atoma

Watch a request turn into finished work.

Ask for a drawing, a sound, a report, a data study, a proof or a piece of software. atoma coordinates AI agents to produce it, checks the result against what you asked for, and lets you inspect every step. The bounded decisions along the way, such as which agent takes a task or whether a plan is approved, are taken by TypeSafe's Jev.

Open atoma.run →

Demo · Use cases · A run, step by step · Features · How it works · Self-host · Documentation

Warning

atoma is under active development. Organisations are designed to be isolated from one another (projects, workspaces, traces and previews), but the platform has not been independently audited and we cannot yet guarantee that isolation, or the absence of other security defects, under every condition. Do not include confidential, personal or otherwise sensitive data in your goals, uploaded files or generated applications, whether on atoma.run or on a self-hosted instance exposed to others. Use the hosted service to evaluate the product, not to process data you could not afford to see leak. See SECURITY.md to report a vulnerability.

Watch the demo

atoma-demo-2026-09-26.mp4

From a business need to a tool you can use

An operations team needs a dashboard. An agency needs a client demo. A product team needs an API prototype. atoma turns those requests into software: web applications, HTTP APIs, command-line tools and their technical documentation.

Start at atoma.run. The web console brings projects, AI execution, acceptance criteria, result previews, model choice and run history into one place. This repository contains the open-source engine and console for teams that want to inspect, extend or self-host them.

What could your team build?

These are example project briefs, not prebuilt industry integrations or customer deployment claims.

Team or industry	Example project	What it helps you do
Agencies & consulting	An interactive client demo or project estimator	Turn a proposal into something a client can try
Retail & e-commerce	A sales dashboard from exported CSV files	Explore product performance and share a clear view with the team
Logistics & operations	An inventory viewer or shipment-status prototype using sample data	Test a workflow before connecting operational systems
SaaS & product teams	A web app prototype or HTTP JSON API	Explore a feature and hand working code to engineering
Data & engineering teams	A CSV-to-JSON CLI, validation utility or technical documentation	Package a repetitive task into a reusable tool

For example:

Build a sales dashboard that lets me upload a CSV with date, product, region and revenue columns. Add filters, monthly totals and a chart by region. Include sample data and instructions to run it locally.

A run, step by step

1. Open Projects → Talk to Atoma, or connect your existing agent through MCP from Settings. Describe the project you want to create or the change you want to make. The integrated assistant uses the saved project brief and latest run to prepare a proposal.
2. Review the agent's proposal for a new or existing project, the run goal and optional acceptance criteria. In the integrated assistant, creation and run launch have separate confirmation buttons. Both use the existing MCP. Without criteria, the run drafts its own checklist from the goal.
3. Follow the run as agents plan, write files, start servers and check their work, with the model, tokens and cost behind every step.
4. Preview web results in a temporary, isolated environment, including a snapshot while the run is still building.
5. Keep the deliverable, with its verification record, and publish it to a connected GitHub repository. The project's next run continues from it; a project imported from GitHub starts each run from its default branch.

Previews are review environments; deploying the generated application is a separate step. Project runs use the configured model accounts and consume model quota or incur API charges.

See what ran, what was checked, and where model usage went.

Filter the timeline to LLM calls: the model, tokens and cost behind each step.

Features

Acceptance criteria you approve before launch

A project run can carry up to twelve criteria, supplied through MCP or the CLI (--criteria <file>). A line such as GET /api/items is an HTTP check; any other line is judged by review. The host stores the list before planning starts and nothing can change it afterwards. The planner is told the user wrote it, and the final check is told which HTTP checks were actually observed on servers the run itself started.

Without a list, the run drafts one from the goal with a single call to the cheapest model. A drafted list can only add to what the final check looks for; it can never make a run pass.

Finished work is never thrown away

A run that exhausts its budget after completing at least one phase, or whose result the final check refuses after one remediation attempt, is kept as incomplete rather than discarded — including when the deadline falls while its finished work is still being checked. Its finished phases stay in the workspace, and the console explains in plain language why it stopped and what to do next, with the technical reasons one click away. In a project created in atoma, the next run starts from that workspace and is told why the previous one stopped; a project imported from GitHub starts each run from its default branch, so unpublished changes are not carried over.

Choose the models, then compare them

Each tier (workers, supervisors, planners) takes its own model selector, of the form <api|sub|own>:<vendor>:<model>, across Anthropic, OpenAI, Google DeepMind, xAI, Meta, Mistral, Alibaba Qwen, DeepSeek, Moonshot, Z.ai and a self-hosted Ollama: api: bills a key, sub: the host's Claude or ChatGPT subscription, and own: the member's own ChatGPT account, whose available models Settings lists, or their own Claude Code token (beta). The operator can delegate the host subscription to named members without making them administrators. The offered models and their per-token prices are one versioned file, src/core/modelCatalog.json, kept current with npm run models -- refresh: prices are a dated history, so a vendor's change applies from its day without re-pricing what came before.

