ClawShell
The Runtime Security Layer OpenClaw needs
What it does
OpenClaw is powerful because it operates with real credentials to perform real work. That same power makes it an attractive target. So we built ClawShell. It assumes agent execution is adversarial by default. Secrets are isolated behind a separate privileged process, enforced at the OS level. Even if the agent is fully hijacked, it only sees virtual identifiers. Onboarding takes less than a minute and requires no changes to OpenClaw. Apache 2.0 licensed. Written in Rust.
Does the same job
all alternatives →
- NCNanoClaw – “Clawdbot” in 500 lines of TS with Apple container isolationFeb 2026 · github.com · ▲533
I’ve been running Clawdbot for the last couple weeks and have genuinely found it useful but running it scares the crap out of me. OpenClaw has 52+ modules and runs agents with near-unlimited permissions in a single Node process. NanoClaw is ~500 lines of core code, agents run in actual Apple containers with filesystem isolation. Each chat gets its own sandboxed context. This is not a swiss army knife. It’s built to match my exact needs. Fork it and make it yours.
- CPClawShell, Process-Level Isolation for OpenClaw CredentialsFeb 2026 · github.com · ▲10
Hi HN, I’ve been using OpenClaw daily since it dropped in November. I love the agency it provides, but as I started giving it more production API keys and access to my local filesystem, I realized the threat model was essentially "hope-based." We ran an experiment to see how resilient a standard OpenClaw setup was to prompt injection. Within 2 mins, we were able to exfiltrate active session tokens and API credentials through the chat interface. The problem is fundamental: in most agent architectures, the LLM logic and the sensitive credentials live in the same process space. If the agent is…
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
