Agent Atlas / Runtimes and workbenches

different-ai/openwork

An OpenCode-powered workbench that turns team memory, self-hosting, desktop packaging, authentication, MCP sessions, and shared workspaces into operator-visible product boundaries.

Agent workbench Scope profile Reported + sourced Reviewed August 26, 2026
Intended operator

Teams hosting and sharing coding-agent workspaces.

Primary surfaces

desktop workbench / server and self-hosting / shared workspace

Tracked repository

different-ai/openwork

Teaching mechanism

Authentication needs a resumable state, not a timeout

A sign-in flow remains pending with a claim link and explicit state instead of turning an operator action into an arbitrary elapsed-time failure.

Evidence limitA clearer state machine does not prove an identity provider, deployment, or client will always deliver the callback.
Inspect the source
System map status

Reporting is still in progress.

This scope profile names the project's place in the field and one useful mechanism. It does not claim that every runtime boundary has been inspected.

Learn Through This Project

9 lessons
Chapter 1 Before the First Model Request Chapter 2 The Invisible Prompt Chapter 3 Tool Calls: Contract, Authorization, Execution Chapter 4 Loops, Workflows, and Recovery Chapter 6 Memory Is a Typed Storage Contract Chapter 7 The Approval Trap Chapter 8 The Human Control Loop Chapter 9 Trust Must Make Its Case Chapter 10 The Future Has Three Branches

Compare Its Boundaries

7 labs
Comparison labTool ContractsComparison labGoverned MemoryComparison labApproval BoundariesComparison labHuman WorkbenchComparison labSessions And RecoveryComparison labEvidence And EvaluationComparison labMaturity Signals

Latest Reporting

8 articles
QM Drops Two Agent Loops but Keeps ChatGPT Access

October 15, 2026 — The shared workplace agent is narrowing its runtime choices to Pi and Claude. Its October 14 code change shows why keeping a model connection does not require keeping the agent software that shares its name. yc-software/qm, different-ai/openwork

 OpenWork Can Import Your Cowork Plugins and Skill Instructions

October 5, 2026 — A new migration command finds existing setup, previews the move and imports selected plugins. The useful change is less work to try another assistant—with a precise boundary around what travels. different-ai/openwork

 API Discovery: Ask OpenWork Who Needs to Sign In

September 28, 2026 — OpenWork’s new auth guide and discovery metadata let an agent distinguish starting a workspace from acting as its owner. Permission errors can now name the human handoff instead of inviting another retry. different-ai/openwork

 API Discovery: Ask Which Skills Exist Before Guessing Their Names

September 23, 2026 — OpenWork adds a direct, read-only route from a member’s permitted skill catalog to its instructions. The returned total matters as much as the list. different-ai/openwork

 The Allow Button Was Waiting for a Socket

September 17, 2026 — OpenWork reproduced a ten-second approval timeout before the user’s decision reached the engine. The repair gives that decision a separate route through a busy desktop app. different-ai/openwork

 A Computer-Using Agent Needs a Room, Not a House Key

September 7, 2026 — OpenWork’s merged macOS 14+ preview gives a desktop-driving agent one person-approved window and a short-lived native session—a meaningful boundary, but not an operating-system sandbox. different-ai/openwork

 A Child Agent’s Approval Request Shouldn’t Hide in Another Tab

September 2, 2026 — Openwork now brings a child session’s blocked permission into the parent task; fresh Goose state-machine work shows why seeing the ask is only half the control. different-ai/openwork, aaif-goose/goose

 The Last Click Shouldn’t Redirect an Automation

August 30, 2026 — OpenWork has stopped a scheduled Automation from silently following whichever workspace a person activated last; a job can now carry its intended place with it. different-ai/openwork

Primary Sources

OpenWork repository

Primary workbench and self-hosting source.

Open Questions

  • Can a team see who owns saved context, live credentials, and every shared session effect?

Evidence state describes what this Atlas profile can support today. It is not a product score and it is not evidence that uninspected capabilities are absent.