01 · training data
Recalled from weights
answers for 0.9.2
Frozen. The signature it remembers quietly stopped existing.
npm-distributed sqlite-indexed no server
Your agent reads the docs for the version you actually installed.
docspack ships documentation as an ordinary npm dependency — pinned next to the code it describes, indexed on your machine, and answered by one command.
In plain terms: coding assistants routinely answer from the wrong version of a library's manual. docspack installs the right manual next to the code and keeps the two in step.
pnpm
$ pnpm add -D @acme/docspack
$ pnpm dlx docspack sync
# the agent asks a question, not for a library
$ npx docspack ask "verify a webhook signature"
## @acme/docspack@1.4.0 · webhooks
Verify the signature header on every event.
Compare with timingSafeEqual; reject on drift > 5m.
the gap
Three ways to answer one question
You have @acme/docspack@1.4.0 in your lockfile. The agent asks
how to verify a webhook. Only one path is bound to the version you are running.
02 · fetch the docs site
Network round trip
answers for 2.1.0
Today's truth. Whatever the vendor publishes now — not what you installed.
03 · docspack
Local index, keyed to the lockfile
answers for 1.4.0
Correct by construction. The docs were installed with the code.
instead of
Why not the thing you already have
The alternatives are not less capable. They differ on one axis: which version of the truth reaches the model, and how much of it.
| docspack | Docs site | MCP server | Agent skill | |
|---|---|---|---|---|
| Matches your lockfile | Always | Latest only | Latest only | Authored once |
| Works offline | Yes | No | No | Yes |
| Resident in context | Never | Pasted pages | Tool defs, always | Whole skill, always |
| Cost of one answer | ≤ 3,000 tokens | Whole page | Whole page + trip | Whole document |
| Setup per project | One line | None | Per client | Per team |
docspack
- Matches your lockfile
- Always
- Works offline
- Yes
- Resident in context
- Never
- Cost of one answer
- ≤ 3,000 tokens
- Setup per project
- One line
Docs site
- Matches your lockfile
- Latest only
- Works offline
- No
- Resident in context
- Pasted pages
- Cost of one answer
- Whole page
- Setup per project
- None
MCP server
- Matches your lockfile
- Latest only
- Works offline
- No
- Resident in context
- Tool defs, always
- Cost of one answer
- Whole page + trip
- Setup per project
- Per client
Agent skill
- Matches your lockfile
- Authored once
- Works offline
- Yes
- Resident in context
- Whole skill, always
- Cost of one answer
- Whole document
- Setup per project
- Per team
A docs MCP server that fetches
Closest relative, and no reason it cannot exist — docspack mcp is exactly that. The difference is what sits behind it: a fetching server returns the same text to every project, pays the network on each call, and ranks whole pages because there is no local index.
An agent skill
A skill teaches an agent how to do something — your review checklist, your deploy runbook. It is authored once and loaded whole. Dependency docs change when you bump a version, and nobody wants to hand-edit them. Skills and docspack compose: the skill says “check the docs first”.
Vendoring docs into the repo
Copying Markdown into CLAUDE.md is the right instinct — it just does not survive upgrades. Nothing notices when it goes stale, and a flat folder has no index, so the agent reads the whole file to find one line.
A vector database
Better recall for vague questions, at the price of an embedding pipeline, a service, and a re-ingestion story on every change. Aimed at a corpus you do not have. Yours is small, textual, and already versioned by the package manager.
how it works
Three moves, no server
01
Vendors publish docs to npm
A docs package is an ordinary npm package: Markdown split into chunks, plus a manifest describing them. Its version tracks the library's.
// package.json "devDependencies": { "@acme/docspack": "1.4.0" }
02
docspack indexes them locally
One sync walks the docs packages this project depends on and writes their chunks into one SQLite database per machine. Keyed by name and version, so a release is read once no matter how many projects use it.
$ npx docspack sync + @acme/docspack@1.4.0 128 chunks indexed = @other/docspack@0.0.8 44 chunks cached
03
Agents ask the index
Every agent already has a shell, so the setup is done: no server to spawn, no per-client configuration, nothing resident when nobody is asking. One line in AGENTS.md is the whole install.
