Clean scanStatic scanned
Sight
cultured_computer · App
Sight is the capture library and command line for the Sight service. Inside a conversation session it records each model call your assistant makes as one turn: the person's message, the reply, model, provider, token counts, latency, tool names and cost when one is available. Turns are sent to the Sight API with an API key, and the system prompt is sent only as a hash. It suits teams who want a record of what their assistant said and what each call involved.
Written by ooruby from the README of @cultured_computer/sight 0.8.3.
Not claimed by its maker.
Why it's useful
You get a record of each model call your assistant makes, with the message, reply, model, tokens, latency and cost, in one place.
What you could do with it
- Wrap your OpenAI client so each chat or response call inside a session is captured as a turn.
- Scope each conversation with your own conversation id so its turns are grouped into one session.
- Attach a stable, pseudonymous user id so one person's sessions are tied together.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
Capture each LLM call of your production assistant as a conversation turn: model, tokens, latency, cost, outcomes. Node SDK and CLI.
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 0.8.3, the file with digest sha512-Q0U97us4s4ghLIP8WG+oK9mylBtnH8H/3t/sk8E9RoJFRI7V0WXck2eTgGi4iEeGBOFfQkfF09/3SBNvABLo/g==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y @cultured_computer/sight@0.8.3Pinned to 0.8.3, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- @cultured_computer/sight
- Version read
- 0.8.3
- Resolved
- 2026-10-10
No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/cultured-computer-sight)About this listing
- Kind
- App
- Category
- Infrastructure
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-06
Similar apps
All appsVerification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.