all AI Coding Agent tools like Claude Code, Codex, Antigravity, etc. Try it free! https://www.producthunt.com/products/sigma-shake-governance-...
- IBI built an open source multi-agent harness in GoApr 2026 · github.com · ▲6
Hey HN. I built an AI agent harness over the past few months and I'm open sourcing it today. Some context on why. I've been building with Claude Code daily using this harness. It orchestrates multiple AI agents as a team, with a dashboard, chat, kanban board, the works. I used it to build a full SaaS product (MyUpMonitor, https://myupmonitor.com) in about 24 hours of focused coding. Then yesterday Anthropic announced Mythos and decided to keep it behind closed doors. Meanwhile I'm paying for Claude and I can't access their best model. I don't think that is nice at all... So I'm…
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, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
