nowfound

AI · May 20, 2026

Hiro

Your agentic security team from first commit to SOC 2

Hiro launched on May 20, 2026 with 28 votes, #837 of 20,538 launches that month and more than 95% of that year's launches.

What it does

Hiro gets your security work done. It reads findings from Aikido and Wiz, pulls open tasks from Drata, and scans Supabase, Vercel, Github, and more then ships the fixes. Not a dashboard of homework. The homework, done.

Autonomous remediation: agents find security gaps, fix them with real PRs and infra changes, and prove it with audit-ready evidence. SOC 2 included. Built for the Claude Code stack.

Hiro pulls open tasks from your compliance platform and security scanners, writes the PRs, tests the changes, deploys, and monitors the rollout. Security issues fixed while you sleep. Vanta and Drata tell you what is failing. Hiro flips them to green in a day. Hiro pulls findings from your scanners, creates a fix, and tests it before deploying to production. The report is table stakes. Hiro runs the program behind it: your stack scanned continuously, every diff reviewed, and vulnerabilities fixed on SLA. Scanners, compliance dashboards, and “AI compliance” platforms all add to your queue. More alerts. More tickets. More evidence to collect. Hiro takes the opposite bet: close the work, don’t…from hirosecure.com

Does a similar job

all alternatives →
  • Aikido Security2025 · aikido.dev · ▲856

    Secure everything you build, host, and run.

  • ZaroJun 2026 · zaro.ai · ▲399

    Build agents & apps on top of your context with one prompt.

  • AgentMicroAug 2026 · agentmicro.cc · ▲160

    Live Codex task status in your macOS menu bar

  • Codex SecurityMar 2026 · openai.com · ▲294

    Our application security agent

  • NerveDec 2025 · usenerve.com · ▲122

    Hi HN, Tanooj and Aziz here from Nerve. We’re building a work AI that handles full end to end workflows rather than just chat replies. It starts with proactively figuring out what’s important to you - anything you need to take action on or updates on any projects - and then moves all the way through the process. Nerve gathers the relevant information, drafts documents, writes jira tickets, sends emails, etc. What this looks like in practice is: say an account executive has a sales call that gets recorded into Gong, Nerve automatically picks up the call, and extracts the next steps. Users can…

  • Epismo Agent PackageApr 2026 · epismo.ai · ▲106

    Hi HN, I’m Hiroki, founder of Epismo. Every day, people share “must-use” prompts, but copying a single prompt rarely reproduces real outcomes. The missing piece is the workflow: task decomposition, step order, intermediate artifacts, and quality checks. So I built Workflow Hub, an open library of human-AI workflows you can clone and run. Each workflow includes step definitions, inputs, expected artifacts/outputs, and verification checks, so you can copy the whole process, not just a prompt. You can clone a workflow, customize it, then execute it in Epismo with the best agent for each…

More ai this month

the category →
  • Video model that turns script into viral social media videos

    AI · 18d ago · spira.ai

  • The browser where Claude Code and Codex work beside you

    AI · 17d ago · rill.love

  • Kolibri is Aleph Alpha

    AI · 19d ago · tej.as

  • Paintings by AI models: programs run through a simulation of oil paint.

    AI · 21d ago · stillwet.art

  • A real-time world model you can explore and change

    AI · 29d ago · world.pixverse.video

  • Beam.win▲377

    Run AI agents on one Mac and use its windows on another

    AI · 4d ago · beam.win

Source: Product Hunt launch ↗

Launched alongside, May 2026

the whole month →
  • Brew ▲900

    Like Claude design for email marketing

    AI · May 2026 · brew.new

  • Parallel agents, diff reviewer, and multi-model comparisons

    Dev tools · May 2026 · kilo.ai

  • StoreClaw▲806

    Grow your store profits with agents that know how to sell

    AI · May 2026 · storeclaw.ai

  • Give your agent a real number and voice to make calls.

    AI · May 2026 · pollyreach.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