Skip to content
Reality Graph

Features

Nine features, one question: what actually happened in that run?

Reality Graph preparesYour taskMissionContextYour coding toolnot oursReality Graph verifiesChecksEvidenceVerdictthe tool writes the code, we establish what happened
The Reality Graph features cover one loop end to end: state what the change should be, bound the context it gets, run the checks yourself, read the evidence out of Git, and end with a single verdict. Reality Graph never writes the code, which is why it works beside the coding tool you already use.

Last updated:

The capabilities

Each one answers a question a review already asks

Nothing here is a category name. Every card is a question somebody raises at merge time, and the page behind it says exactly how far the answer reaches.

A contract that says what done means

Describe the change in one sentence. Reality Graph proposes the goal, the paths and the checks; you correct and confirm them before anything runs.

  • Empty acceptance criteria fail validation
  • Eleven declared intents, never guessed
  • A pre-run recommendation with no authority to block
Read more

Context bounded by that contract

Your coding tool receives the files the contract declares, in a fixed order, with credentials removed before the prompt is assembled.

  • No retrieval and no similarity search
  • .env refused in every case
  • Every token count labelled exact or estimated
Read more

A local index you can check

One node per module, class, function and method, anchored to file and line, with a content hash that tells you whether the map still matches.

  • Python only, other languages index to nothing
  • Five standard-library imports, no network
  • Fresh, stale or incomplete, by content hash
Read more

Checks Reality Graph runs itself

Approved commands run as an argv list with no shell and a bounded timeout, and the observed exit code is recorded rather than reported.

  • Executed or attested, with no third value
  • A missing result blocks instead of passing
  • No sandbox, and the page says so
Read more

One verdict, computed the same way every time

Verified, verified with limitations or blocked, from one deterministic function fed by changed files read out of Git.

  • Green tests can still end blocked
  • One call site, so CLI and dashboard agree
  • Receipts carry a digest that flags later edits
Read more

Every run, still open

One local workspace on 127.0.0.1 holding every run, review, check and receipt, rendering exactly what the CLI prints.

  • Eight views, one canonical projection
  • The browser never computes a verdict
  • A port per worktree, and no request off the machine
Read more

Every prompt becomes a ticket

Your backlog and your agent's work are the same record: a command runs a ticket, and a prompt without one gets one.

  • The mission lives inside the ticket
  • No status moves without evidence
  • Append-only, so failed attempts stay legible
Read more

Four tools your agent gets, ten it does not

A local read-only MCP server over stdio. The dangerous operations are not missing from the contract, they are in it and refused by name.

  • No port, no socket, no network call
  • approve_own_patch is declared and denied
  • Deterministic ranking, no embeddings
Read more

Approvals that do not follow the branch

A protected path that changed forces a block nothing clears, and an approval is bound to the run, HEAD, scope and checks it was given for.

  • Any of those four moving marks it stale
  • A local attestation, not an identity
  • Detection after the fact, not prevention
Read more

By design

The list an evaluator reads first

This is not modesty. It is the fastest way to find out whether Reality Graph fits, and putting it on the page means nobody has to spend a week discovering it.

You can rely on

  • A contract validated before the run, with acceptance criteria that cannot be left empty.
  • Context assembled only from what that contract declares, with credentials scrubbed first.
  • Checks executed by Reality Graph, with the exit code it observed.
  • Changed files and diffs read from Git, not from the model's prose.
  • One deterministic verdict, and a local record that outlives the session.

Not true today

  • Team features. No accounts, no seats, no roles, no shared history.
  • CI or pull-request integration. No Git hooks, no GitHub App, no pipeline import.
  • Test-strength analysis. No assertion counting, no coverage, no mutation testing.
  • Indexing anything but Python, and no incremental rebuild.
  • Any certification, and no benchmark or token-saving figure.

Validated on Linux with Python 3.12 and the official Codex CLI. Windows and macOS are unverified in the current release matrix.

How the six pieces fit into one run is walked through on the product page, and what leaves your machine is traced on the data-path page.

Questions people actually ask

Which coding tools does this work with?
The Codex CLI and Claude Code are bound through reversible hooks in their own project configuration: a run opens on prompt submit and finalises on stop. Cursor, GitHub Copilot and the rest work beside Reality Graph through a prompt you paste yourself, and the evidence still comes from Git afterwards. That is a weaker statement than an integration, and for those tools it is the true one.
Does it work on a codebase that is not Python?
Partly. The mission contract, the executed checks, the evidence from Git, the verdict and the approvals are language-agnostic. CodeGraph is not: it reads Python only, and any other repository produces an empty graph.
Can our whole team use this?
Not as a team product. Reality Graph is a single-operator, single-machine tool with no accounts, no seats and no shared state, so there are no roles, no team approvals and no history a colleague can open. Several people can run it, but each of them runs their own.
Does Reality Graph write or fix code?
No. Your coding agent writes the change; Reality Graph states what the change was supposed to be and then establishes what actually happened. It does not write your source, stage your index, commit or push.

Pick the feature closest to the argument you keep having

Every page states what its feature does, and where it stops, in the same breath.