repowiserepowise
Sign in
earendil-works/pi
OverviewDocsArchitectureKnowledge GraphFilesCode HealthRefactoring

People & History

CommitsContributorsDecisions
Chat
Stats
repowiserepowise
ExplorePricingDocs
Sign in
repowiseearendil-works/pi

earendil-works / pi

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

TypeScript102,923github.com/earendil-works/pi
Indexed atb2602be·1d ago·Up to date with upstream
Open dashboardChat with repo

Code health

7.0out of 10Good

earendil-works/pi scores 7.0 out of 10 on defect risk, which Repowise rates Good. Maintainability scores 8.2 out of 10. Static performance risk scores 9.8 out of 10. The three are scored separately and never blended into a single number. 150 of 1,577 files are git hotspots, the places where changes and bug fixes concentrate.

Full health report
Defect risk7.0/10 · Good
Maintainability8.2/10 · Excellent
Performance risk9.8/10 · Excellent
Files
1.6k
Symbols
13k
Modules
22
Doc pages
1.8k
Dead exports
70

Where the risk concentrates

All 150 hotspots

Ranked by prior bug fixes and change frequency, mined from the full git history rather than from the code alone.

FileChurnPrior fixesMaintainersCommits 90d
interactive-mode.tspackages/coding-agent/src/modes/interactive99.5th %ile20bug magnet528
experimental-remote-runtime.test.tspackages/coding-agent/test99.8th %ile6bug magnet352
conformance.test.tspackages/server/test99.7th %ile5bug magnet326
client-tui.tspackages/coding-agent/src/experimental99.9th %ile4bug magnet2bus factor 127
protocol.test.tspackages/protocol/test99.7th %ile4bug magnet333
jsonl-v3-migration.test.tspackages/agent/test/harness99.9th %ile32bus factor 124

Read more about earendil-works/pi

  • OverviewFiles, symbols, languages, packages, git intelligence
  • ArchitectureDependency graph, layered architecture, symbol index, and third-party dependencies
  • Code healthPer-file health scores, hotspots, test coverage, dead code, and refactoring targets
  • AI explanationsProModule-by-module documentation generated from source
  • CommitsChange-risk ranked history with AI-agent provenance and hotspots
  • ContributorsBus-factor, per-file maintainer maps, and human/agent collaboration
  • DecisionsArchitectural decisions extracted from commits and PRs
  • Chat with this repoSign inAsk grounded questions over the indexed code

Add a badge to your README

Both badges are public, cached, and update on their own after every index. Nothing to install.

Repowise badge

Links to this page. Adding it also re-indexes the repo every week.

Repowise badge: explore code
[![repowise](https://api.repowise.dev/badge/wiki/earendil-works/pi.svg)](https://repowise.dev/repo/earendil-works/pi)

Code health badge

Average health across every file, straight from the latest index.

Code health badge showing the average health score out of 10
[![Code health](https://api.repowise.dev/badge/health/earendil-works/pi.svg)](https://repowise.dev/repo/earendil-works/pi)

How earendil-works/pi works

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI This page is an auto-generated, always-fresh map of the earendil-works/pi repository, written primarily in TypeScript. Repowise indexes the source, parses every symbol, computes a dependency graph, scores per-file code health from complexity, duplication, test coverage and churn, mines git history for hotspots and ownership, and lifts the resulting architectural decisions into a wiki you can read or query through MCP.

The codebase has 1,577 source files, 12,551 symbols, and 11 languages, organised into 22 modules, led by typescript, markdown, json. Static analysis leaves 6,198 open findings across the three health dimensions.

Use the links above to open the interactive dashboards, or connect this repo to your editor via the Repowise MCP server for grounded answers inside Claude, Cursor, or VS Code.