WhyKit

io.github.CometWeb-ioPublished by GitHub account CometWeb-iov0.5.1Updated Nov 14, 2026

Read-only decisions and evidence from a Git vault, and which decisions a code change touches.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Read-only MCP access to a Git-stored vault of decisions and their sources, so an assistant can look up the reasoning behind code before editing it.

What you can do
  • Query and read decisions, sources and their links in the vault
  • Fetch context and packed reasoning for a given area or task
  • Trace a decision to its sources and list backlinks
  • Check status, review dates and sensitivity-filtered records
  • Map planned or changed files to the decisions that govern them and flag stale evidence
When to use it
Useful when a codebase keeps its architectural decisions and their evidence as Markdown in Git and you want a coding agent to consult them before changing covered code. Also fits teams that want agents to see which decisions a planned patch touches.
Requirements
A local Python 3.11+ environment with uv (0.13.4+); the package is installed with uv tool install and the MCP extra. A WhyKit vault or an existing ADR folder in the repository, and a host configuration produced by the connect command. No account, API key or network access is needed.
Before you install
The server is read-only, but the connect command can write a marked instruction block into the repository's CLAUDE.md or AGENTS.md. Sensitivity labels only filter what is returned and are not access control, so keep real vaults in private repositories. Agent instructions are advisory; the README recommends pairing them with a CI gate. The project is a public alpha.

Installation

In SourceWeft

  1. Open WhyKit in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

WhyKit

Know which decisions a change touches, and which of them need another look.

Your coding agent sees the code, not the reasons behind it, so it "fixes" things that were deliberate. WhyKit keeps decisions and their sources as plain Markdown in Git, maps every change to the decisions that govern it, and flags the ones whose evidence or review has gone out of date: in the pull request, before merge, and for Claude Code, Cursor or Codex before they edit.

[CI] [PyPI] [Python] [License] [OpenSSF Scorecard] [Website]

No runtime dependencies · Offline by design · Your data stays Markdown

Live demo · Tutorial · Connect agents · Docs · Roadmap

[WhyKit Explorer: decisions, their supersession chain and a timeline, from the synthetic Northline example vault.]

What it does

Each decision cites its sources (E-001) and declares the code it governs (applies_to: ["src/payments/**"]). Before a change lands, one command answers which decisions does this touch, and has anything they rest on changed?

console
$ whykit affected --root examples/payments --today 2026-11-12 \    --files src/payments/ledger.py src/webhooks/refunds.py README.mdWhyKit affected — 3 changed files · 2 decisions apply · 1 needs review · 1 file not covered by any decision  D-001  review   Store money as integer cents      files: src/payments/ledger.py      - a cited source was retired  D-003  applies  Make every webhook handler idempotent      files: src/webhooks/refunds.py  not covered by any decision: README.md  1 live decision(s) declare no applies_to scope: D-005

That is real output from the synthetic payments example; a test keeps this block in step with the code. The ledger decision rests on an audit checklist that has since been replaced, so its reasoning needs a look before this change merges. WhyKit says what it checked and what it did not: uncovered files and unscoped decisions are listed, and it never claims a change is safe.

[A source, a decision and a review, kept together in WhyKit.]

  • Sources get stable IDs and can be retired or replaced; captured sources are pinned by their bytes.
  • Decisions cite sources, declare their scope, carry an owner and a review date, and are append-only: you supersede, you don't rewrite.
  • Changes are mapped to decisions by whykit affected, locally, in CI and by agents, with review signals for retired, missing, stale or changed sources (including source files the change itself modifies) and overdue or failed reviews. Scopes can be suggested from Git history.
  • Agents read the same files through a read-only MCP server, and whykit connect tells them to ask before they edit.

Try it

Install uv (0.13.4+) and use Python 3.11+. This creates a vault, a folder of Markdown files, with one source and one draft decision that cites it:

bash
uv tool install whykit
# Create a vault.whykit init my-ledger
# Record a source, then a draft decision that cites it.whykit new --root my-ledger evidence \  --source "Support ticket export, Q3" --type dataset \  --location "https://example.com/exports/q3-tickets.csv" \  --claims "Most onboarding tickets mention SSO"whykit new --root my-ledger decision "Ship SSO before audit logs" \  --owner Platform --status draft --source E-001
# See the connection, then check the vault.whykit trace --root my-ledger --decision D-001whykit lint --root my-ledgerwhykit review --root my-ledger list --due-days 120

The trace shows the decision and the source it cites:

text
D-001  06-decisions/d-001-ship-sso-before-audit-logs.md  (draft)    E-001 active

The lint check reports five expected warnings: one for the unfinished draft and four for unanswered questions in the vault's AGENTS.md. Fill in the draft's context, options and consequences, then approve it. If whykit is not found, run uv tool update-shell and open a new terminal.