# AGENTS.md Run docspack ask "question" for docs on this project's dependencies. It answers from the installed versions.
85ms
Per query, roughly half of it Node starting. Invisible next to the seconds an agent spends thinking.
SQLite FTS5
Porter stemming, so authenticate finds a chunk that only says authentication.
Also MCP
docspack mcp serves the same index over the protocol, byte-identical answers, if you would rather have a tool.
what it costs in context
A query, not a library
Measured against one vendor's published documentation. The middle bar is what the index holds on disk; it never reaches the model.
About one percent of the documentation reaches the model, and a response is capped at 3,000 tokens no matter what was asked.
the specification
A docs package is just files
Any tool can read one. The manifest maps chunks to search terms, so indexing needs no model in the loop.
node_modules/@acme/docspack/ ├─ package.json holds the version ├─ llms.txt table of contents └─ .llms/ ├─ manifest.json chunk routing table ├─ chunks/ │ ├─ api-auth.md │ └─ webhooks.md └─ schemas/ optional openapi
{
"name": "@acme/docspack",
"version": "1.4.0",
"chunks": [
{
"id": "api-auth",
"tokens": 150,
"tags": ["authentication", "bearer"]
}
]
} Generate one from what you already have
Split Markdown at headings, or walk an OpenAPI document. The only command that
touches the network reads a project's public llms.txt.
$ npx docspack build --from ./docs $ npx docspack build --openapi ./api.json $ npx docspack build hono
feedback
The agent noticed the docs are wrong
An agent has the documentation, the installed library and a failing program in front of it at the same moment. That signal is worth capturing, and today it evaporates.
The obvious version — let the agent file an issue — points a firehose at the people the whole model depends on. curl ended its bug bounty in January 2026 over AI-generated slop. So the goal is not to make feedback easy. It is to make high-signal feedback cheap and low-signal feedback impossible to transmit.
Claims must be falsifiable: drift has to name the identifier, anything
else has to carry a reproduction, and there is no kind for "this page is confusing".
Repeats increment a counter, so twelve agents hitting one bug produce one report
that says twelve.
Nothing is sent, and nothing can be — docspack contains no code that transmits a
report. A vendor who wants them declares a channel in their own
package.json, and a human decides whether to open the prefilled issue.
# the agent records what it found $ npx docspack feedback add \ --chunk @acme/docspack@1.4.0/api-auth \ --kind drift \ --evidence "client.setKey is not exported" # a human reviews, then decides $ npx docspack feedback submit 182ec604a6ea drift @acme/docspack@1.4.0/api-auth Open: https://github.com/acme/sdk/issues/new?… // the vendor opts in — or gets nothing "feedback": { "github": "acme/sdk", "accepts": ["drift"] }
guarantees
What holds, every query
Offline by construction
sync, ask, search and list make no network requests. They read node_modules and a local SQLite file.
Version-scoped answers
The shared index may hold five versions of a library. A project only ever sees the one it installed.
Bounded responses
Three chunks and 3,000 tokens by default, counted from the manifest before content is returned.
Untrusted input, treated as such
Community packages are labelled, and a manifest path that escapes the package is refused rather than read.
questions
Before you install it
What is docspack?
docspack distributes a library's documentation as an ordinary npm package, so the docs install alongside the code and stay pinned to the same version. It indexes those packages into a local SQLite database and answers questions from it with one command, offline.
Do I need to run a server?
No. docspack is a CLI: the agent runs docspack ask in the shell it already has. There is nothing resident when nobody is asking. An MCP server ships too (docspack mcp) and serves the same index, for assistants that cannot run commands.
What if a library does not publish a docs package?
Build one yourself with docspack build --from ./docs, from an OpenAPI document, or from a project's public llms.txt. The result is a normal npm package you can publish or keep private.
How much context does an answer consume?
Three chunks and 3,000 tokens by default. The cap is counted from the manifest before any content is returned, so a query cannot overrun it. Measured against one vendor's published docs, roughly one percent of the corpus reaches the model.
Does docspack send anything anywhere?
No. sync, ask, search and list make no network requests at all, and docspack contains no code that transmits a feedback report. The only command that touches the network is docspack build, which reads a project's public llms.txt when you ask it to.