Analyse first
Inspect the objective and project, identify the real work, choose the intelligence required and estimate the likely spend before execution starts.
Pixelhatch productFree public beta · v0.8.0
Coding agents are powerful. Their allowance isn't endless.
Helm is a local intelligence-control and continuity layer for coding agents. Give it the job, let it work out how much intelligence each part deserves, then approve the plan before anything runs.
macOS UniversalWindows 10/11 x64Node.js 20+ requiredOpenAI Codex CLI required
Intelligence controlForecast. Approve. Execute.
Why Helm exists
A coding job is rarely one level of difficulty.
A repository inspection, a routine file change and a difficult architecture decision should not automatically consume the same level of intelligence. Helm treats the job as a sequence of technical work rather than one giant model choice.
It analyses the objective, preserves any stages or constraints you explicitly supplied, creates internal execution steps where it needs them, and assigns model capability and reasoning effort stage by stage. Stronger intelligence is used when the evidence warrants it, not simply because it is available.
Helm is not a general chatbot. It is built for coding agents and technical agents that actually inspect, edit, test, debug, deploy and operate against real projects.
How it works
Give Helm the destination. It works out the route.
You do not need to write an orchestration spec to use an orchestration tool.
Example objective
“Build me a website for my cookie shop. Use Astro, set it up in GitHub, choose the right hosting for online ordering, deploy it, and make sure everything works.”
Helm can turn a normal objective like that into the technical work required to complete it. If you do provide explicit stages, Helm preserves them instead of inventing a different structure.
Route intelligence
Use cheaper capable models for routine work and stronger reasoning where complexity, risk or evidence genuinely justifies it.
Verify the work
Run tests, inspect evidence and repair failed work instead of treating a model response as proof that the job is finished.
Protect continuity
Watch live provider capacity, preserve enough allowance to stop safely and keep the job resumable when the coding agent reaches its limit.
Analyse job
See the plan before you spend the credits.
Analyse job is the planning gate. Helm reads the objective and project, works out what needs doing, forecasts the coding-agent workload and compares it with live provider capacity before you approve execution.
Project and objective inspectionModel capability + reasoning allocationEstimated credit-equivalent spendLive Codex 5-hour and weekly capacityExplicit approval before execution
Continuity failsafe
Running out of coding-agent capacity should not mean losing the job.
Helm watches provider capacity while work is running. At the warning threshold it tells you the margin is getting tight. At the protected reserve it stops before starting another expensive turn and leaves the project in a state that can be continued safely.
10%
Helm warns that the limiting provider window is approaching the reserve.
5%
Helm protects the final reserve and does not start another coding-agent turn.
Handoff
The execution position, project path and local handoff are preserved. Helm generates a compact prompt for continuing the technical job in ChatGPT if you want to keep moving.
Reset
When coding-agent capacity returns, the saved Helm job can continue from the recorded position instead of repeating completed work.
Local first
Your project remains the source of truth.
Helm runs locally, keeps its run metadata local and points continuation back to the project you already have. It does not copy your repository into some second Helm workspace just to create a handoff.
Project filesStay on your machine
Helm run stateStored locally
Coding providerReceives the context required to perform the job
Pixelhatch telemetryNone in the public beta
Download + install
A beta you can launch like an app.
No Terminal command is required to launch Helm after installation. The current beta is unsigned, so macOS and Windows may ask you to approve the app the first time.
macOS
Universal build
- Download the macOS ZIP and unzip it.
- Drag Helm.app into your Applications folder.
- Open Helm once. Because this public beta is not yet signed and notarised, macOS may block the first launch.
- If it does, open System Settings → Privacy & Security, scroll to the Security section, then click Open Anyway next to Helm.
- Confirm Open when macOS asks again.
- After that, Helm is approved on your Mac and you can launch it normally from Applications or keep it in the Dock.
Why am I seeing this? Helm is currently a public beta and has not yet been signed and notarised with Apple, so macOS may ask you to approve it manually the first time. A normally signed release is planned.
Download macOS UniversalWindows
Windows x64
- Download the Windows ZIP and unzip it.
- Double-click Helm.exe.
- If Microsoft SmartScreen appears on this unsigned beta, choose More info then Run anyway.
- Helm starts its local interface and opens it in your default browser.
Before you start
Helm currently expects the coding toolchain to already be available.
- Node.js 20+ installed.
- OpenAI Codex CLI installed and signed in for Codex jobs.
- Git strongly recommended so project changes remain easy to inspect and recover.
- Keep important work under version control. Helm is beta software and can instruct coding agents to edit files and run commands.
Questions
The useful bits before you install it.
Does Helm replace Codex?
No. Helm sits above the coding agent. Codex still performs the technical work; Helm plans, routes intelligence, watches capacity, verifies execution and preserves continuity.
Do I need to write stages into my prompt?
No. A normal objective is enough. Helm can create its own internal execution structure. If you explicitly provide stages, milestones or constraints that matter, Helm preserves them instead of silently replacing them.
Is Helm for ordinary ChatGPT questions?
No. Helm is designed for coding agents and technical task-running agents working against projects, repositories, files, tests, deployments and infrastructure. It is not intended to route basic chat.
What happens if my Codex allowance resets?
Helm keeps the paused run state locally. Once the limiting provider window has recovered beyond the protected reserve, the job can be continued from its recorded execution position rather than started again.
Is the public beta free?
Yes. Helm v0.8.0 is a free public beta while Pixelhatch tests the routing, forecasting and continuity system across a wider range of real coding-agent workloads.