Sentinelle
Autonomous offensive security, powered by AI
Sentinelle launched on May 21, 2026 with 1 votes.
What it does
I got tired of doing the same recon for the 1000th time. So I built an AI agent that does it for me and it turned out to find real bugs. In the wild: OTP bypasses, IDORs exposing millions of records, leaked credentials, Cloudflare WAF bypasses, RBAC privilege escalation, S3 misconfigurations. Full workflow: recon → exploitation → reporting. Autonomous, but with real guardrails (scope validation, blocklists, audit logs). For bug bounty hunters and pentesters. Solo built.
Sentinelle is an agentic security agent: reconnaissance, vulnerability detection and exploitation, driven end-to-end by an autonomous AI.
Sentinelle helps pentesters and bug bounty hunters focus on high-value targets instead of repetitive recon. A loop you can interrupt, redirect, re-prompt — Sentinelle is always one message away. A URL, a CIDR, a GraphQL schema. Scope is yours — Sentinelle stays in bounds. From your first mission to running pentests as a day job — every plan ships with the same agent and the same toolkit. You pay for usage, not for tools. The $0 tier is for testing and evaluation. Paid plans are priced in USD, billed monthly. Cancel anytime. Everything you need to know before launching your first mission. Another question? The blog covers the rest. AI pentesting is an end-to-end offensive security audit…from sentinel-sec.pro
Does a similar job
all alternatives →
Astra Autonomous PentestJun 2026 · getastra.com · ▲406AI agents that find, validate, and fix every vulnerability
The Autonomous StackApr 2026 · dvdshn.com · ▲65Production-tested architecture for autonomous Claude agents
Sentinel AgentOSJun 2026 · github.com · ▲2Guard+Memory+Eval—reliable, auditable, self-improving Agents
I built a firewall for agents because prompt engineering isn't securityJan 2026 · github.com · ▲7Hi 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…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 26d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 27d ago · fastrouter.ai
Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
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
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com