OpenOrg

Build your knowledge locally and put it to work.

OpenOrg is a local-first workspace where your notes, decisions, commitments, and agent work become durable follow-through. Use the agent, model, or provider you choose while your knowledge stays in files you control.

From decision to done.

Start with a meeting, note, message, or TODO. OpenOrg keeps the source context attached while the work moves, and interrupts you only when a decision needs you.

Capture

Keep the decision, commitment, and exact source together.

Delegate

Send bounded work to a person or any configured agent, local or remote.

Review

Bring consequential actions and uncertain results back for approval.

Verify

Record the outcome and its evidence where the work began.

One place to see what is moving.

Plan your own work, follow delegated work, review decisions, and keep the underlying context intact.

OpenOrg Agenda showing launch readiness tasks and linked context
Know what you promised, what is due, and the context behind each item.
OpenOrg Agent Work showing an approval-ready delegated launch brief
See what agents are doing, what needs you, and what finished with evidence.
OpenOrg meeting surface with a beta review transcript and summary
Turn conversations into source-backed decisions and follow-through.
OpenOrg rendering a launch-readiness data notebook with an interactive chart
Data notebooks: keep materialized results, freshness metadata, and interactive charts beside the notes that use them.
OpenOrg shared AI room showing two configured agents answering the same launch question
Multi-agent chat: ask named local or remote agents—or @all—and compare independently attributed answers in one shared thread.
OpenOrg approvals list on iPhone showing review-required corpus items
Mobile approvals: review generated drafts and approval-gated work from the phone.

Work ends in something useful.

OpenOrg keeps finished artifacts connected to the decisions, data, and source material that produced them.

Talks and slides

Develop a talk beside its research, preview it as slides, and export a presentation-ready PDF.

Analytics and visualizations

Query data, materialize reviewable results, and publish tables and charts with freshness and provenance intact.

Customer-ready PDFs

Turn approved source material into quotes, reports, and marketing collateral without losing the evidence behind it.

What an Org2 file looks like

One plain-text document can carry notes, tasks, dates, links, data records, source provenance, and agent handoff boundaries while staying readable in any editor.

notes/product-launch.org2
#+title: Product launch workspace
#+filetags: :launch:q3:
#+roam_aliases: beta launch rollout

* TODO Ship beta checklist :product:
  SCHEDULED: <2026-06-01 Mon>
  DEADLINE:  <2026-06-12 Fri>
  :PROPERTIES:
  :ID: launch-beta-checklist
  :EFFORT: 3h
  :OWNER: Product
  :END:

  - [X] Draft invite copy
  - [ ] Confirm onboarding path with [[id:design-review][design review]]
  - [ ] Publish release notes from [[file:release-notes.org2][release notes]]

** Meeting notes
  Decisions:
  - Keep beta small until support docs are complete.
  - Track follow-ups in the same file as the project plan.

** Source query for docs
  ``` sh
  org2 query --tag launch --format json
  ```

** Launch readiness data :evidence:
  :PROPERTIES:
  :ID: launch-readiness-data
  :KIND: dataset
  :END:

  ```dataset launch_readiness
  type: csv
  path: data/launch-readiness.csv
  engine: duckdb
  ```

  ```sql results=launch_readiness_summary artifact=views/launch-readiness.org freshness=24h
  SELECT week, activated_users, blocker_count
  FROM launch_readiness
  ORDER BY week DESC
  ```

** TODO Summarize launch blockers
  :PROPERTIES:
  :ID: launch-blocker-summary
  :ASSIGNEE: research-agent
  :STATUS: ready
  :CONTEXT: id:launch-beta-checklist, id:launch-readiness-data
  :END:

  Summarize launch blockers with citations.

* AI draft summary :draft:
  :PROPERTIES:
  :ORG2_ARTIFACT_ROLE: view
  :ORG2_PROVENANCE: file:raw/calls/beta-kickoff.org2, id:launch-readiness-data
  :ORG2_CLAIM_STATE: source-backed
  :ORG2_REVIEW_STATUS: review-required
  :END:

  The beta should emphasize local files, agenda workflows,
  and source-backed AI summaries.

A durable follow-through system

Most second brains help you find what you knew. OpenOrg also tracks what you decided, who or what is acting on it, which decisions still need you, and what evidence proves the work finished.

Your files are the source of truth. Apps and agents share the context, people keep clear review boundaries, and your work stays portable across models, agents, and clients.

What you can do with it

  • Turn commitments into follow-through without separating them from the conversation or document that created them.

  • Delegate across people and agents while keeping responsibility, progress, and context visible.

  • Review the decisions that matter in one approval queue while routine agent steps continue in the background.

  • Produce useful artifacts including talks, analytics, visualizations, reports, PDFs, and published sites.

  • Keep durable memory that people can read, agents can cite, and no single model or application owns.

Private-by-default agent collaboration

A useful agent workspace needs precise sharing boundaries. OpenOrg keeps files local by default and can encrypt individual subtrees to you, a device, or a specific agent key. Encrypted notes are ordinary files that can sync through Git, iCloud, Syncthing, or any transport you choose.

How it works

OpenOrg reads ordinary .org and .org2 files through the Org2 compiler, which turns tasks, links, dates, properties, provenance, and agent boundaries into one shared semantic model. The native workspace, editors, CLI and MCP clients, runtime adapters, and configured models all work from that same source-backed context.

The result is deliberately boring composability: inspectable files that can drive daily planning, agent workflows, data views, and publishing without locking the work into one application.

Start here

OpenOrg Alpha is for technical founders, operators, and knowledge workers who want agents working over files they own. Org2 provides the open format, compiler, CLI, and editor tooling underneath the workspace.

Reference post: Standalone Org rationale

Repository