uvyadav04 / architekt-ai---server
pythonmaind342d362.3K linessynced 1mo ago
Code health
9.1out of 10Excellent
This codebase scores 9.1 out of 10 on defect risk, which we rate excellent. It also scores maintainability 9.4 and static performance risk 10.0 out of 10. The three are scored separately and never blended into one number. The files you change most are the weak spot: 3 of 32 files are git hotspots, and they average 8.2.
- Lines of code
- 2.3K
Recent activity
All commitsCommits
No commits indexed yet.
Decisions
- Use an iterative agent loop to refine outputsproposed
- Implement robust error handling inside agent loops to prevent cascading failuresproposed
- Use Singleton pattern for shared resources (LLM instances and vector DB connections)proposed
- Build the backend with FastAPI for asynchronous processingproposed
- Persist generated designs in MongoDBproposed
- Use Qdrant for efficient context retrieval via vector similarity searchproposed
Needs attention
23 open- medium severity. ProposedUse an iterative agent loop to refine outputsAuto-proposed decision awaiting review
- medium severity. ProposedImplement robust error handling inside agent loops to prevent cascading failuresAuto-proposed decision awaiting review
- medium severity. ProposedUse Singleton pattern for shared resources (LLM instances and vector DB connections)Auto-proposed decision awaiting review
- medium severity. ProposedBuild the backend with FastAPI for asynchronous processingAuto-proposed decision awaiting review
- medium severity. ProposedPersist generated designs in MongoDBAuto-proposed decision awaiting review
Where the risk concentrates
All 3 hotspotsRanked by prior bug fixes and change frequency, mined from full git history rather than from the code alone.
| File | Churn | Prior fixes | Maintainers | Commits 90d |
|---|---|---|---|---|
| chat.pyAPI_Layer/routes | 90.0th | 0 | 1bus factor 1 | 3 |
| graph_agent.pyLLM_Layer/Prompts | 86.7th | 0 | 1bus factor 1 | 7 |
| design.pyAPI_Layer/controllers | 80.0th | 0 | 1bus factor 1 | 10 |
Composition
Open the graphpython 94%markdown 3%yaml 3%
Explore this codebase
- Docs0 pages across 5 modules
- ChatAsk this codebase a question and get an answer with its sources
- Files32 files with per-file docs, health and history
- ArchitectureDependency graph, layers, and 2 entry points
- Code healthPer-file scores, 44 open findings, coverage and refactoring targets
- Knowledge graphEntities, communities, and the paths between them
- Change couplingFiles that keep changing together, mined from commit history
- CommitsChange-risk ranked history with agent provenance
- ContributorsBus factor, per-file maintainers, and the human/agent split
- StatsSize class, origin, lifetime churn, rhythm and records
- CostsWhat indexing this snapshot cost, by model and by run