AI agents for the mainframe.

Zcrafter builds collaborative bots and the RL environments that train them.

Request access (opens in a new tab)

Backed by

  • Claude for Startups
  • Cloudflare for Startups
  • 1871 Chicago
  • The Linux Foundation
  • Open Mainframe Project

Our software

Cobots

A team of agents that works on your mainframe. Every change waits for your approval.

See Cobots

Bench

Reinforcement-learning (RL) environments where agents practise mainframe work and are scored on the result.

See Bench

Cobots: a team of agents on your mainframe.

Reads run now

Agents list datasets, browse members and read spool on their own. Reading changes nothing.

Cobots: the z/OS Systems agent has listed six datasets in the chat, with the mainframe screen and the two commands it ran beside it
Changes wait for you

Edits, job submits and console commands stop at an approval card that shows the exact change.

Cobots: an approval card from the COBOL Dev agent showing the one line it wants to add to a member, where the old version will be kept, and the buttons Allow once, Edit and Deny
Every screen, in the open

Each agent has a live 3270 screen and the list of commands it ran, in order.

Cobots: the Batch Ops agent’s mainframe screen opened large, showing the job log of a job that ended with condition code 0000
Yours to run

A desktop app for macOS and Windows. Passwords stay in your keychain. Bring your own model.

Cobots: the Models settings, with OpenAI Codex and Anthropic connected, other providers and a self-hosted server offered, and a list of Claude models to choose from

Bench: RL environments where agents learn the job.

Task environments

Isolated, resettable tasks with COBOL, JCL, datasets, jobs and failures. Two attempts face the same conditions.

An example task: payroll abend recovery

StartPAYRUNABEND S0C7
The agentFinds the faultand fixes it
GoalPAYRUNCC 0000

The system is reset before every attempt.

Controlled tools

TN3270, MCP and APIs for inspecting state and acting. The tools enforce permissions, not the model.

What the agent may use

Allowed

  • Read datasets, spool, jobs
  • Edit PAY.TEST.**
  • Submit PAY.TEST.JCL

Denied

  • PAY.PROD.**
  • Console commands
  • Security changes
Deterministic rewards

Correctness, safety and efficiency, checked on the system. The same outcome always scores the same.

How an attempt is scored

  • CompiledPAYCALC builds
  • CompletedPAYRUN ends CC 0000
  • Correctthe report matches
  • Containedprotected datasets unchanged

Reward4 of 4

Agent trajectories

Observations, tool calls, state changes and outcomes, recorded. How a result was reached matters as much as the result.

One attempt, as recorded

  1. observePAYRUN abends, S0C7
  2. toolRead PAYCALC
  3. toolRead TIMECARD
  4. changeEdit PAYCALC
  5. toolSubmit PAYRUN
  6. outcomeCC 0000

Bridge: an open-source MCP server for z/OS.

One line to install

Use the AI agent you already have. Nothing is installed on the mainframe.

How it connects

Your AI agentClaude, Codex, Cursoror any MCP client
On your machineBridge48 tools, one gate
Your mainframez/OSthrough z/OSMF

Installuv tool install zcrafter-bridge

48 tools

Datasets, members, jobs, spool, z/OS UNIX files, TSO and the console.

What an agent can work with

  • 11Datasets
  • 7Members
  • 15Jobs and spool
  • 7z/OS UNIX files
  • 3TSO and console
  • 5System

23 read. 25 change the system, and wait for your yes.

You approve every change

Reading is free. A change runs only if it is a step in a plan you approved.

What you are asked

Approve this plan?

  1. member.patchPAY.TEST.COBOL(PAYCALC)
  2. job.submitPAY.TEST.JCL(PAYRUN)

ApproveReject

Only these two steps can run. The agent cannot approve its own plan.

Open source

MIT licensed. Passwords stay in your keychain and never reach the model.

Where to get it

Technical overview

How Cobots and Bench are built, hosted and secured.

PDF, 4 pages. November 2026.

Read the overview (PDF, opens in a new tab)
The first page of the technical overview: the Zcrafter logo, the title, the date and the abstract Its second page: an approval card in Cobots and a diagram of the parts of the app Open the technical overview (PDF, opens in a new tab)

Research

Design notes on RL environments, evaluation, and mainframe interaction.