nandhakishorm / laya
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
github.com/nandhakishorm/layaIndexed at 23a1752Up to date with upstream
About this codebase
Laya is a codebase documentation and routing engine: it consumes a target repository (source files plus optional checkpoints), traverses and parses the inputs into analyzable structures, runs prediction and decision pipelines (via router and agent flows, optionally with ONNX and model-specific routing hooks), and produces structured artifacts like routed decisions, prediction outputs, and LLM-synthesised wiki pages served through an HTTP server and an MCP interface. In practice, developers use Laya to turn code and documentation-adjacent evidence into navigable guidance—then expose that capability to tools like the web UI, LangChain/LangGraph workflows, and external clients via MCP.
Written by gpt-5.4-nano from the index
207 files and 1,964 symbols in 10 modules, led by Python (108 files) and TypeScript (23).
Code health
This codebase scores 7.4 out of 10 for code health, which we rate good. It also scores maintainability 7.5 and static performance 9.9 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 20 of 207 files are git hotspots, and they average 5.1 — which is where the fixes pay off most.
On the leaderboards:#12 of 44 Python repos
Do next
1 thing worth doing in the week to Sep 24, the last indexed commit, 1 of them now.
Now
- Critical
Clean up what this week's commits left: 61 serious findings in 24 files
21 commits in the last 7 days added or worsened them, and they are still open. Start with
research/benchmarks/feishu_zh/audit.py, which has 2 critical.- serious findings
- 61
- critical
- 9
- files
- 24
Large effort
Improve what Repowise can see
Add a test coverage report
Without one, Repowise cannot tell tested code from untested code, so every test-related action says “unknown”.
- line coverage
- Unknown, no report
Small effort
Use nandhakishorm/laya in your agent
Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.
https://api.repowise.dev/mcp/nandhakishorm/layaOne command, run anywhere. Adds the server to your local Claude Code config.
Docsclaude mcp add --transport http repowise https://api.repowise.dev/mcp/nandhakishorm/laya \ --header "Authorization: Bearer rw_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
This repo is public, so anyone with a Repowise account and an API key can connect.
Try asking
- get_overview()
- get_answer("how is laya put together?")
- get_why("why is laya structured this way?")
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.
Go deeper
- OverviewEverything the index found, what changed this week, commits and decisions.
- DocumentationModule-by-module documentation, 226 pages, 15 written by a model.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score, the findings behind it, tests and refactoring plans.
- CommitsEach commit's effect on code health, with agent provenance.
- ContributorsWho owns what, and where one person holds most of the knowledge.
- DecisionsArchitectural decisions mined from commits and pull requests.
- Ask this codebaseSign inGrounded answers over the indexed code.
Maintain this repo? Claim the page
Sign in with GitHub and we check that you are an admin or maintainer of nandhakishorm/laya. Then add a badge to the README that links readers here.
Use this repo from Claude or ChatGPT
Add this URL as a custom connector and sign in with repowise when asked. No API key to copy.
https://api.repowise.dev/mcp/nandhakishorm/layaFor maintainers
Add a badge to your README
Every badge is public, cached, and updates on its own after every index. Nothing to install.
Repowise badge
Links to this page, with no score on it. Adding it also re-indexes the repo every week.
[](https://repowise.dev/repo/nandhakishorm/laya?src=badge_wiki)Code health badge
The repo's health score out of 10, from the latest index.
[](https://repowise.dev/repo/nandhakishorm/laya?src=badge_health)Code health card
A larger card with the score, its change since the last index, and when it was measured. The HTML version follows the reader's light or dark theme.
[](https://repowise.dev/repo/nandhakishorm/laya?src=badge_card)How nandhakishorm/laya works
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request. This page is a map of the nandhakishorm/laya repository, written primarily in Python, rebuilt from the source each time it is indexed. Repowise 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 architectural decisions into documentation you can read here or query through MCP.
The codebase has 207 files and 1,964 symbols in 10 modules, led by Python, TypeScript and JavaScript. Code health is 7.4 out of 10, rated good.
Use the links above to open each view, or connect this repository to your agent for grounded answers inside Claude, Cursor, Codex or VS Code.