Catch decision drift

Declare what each decision governs, then ask about any change, planned or committed:

bash
whykit new --root my-ledger decision "Store money as integer cents" \  --owner Payments --status draft --source E-001 --applies-to 'src/payments/**'whykit affected --root my-ledger --files src/payments/ledger.py   # before you editwhykit affected --root my-ledger --base origin/main --format markdown   # in a pull request

Don't want to write scopes by hand? Let Git suggest them from the commits that changed each decision or name it in their message, then confirm:

bash
whykit scope suggest --root my-ledger            # previewwhykit scope suggest --root my-ledger --write    # fill in decisions without a scopewhykit scope check --root my-ledger --strict     # in CI: fail when a scope points at code that moved

A source kept in the repository (a benchmark, a spec) counts too: when a pull request modifies it, every decision citing it is flagged.

Decisions about a library or a convention can watch for words instead of paths: with watch_terms: ["moment"], a change that adds import moment surfaces the "Use Luxon" decision. An agent can send its planned patch before applying it. We replayed real ADR repositories to tune this, and publish what did not work too.

Already have ADRs? Skip the vault and point it at the folder; scopes are inferred from the paths each ADR mentions, and moved code is flagged:

bash
whykit affected --adr docs/decisions --base origin/main

The ten-minute tutorial goes from an empty repository to a flagged decision and its successor; every command in it runs in the test suite. Affected decisions covers scope patterns, every signal and a pull-request workflow.

Connect your agents

One command prints the MCP configuration for your host and adds a short, marked block to your code repository's CLAUDE.md or AGENTS.md telling the agent to look up decisions before it changes what they cover:

bash
uv tool install --upgrade 'whykit[mcp]'whykit connect --root my-ledger --host claude-code          # previewwhykit connect --root my-ledger --host claude-code --write  # apply

Hosts: claude-code, cursor, vscode, codex, claude-desktop and generic. The server is read-only with eight tools (query, context, impact, status, pack, trace, backlinks, affected); records above your chosen sensitivity ceiling are never returned. The instruction block also tells the agent to call affected on the files it plans to change. whykit connect, whykit affected and the affected tool are new in 0.5.0; the MCP server itself is in 0.4.0. Read the agent guide.

Gate pull requests

Instructions ask; CI enforces. On a pull request, the GitHub Action fails when an accepted decision's reasoning is rewritten, a cited source is missing or a credential slips into the vault:

yaml
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1  with:    fetch-depth: 0- uses: CometWeb-io/whykit@<reviewed-40-character-commit-sha>  with:    root: decisions    profile: ci    affected: "true"   # add the decisions this change touches to the job summary

See gate pull requests for the full workflow and a good and a bad example, and CI integration for PR comments, SARIF and other CI systems.

What would you like to do?

Why WhyKit

Plain ADRsWiki / NotionWhyKit
Lives next to the code, in Git✓✓
Maps a code change to the decisions that govern it✓
Flags decisions whose sources were retired, replaced or changed✓
Review dates that expire and get reported✓
Rewriting accepted decisions blocked in CI✓
Read-only MCP access for agents, sensitivity-filtered✓
Works offline, no account, no service✓✓

Already happy with ADRs? Keep them; here is when they are the better fit. When you outgrow them, whykit adopt --profile adr-only brings them in.

Built to be trusted

  • Plain files are canonical. Every view (queries, graphs, MCP, the Explorer) is derived from Markdown you can read and diff.
  • Nothing phones home. No telemetry, accounts or network calls; a test breaks the socket layer and runs every vault command.
  • A stable machine contract. Every --json output has a published JSON Schema; error codes and exit codes are documented in the automation contract.
  • Tested hard. About 1,800 tests, property and fuzz tests for the parsers, reproducible builds, an SBOM and OpenSSF Scorecard on every release.

Limits, stated plainly

WhyKit checks that reasoning is cited, dated and not rewritten. It does not decide whether a source is true or a decision is right, and it does not re-check external sources on its own. Sensitivity labels filter what the MCP server and exports return; they are not access control, so keep real vaults in private repositories. whykit affected matches files by path, not by meaning, and sees only changes recorded in the vault. Agent instructions are a request: pair them with the CI gate. The project is a public alpha; see the feature status and the 0.4 upgrade guide.

Documentation

Contributing

Issues and pull requests are welcome. Start with CONTRIBUTING.md; the whole suite runs offline with the standard library. If WhyKit is useful to you, a ⭐ helps other people find it.

Contributing · Code of Conduct · Security policy · Release checklist · Changelog · Roadmap

Copyright 2026 Maciej Zmitrukiewicz ([email protected]), licensed under Apache-2.0. CometWeb is the product name, not the copyright holder.

Source: README.md at commit 721afc2

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the server did not start.

Version history

1
  1. v0.5.1LatestNov 14, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts