Pinakes
A portable, agent-first knowledge base. One directory = one KB.
The Pinakes were Callimachus's catalogue of the Library of Alexandria — the first known index of a body of knowledge.
📖 Documentation site — searchable, and the same files rendered below: Guide · CLI · Manifest · Design · What ships today
The idea
A knowledge base is a plain directory you can read, edit, diff, commit and hand to someone:
my-kb/
├── pinakes.toml # manifest: sources, models, chunking, budget
├── docs/ # SOURCE OF TRUTH — your files, unmodified
│ ├── paper.pdf
│ ├── paper.pdf.pnk.yaml # sidecar: stable ID, tags, links, provenance
│ ├── notes.md
│ └── notes.md.pnk.yaml
└── .pinakes/ # generated, disposable, gitignored
└── index.db # SQLite: chunks, FTS5, vectors, links
Your documents and their metadata are the truth. The index is derived state that can always be rebuilt. That split is what makes a KB both a reproducible recipe and a directory you can move.
What makes it different
It costs nothing to run. Retrieval is BM25 (SQLite FTS5) + local embeddings + local reranking, fused and scored entirely on your CPU. No API key is needed to search, and re-indexing is free — so there is never a cost reason not to improve your chunking or swap your embedding model. That the free path stays free is enforced by a CI gate, not by a promise.
Reasoning is the caller's, not the KB's. The MCP tools return ranked, cited evidence.
pinakes_search → pinakes_get → pinakes_search is a plan-retrieve-read-refine loop, and your agent
already runs it in its own context. Multi-hop reasoning falls out of composable tools rather than a
second agent framework.
Money is opt-in and bounded by design. Every paid path is an explicit, enumerated entry point, and a pre-call reservation makes a hard cap a real ceiling rather than an after-the-fact report. See what is actually built.
KBs link to each other. Sidecars carry pnk://<kb-ulid>/<doc-ulid> references, so links survive
renames, moves, and being shared with someone else. pnk links and the pinakes_links tool walk
them — bounded, and a neighbour in another KB is returned but never expanded, because this index
holds that KB's links pointing here and not its own. pnk sync --scan-links learns what points
back by reading the other KB's committed sidecars, and pnk link authors one from the command
line, straight into the source document's own sidecar.
Your sidecars are yours. They are read and written through a round-trip parser, so a rewrite
keeps your comments, your quoting and your own key order — and a value is stored as you wrote it:
country: NO stays NO.
Its limits are published, not hidden. No vector tier is sublinear; cross-KB answers will be capped by how well your KBs are linked; and the confidence heuristic's measured false-confidence rate is 0.25 — one no-answer question in four still gets a confident answer. A heuristic whose cost is unmeasured is worse than one whose cost is known.
Quickstart
uv add "pinakes[st]" # default backend
uv add "pinakes[light]" # fastembed, no torch
uv add "pinakes[light,pdf]" # + PDF ingest, free and local
uv add "pinakes[light,pdf,claude]" # + the opt-in paid extractor for scanned PDFs
[claude] installs a path that can spend money, and nothing spends without you asking: the default
extractor is free, and reaching the paid one takes --extract=claude-vision (or a manifest key)
and a real API key in the environment. When you do ask, the run is priced before the first call
and refused if it would breach any of the three [budget] caps — per_operation_eur, daily_eur
or monthly_eur. Raising one and hitting the next is the discovery path those caps exist to
prevent, so a refusal names every window that binds, not just the first. pnk budget reports what
has been spent.
pnk init my-kb # stamp a KB
pnk sync # index what changed (git-hook friendly)
pnk search "hybrid retrieval" # free: BM25 + vector + rerank
pnk doctor # environment, coherence, orphans, link coverage
uvx --from "pinakes[st]" pnk serve # MCP server, nothing installed
⚠️ Two things pnk init cannot know, each needing one manifest edit: on a [light] install set
provider = "fastembed", and to index PDFs add "**/*.pdf" to [sources] include. Both are in the
Guide.
→ Full guide — PDFs, filters, calibration, git hooks, MCP setup, troubleshooting.
Development
make install # sync the dev environment (the light extra — CI's minimum leg)
make check # every gate, stopping at the first failure — run before every commit
make demo # index the synthetic demo KB
make eval # golden-set evaluation against the recorded baseline
make corpus # regenerate the synthetic PDF corpus in place
make pdf-eval # extraction-quality baseline + floor-drift check (needs [pdf])
make budget # the demo KB's spend ledger (free: it only reads)
make docs # build the documentation site (--strict — exactly what CI runs)
make docs-serve # preview it at http://127.0.0.1:8000 with live reload
make help # all targets
Every target wraps the command CI actually runs, so green locally means green on the runner. Note
that make check formats Python inside Markdown fences too — a docs-only change can fail it.
Conventions are in CLAUDE.md, the increment workflow in
docs/BUILDING.md; how the docs are organised —
and which file to edit when you land a feature — is in docs/README.md.
docs/VERIFICATION.md maps every promise this project makes to the test
that holds it, and a test asserts every one of those tests exists.
Your data stays yours
This repository contains the engine only. Real knowledge bases live outside it. The only KBs
here are two small synthetic corpora — an archive and a partner museum that transacts with it —
used for tests, retrieval benchmarking and cross-KB linking, and the only other committed content
is tests/pdf-corpus/ — PDFs generated from scratch by a committed script to exercise hard
extraction cases. None of it was harvested from anywhere; no real-world document is committed
here.
pnk init ships a .gitignore covering .pinakes/, so your index — and your spend ledger — never
leaves your machine. Note that publishing a KB repo publishes docs/ and every sidecar: titles,
tags and provenance URLs included.
Licence
1 maintainer
Metadata
1 maintainer
Release files for pinakes 0.16.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| pinakes-0.16.0.tar.gz | 1.9 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pinakes-0.16.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.2 MB
Release files / pinakes-0.16.0.tar.gz
| Download URL | pinakes-0.16.0.tar.gz |
|---|---|
| Size | 1.9 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7af173785abb920afa60cf8878eacdd627b093b2b60300f3566a65d9960b3130
|
|
BLAKE2b-256 checksum How to use checksums |
d7f3f01c6bed178d4fdeb85ad66d1a8a123f2f7a1225ab192aa6ae8c07cd6918
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.2 {"installer":{"name":"uv","version":"0.12.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / pinakes-0.16.0-py3-none-any.whl
| Download URL | pinakes-0.16.0-py3-none-any.whl |
|---|---|
| Size | 332.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
87f0fcb452111a7f386f7c80a53c21b944d6b942cc7c86cbd36c58dea2538609
|
|
BLAKE2b-256 checksum How to use checksums |
bb16556e43901bca7bf80c9cf40f1459b4b731e8b3798b4983a3f32201392e66
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.2 {"installer":{"name":"uv","version":"0.12.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
