Pikelet

Knowledge that ships as a file.

Pikelet compiles a corpus into one self-contained, queryable artifact.

A model can interrogate a 456,153-record knowledge base whose backend is a static file.

A .pikelet can carry the source text, semantic index, keyword index, query encoder, integrity commitments, retrieval calibration, and evaluation fixtures needed to interrogate that corpus. Put the file on disk, S3, R2, a CDN, or any static HTTP host. A reader can mount it locally or over HTTP Range and search it without a vector database, embedding API, or retrieval server.

The pikelet CLI requires Node 20+; the pikelet-wasm library runs on Node 18+ (CI tests 18, 20, 22), browsers, and Cloudflare Workers.

Upgrade to pikelet-wasm@0.8.1 if you mount packs you did not compile. 0.8.0 and earlier sized the inline encoder's WASM buffers from the artifact's own maxTokens with an upper bound only, so a pack declaring an out-of-range value could overflow them — at mount, before any query, and with every integrity check passing, because the pack's author is the one who signed it. 0.8.1 validates the bound. Packs the toolchain produces were never affected. pikelet@0.8.1 picks the fix up through its dependency range; see the CHANGELOG for the detail.

npx pikelet compile --source ./docs --out docs.pikelet

Installing rather than using npx? Use npm install -g pikelet --omit=optional. The optional dependency is @xenova/transformers, which only the create scaffold path uses. Measured on a clean project, omitting it takes the install from 82 packages / 257 MB / "6 vulnerabilities (5 high, 1 critical)" to 2 packages / 1.8 MB / "found 0 vulnerabilities" — the advisories are all inside a dependency compile and mcp never load.

Ingested 3 docs -> 3 chunks
Embedded 3/3 chunks with inline transformer
Built complete .pikelet artifact with 24.5 MB
Compiled docs.pikelet
  24.5 MB, 3 records, identity 8d731a...

First run fetches the ~25 MiB query encoder from a GitHub release and caches it; every .pikelet file is at least that size regardless of corpus, because the encoder ships inside it — a 5-file folder and a 500-file folder both start around 25 MiB.

Then query it from an LLM — Claude Code, Claude Desktop, or any MCP client:

npx pikelet mcp install --client claude-code --pack ./docs.pikelet
# or --client claude-desktop; any other MCP client can run
# `npx pikelet mcp --pack ./docs.pikelet` directly, no install step

Wrote MCP server "knowledge-packs" to ./.mcp.json
Claude Code picks it up on the next session in this project.

Claude now has a search tool over your docs. Or query it directly from code:

import { openPikeletFile } from 'pikelet-wasm/complete';
const pack = await openPikeletFile('docs.pikelet');
const out = await pack.query('how do workers restore snapshots', { k: 5 });
console.log(out.matchQuality, out.results[0]?.title);
// 'strong' 'Snapshot restore'

That's the whole loop. compile also takes a live URL (--source https://docs.example.com) instead of a directory. If you want a deployed search app — a Worker + UI, not a file — use npx pikelet create instead; see packages/pikelet/README.md for the full CLI reference and the tradeoffs between the two. create is the one path that needs the optional @xenova/transformers dependency, which is why the install above omits it by default.

Under the hood, the file is one container for everything a reader needs:

documents
    │
    ▼
┌──────────────────┐
│   docs.pikelet   │
│                  │
│ corpus           │
│ semantic index   │
│ lexical index    │
│ query encoder    │
│ integrity        │
│ calibration      │
│ evaluation       │
└──────────────────┘
    │
    ├── local file
    └── static HTTP / object storage
              │
              ▼
        browser / Node / edge / agent

Search is the interface. The file is the knowledge deployment unit.

The shortest demonstration

A real Pikelet pack contains 456,153 Simple English Wikipedia records in a 648.5 MiB artifact.