Every run records the models it was pinned to and the models the provider actually served. A delivered or incomplete run of a project created in atoma can be rerun on other models through the API or MCP: same goal, same acceptance criteria, same starting workspace. The rerun sits beside the project's history, so you can compare cost, time and result; it never publishes and never seeds a later run.

Start from your repository, publish back to it

Install the GitHub App to import a repository into a project or create a new one, then publish delivered results to it. A project's earlier deliverables, including Markdown, CSV, PDF and Office documents, are indexed so later runs can search them and cite exact passages. TypeScript/JavaScript sources also expose symbols and resolved local imports through Haystack; clients use atoma_run_search to inspect saved versions (scope and evaluation). See GitHub App setup.

Verification you can read

Supervisors check results with evidence the run produced: files, command exit codes, HTTP probes, and browser checks laid out at the viewport widths the goal asks for. They never replay shell commands a model wrote. Every verdict, retry and refusal is in the timeline, and the console is available in thirteen languages, on desktop and mobile.

For an existing static page, the host also replays browser checks recorded by earlier runs before editing begins and again before delivery. Regressions go to the final review, which distinguishes requested changes from lost behaviour. Read-only phases restore the files they changed, and workers read existing files before editing them. See inherited browser checks.

Jev handles bounded decisions

TypeSafe's Jev helps choose an agent or recipe, approve intermediate plans and results when the evidence permits it, and avoid learning equivalent recipes twice. It answers structured questions; the run's models still plan, write code and explain refusals. Uncertain or unavailable answers go back to those models, and final delivery acceptance stays independent of Jev.

The initial goal and starting repository guide the root tissue choice. Jev selects a suitable registered L3; if the choice is uncertain or no tissue fits, a bounded model call reuses one or requests a new capability. New tissue prompts are authored by the platform's pinned L3 model using the platform's credentials. The legacy run:build command also accepts analysis and explanation tasks.

Jev is enabled for every organisation when the host has TYPESAFE_API_KEY, unless the operator sets ATOMA_JEV=0. Decision context, including task text and evidence excerpts, is sent to TypeSafe as described in the service terms. The timeline records its decisions, latency and separate cost; a sample of approvals is reviewed by the model for comparison. See the architecture guide.

Adjust run limits without redeploying

Platform administrators can change run budgets, token and spend ceilings, call timeouts and tool-iteration limits in Settings or with npm run settings. Changes are recorded in the audit journal and apply to new runs. A token or spend ceiling stops further model calls and preserves completed phases as an incomplete run. See operating run limits.

Connect an existing agent through MCP

The console serves an HTTP MCP endpoint at https://<your-instance>/mcp. Compatible clients such as Claude Code or Codex can create projects, draft run goals from the conversation and repository context, start runs, pass acceptance criteria, request reruns and read traces, costs and diagnostics. The Web console also provides an integrated assistant for customers without an external agent, and remains the place to review projects and results. Choose a personal subscription, organisation API key or configured platform API connection; conversation usage is accounted separately from runs; see setup and limits. Conversations can continue in either direction between Atoma and an MCP client. Use Continue in Claude or another agent to copy the continuation prompt; shared messages and proposals remain private to the same account and organisation.

One endpoint supports both MCP protocol revisions 2025-11-25 and 2026-07-28. OAuth clients can connect through browser consent, including clients identified by a metadata URL. Project run tasks survive a client reconnect, and results link to run resources that compatible clients can open or follow.

Fifty-eight tools. The visible subset depends on the caller's role. Compact searchable menus, recorded progress and saved-file readers keep the workflow inside the conversation. Versioned project briefs and client-confirmed decisions are captured per run through atoma_project_context and atoma_project_context_update. Model suggestions remain proposals until the client confirms them. Sequential project runs can pause for a blocking client choice, receive an answer through atoma_run_answer, and resume saved work through atoma_run_resume. atoma_run_review assembles bounded saved evidence before client acceptance, without running tests or opening a preview. Clients can pause and resume validated work and compare saved file inventories between runs. atoma_run_start accepts baseRunId to iterate a specific saved version; status and readiness expose the accepted reference. Deliveries await client testing and explicit acceptance before GitHub publication. Hosts supporting MCP Apps can also display an inline run view; every client retains text results and file resource links. See the MCP connection and authorization guide.

A platform that reviews its own runs

Three background services watch the platform itself. The sentinel watches runs in flight for cost overruns and drifting trajectories. The analyst writes a cited post-mortem verdict for each finished run. The mender turns a verdict that names a code defect into a pull request, which a person reviews and merges. Read the supervisor design.

How it works

atoma assigns planning, supervision and execution to different AI agents and model tiers. Ordinary build runs start with a supervisor and workers; a deeper planning tier takes over if supervision exhausts its retries, and a seeded run keeps its starting workspace when it does.

