atom

From instructions to finished work

Atom is a locally run AI employee workspace. Teach an employee your business rules, supply company data, and ask it to calculate, assess or prepare a deliverable. When a field or instruction is ambiguous, it asks. When work must wait, it saves its state so you can leave and continue after a restart.

• Teach and correct. Save contextual lessons, field mappings, document formats and email protocols. New work adopts corrections; active work keeps its accepted teaching snapshot.
• Work with unfamiliar data. Upload CSV/XLSX files, confirm ambiguous column mappings, calculate against source records and produce cited DOCX/PPTX output.
• Turn policy into repeatable decisions. Author ordered rules in the canvas editor. Supported deterministic rules preserve unresolved requirements rather than inventing an approval.
• Keep work moving. Durable questions, approvals and waiting states survive restarts. Completed operations are preserved and uncertain effects require reconciliation before another attempt.
• Choose your model. Configure your own provider in Settings or use a local OpenAI-compatible endpoint. The sample below needs no model or cloud key.

Try Atom locally

Prerequisites: Git, Make, Python 3.11–3.13 (3.11 recommended), Node.js 20.9+ and npm. Python 3.14 is not supported by this dependency set.

git clone https://github.com/rush86999/atom.git
cd atom
PYTHON=python3.11 make setup
make dev

In a second terminal, from the same atom directory:

make sample

Open http://localhost:3001. Sign in as [email protected] using the generated password in backend/logs/bootstrap_admin_password.txt. Open Assignments to find the completed sample and download its Word document.

Your first result: Sample Quote Analyst reads sample-workspace/sample_quote.csv, calculates 232990.00, and creates a DOCX. Its lessons are editable under Agents → Sample Quote Analyst → Training. The sample uploads local data and creates local records/artifacts; it sends no email and needs no connected account or cloud credential.

If the default ports are busy, use the same pair for startup and the sample:

BACKEND_PORT=8101 FRONTEND_PORT=3101 make dev
# Second terminal:
make sample PORT=8101 FE_PORT=3101

Then open http://localhost:3101. Stop the development processes with Ctrl+C; restart with make dev against the same checkout to keep your local data. Do not delete the database or generated keys to troubleshoot an existing install.

Measured first use: approximately 5 min 15 s on one fresh-worktree run with warm package caches, including setup, startup, sample and browser access. 15 minutes is a cold-install target, not a measured guarantee. See the setup guide and measured first-use record.

See what an employee can do

The demo guide distinguishes reproducible steps from historical runs and lists their exact sources. The two-hour run is elapsed/recovery evidence on its recorded source; later budget repairs have their own focused verification.

What you can rely on

111 of 123 frozen functional claims (90.2%) were accepted within the documented local and controlled-provider configurations. This is a source-bound feature coverage milestone, not a promise of 90% accuracy or universal reliability.

To use the fixed snapshot rather than development main, run git checkout successor-first-use-2026-11-01 before make setup.

Clear boundaries

• The demonstrated local topology is single worker. Multi-worker execution and long soak behavior are not qualified.
• The sample and main acceptance campaigns use local or controlled providers. Deterministic taught policy is qualified separately from discretionary model judgment; the tested small-model judgment configuration failed qualification.
• One specifically authorized Outlook send and Microsoft read-only ingestion were separately qualified. That does not qualify every connector, broader live sending, autonomous live sending or independent recipient delivery.
• Supported workbook formulas and taught schemas are bounded. Arbitrary Excel compatibility, arbitrary schema understanding and UI-taught rounding are not promised.
• The broader platform includes workflow, routing, graph, governance and integration surfaces. Some need ATOM_PRODUCT_PROFILE=full, a configured provider or additional infrastructure. Consult the inventory before relying on a particular feature.

Connect your own data and models

After the sample, open Settings to configure a provider and the connections you need. Provider usage and connector access depend on your account and permissions. Keep credentials out of issues, screenshots and commits.

For local inference, see Run with Ollama. For connected Office work, see Office automation and OAuth setup. Local storage does not make cloud inference private: data sent to a configured provider follows that provider’s terms.

Documentation and contributing

• Documentation hub · Quick start
• Verified workflow walkthroughs
• Troubleshooting
• Architecture · Security boundaries
• Brennan business-workflow engineering orders
• Contributing · Open an issue

For a useful bug report, include the commit/tag, operating system, launch command, expected result and a minimal sanitized example. Please do not include passwords, tokens, private documents or your database.

Atom is already public on GitHub under AGPL v3. Hosted deployment is separate from the verified local setup. If this project helps your work, star the repository, try a real workflow and tell us where it gets stuck.