TEOS Sovereign Sentinel
ALLOW / WARN / BLOCK every AI-generated command
What it does
AI agents execute code. Most pipelines have no safety layer between generation and execution. TEOS Sovereign Sentinel intercepts every command before it runs and returns ALLOW, WARN, or BLOCK — deterministically, no LLM guessing. 27 rules. 142 scans. 19 threats blocked. Try it free → @teoslinker_bot on Telegram /scan rm -rf / → instant BLOCK, 100/100 risk score Built in Alexandria, Egypt 🇪🇬
Does the same job
all alternatives →- CPClaw Patrol, a security firewall for agentsJun 2026 · github.com · ▲112
At Deno we've been using OpenClaw and other agents increasingly for addressing production problems in Deno Deploy - when a PagerDuty alert fires, the agent starts researching the cause and making fixes. In order to do this, the agent needs access to real production systems - postgres, kubernetes, gcp, clickhouse, github, etc. But this is dangerous to say the least - we want destructive actions to be reviewed by other LLMs, approved by humans, and logged appropriately. Claw Patrol terminates TCP connections over WireGuard or Tailscale, then parses application protocols (eg http, postgres,…
- 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…
Sentinel AgentOSJun 2026 · github.com · ▲2Guard+Memory+Eval—reliable, auditable, self-improving Agents
- LCLimits – Control layer for AI agents that take real actionsFeb 2026 · limits.dev · ▲9
Prompt instructions like 'never do X' don't hold up in production. LLMs ignore them when context gets long or users push hard. Limits sits between your agent and the real world. Every action — database writes, API calls, refunds — gets intercepted and checked against your rules before it executes. Deterministically. No LLM involved in enforcement. Three modes: Conditions: hard rules on structured data Guideance: validate LLM output before it reaches the user and give the agent chance to reason and retry Guardrails: scan for PII, toxicity, prompt injection etc One line to integrate: npm…
Talos – An AI agent with a permission kernel between model and shell9d ago · talos-agent.ch · ▲14An autonomous agent you can hand a shell to. Every tool call passes a gate that grants authority for exact arguments, once, for 30 seconds — and logs the verdict.
- OSOpen-Source Gateway to Stop Tool-Abusing Prompt InjectionsOct 2025 · archestra.ai · ▲9
Hi HN, Matvey, Ildar, Joey, and Dominik here. If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools. We were too, and found that solutions like prompt-based filtering or secondary "guard" LLMs can be unreliable. Our thesis is that agent security should be handled at the network level between the agent and the LLM, just like a traditional web application firewall. So we built Archestra Platform: an open-source gateway that acts as a secure proxy for your AI agents. It's designed to be a deterministic firewall against…
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