• Workers build. They read and write files, run commands and use tools. Project runs do so in a container with no network unless egress is explicitly allowed; a local npm run run:build uses the host unless it is given --container.
• Supervisors check. They review results against artifact evidence and fixed probes. Before delivery, a separate check reviews the final result against the goal and its acceptance criteria.
• Trust is earned. Components that keep succeeding can skip some model reviews while retaining mechanical checks. A failure revokes that trust.
• Skills carry forward. Verified work becomes reusable recipes. A recipe that can be turned into a script is compiled as soon as it is learned, and the script then runs without model calls until it fails.

The composition model is Element → Molecule → Cell → Tissue: tools, workers, supervisors and planners. Read How atoma works for the architecture, execution boundaries and verification design.

One catalogue, shared by every run. An instance keeps one agent registry, one skill catalogue and one set of trust counters, and every run reads and writes them, whichever organisation started it. What one team's run works out is offered to the next team's run. Projects, workspaces, traces and searchable documents stay scoped to their organisation. This is the design, and it has a price: prompts and recipes a run writes, including wording derived from a document it was given, are readable by other organisations' runs. An instance therefore suits teams that accept pooling what their runs learn. The hosted service states this in its shared-learning terms.

Install and evaluate it locally

For the web experience, start at atoma.run. For a source checkout, use the pinned Node version and follow the development setup guide, including system prerequisites. Runs and the full test suite require macOS or Linux; on Windows, use WSL2 with its own checkout on ext4.

git clone https://github.com/atoma-run/atoma.git
cd atoma
nvm install && nvm use
npm ci
npm run release:check
npm run doctor

Configure your model providers using .env.example and the development guide, then run a task and open the console:

npm run run:build -- "a Node CLI that converts CSV to JSON"
npm run viz:serve

The compiled commands read the process environment; they do not load .env. The local console is open on loopback by default. Organisation-scoped project runs additionally require Docker and a Haystack search runtime, described in the development setup guide. A fresh checkout contains no learned state.

To host an instance for others, follow the packaged stack, deployment, GitHub App and preview guides, and back the state up off-machine with npm run backup -- --dest <mount>.

Status

atoma is an evolving open-source system. Its web console, project runs, acceptance criteria, comparison reruns, GitHub import and publication, result previews and MCP endpoint are in use on atoma.run.

Local file-tool containment is not shell isolation; use the container backend for isolated execution. A platform admin can read across organisations, and mutually untrusted tenants are not a supported deployment shape. Verification provides evidence for review, not a guarantee that a generated application is ready for production. See the changelog for what changed.

Repository facts

Read out of this checkout
Version	0.4.0
Node	24.20+ (.nvmrc 24.20.0, engines >=24)
Subsystems under their own contract	18
MCP tools	58
Curated agent names	118 molecules · 40 cells · 20 tissues
Controlled benchmark rounds	12 (benchmark/RESULT.md + ROUND<n>.md)
Interface locales	13 catalogs — 1 source, 12 translated

Documentation

Browse the documentation index for current guides and the archive for historical designs, reviews and release evidence.

I want to…	Read
Understand the architecture	How it works
Understand Jev and its evaluation	Architecture · Decision record · Latest policy corrections
Know what runs share with each other	Shared-learning terms
Use your own ChatGPT account	Personal model discovery
Develop locally or contribute	Development setup · Contributing
Operate a hosted instance	Packaged stack · Deployment · Maintenance · Configuration
Publish results or enable previews	GitHub App · Preview deployment
Connect an MCP client	MCP authorization
Review changes	Changelog · Code reviews
Report a vulnerability	Security policy

Historical measurements

Twelve controlled rounds explored build and maintenance tasks against a single agent — a frontier model, and in later rounds cheaper Sonnet and Haiku agents. Results were mixed: some comparisons favoured atoma, while cheaper direct models matched or outperformed it on the tested maintenance tasks. They predate the 2026-08-18 state reset, so they do not establish savings or correctness for the current release. Read the protocol and the results for context.

License

atoma is free and open-source software under the GNU Affero General Public License, version 3 (AGPL-3.0-only). If you distribute a modified version, or run one that users interact with over a network, you must offer those users its source under the same licence. Unmodified use, including internal production use and hosting, carries no obligation beyond keeping the notices. A commercial licence is available from the author for organisations that cannot accept the AGPL; contributors grant the rights that make this possible through the CLA, which also commits the project to remaining under an OSI-approved licence.

Contributions start with CONTRIBUTING.md. Vulnerabilities go through SECURITY.md, not the issue tracker. The hosted service at atoma.run publishes its shared-learning service terms and operator contact separately from the software licence.

Model providers are called with the credentials you supply, under each provider's own terms. The @anthropic-ai/claude-agent-sdk dependency is distributed by Anthropic under its own licence, and the 3D assets under src/viz/public/ carry their CC0 and CC-BY-4.0 notices beside the files.

Copyright 2026 Matthieu Foillard.

---

Explore atoma.run →