Try the live browser demo:

https://pikelet-wiki-playground.pages.dev/

The page is static HTML/JS on Cloudflare Pages. It mounts the pack from R2:

https://pub-6da2384a3bca4a44b2b2fa29a94cc811.r2.dev/wikipedia.pikelet

There is no /search, /embed, /query, or /api backend behind the demo. The browser opens the .pikelet file over HTTP Range, verifies the artifact, loads the embedded query encoder, and shows the byte ranges it reads.

That file was served by a deliberately dumb HTTP server whose only relevant capability was:

fs.createReadStream + HTTP Range

There was no vector database, no search service, no embedding service, no application server that understood the pack, no index process on the server.

The pack was mounted by URL and exposed to a real headless Claude process through MCP. Each invocation was restricted with --strict-mcp-config to only:

mcp__wiki-pack__search
mcp__wiki-pack__list_packs
mcp__wiki-pack__get_record

No web tool. No filesystem tool. No alternate retrieval tool.

One of the actual responses:

Q: What causes earthquakes?

Earthquakes are caused by the movement of tectonic plates in the Earth's crust. Stress builds up along fault boundaries where plates grind against or ride over one another; when that stress exceeds the friction holding the locked fault in place, it suddenly releases as shock waves (seismic waves) that shake the ground [record 429637].

There are three main fault types that can produce quakes — normal, reverse (thrust), and strike-slip — and some quakes have less clear-cut causes, like deep shifts in ancient rock or mine-collapse "tremors" [record 429638].

Two related mechanisms compound this:

• Subduction, where one plate is forced under another into the mantle, produces the most powerful earthquakes and can trigger tsunamis [record 132833].
• More broadly, the slow convection-driven movement of crustal plates over the hot mantle is the underlying driver of quakes, volcanoes, and mountain formation [record 132267].

Volcanic eruptions can also cause earthquakes, though these are localized to areas near active volcanoes [record 429637].

The model did not just repeat the first search hit. It retrieved multiple records and synthesized them into a sourced answer.

Other runs produced:

Who was the first person on the moon?          → Neil Armstrong          (records 408686, 408684)
How do volcanoes form?                          → plates + subduction + hotspots
                                                                          (records 132770, 132765, 132852, 132853)
How does photosynthesis work?                   → two-phase reaction, cited (5 records: 114219, 114220, 114222, 114223, 269279)
What is the capital of France?                  → Paris                  (records 454641, 302684)

That is the product in one demonstration:

A model is interrogating a 456,153-record knowledge base whose backend is a static file.

The model may already contain some of these facts in its pretrained parameters. This test demonstrates the retrieval, synthesis, citation, and deployment path; the Veyra ablation tests whether support changes when evidence is removed from the pack.

Network cost. In a single persistent session (one mount, five queries, one repeat):

Roughly 12.5% of the 648.5 MiB artifact crossed the wire across that whole session. Excluding the one-time ~25 MiB encoder load, fresh-query traffic ran ~0.5–1.1 MiB per query. The complete artifact was never downloaded.

The headless-Claude test above used a fresh process per question, so each invocation repaid the ~52 MiB mount and ~25 MiB encoder cost — about 78 MiB per cold query. That's a real operational distinction: persistent sessions amortize mount and encoder cost; independent cold processes do not.

(The large benchmark fixture still carries its historical .pancake filename from before the Pikelet rename; current artifacts use .pikelet.)

Attach a pack to an LLM

pikelet mcp exposes one or more packs through the Model Context Protocol:

npx pikelet mcp install \
  --client claude-code \
  --pack https://example.com/docs.pikelet#<sha256>

The agent gets search, get_record, list_packs, verify_pack. A search result carries the identity of the pack and the location of the source record, so an agent can work against product-docs.pikelet, rust-reference.pikelet, policy-2026-09.pikelet, customer-manual-v4.pikelet without each publisher operating a retrieval API. The artifact can be local, private, public, behind authenticated object storage, or distributed like any other static asset.

A pack mounted with a content hash has a stable identity — https://example.com/docs.pikelet#8d731... — so "what body of knowledge did this agent query?" has a reproducible answer.