The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Ocelot is an open-source code intelligence platform I designed to help developers and teams understand complex codebases through AI-powered search and natural language queries.
The system combines semantic retrieval, syntax-aware analysis, and dependency graphs to build a structured representation of a software project rather than treating source code as plain text.
Ocelot analyzes classes, methods, dependencies, and relationships across the codebase, allowing users to ask questions about architecture, business logic, implementation details, and dependencies in natural language.
Key capabilities include:
Hybrid semantic and syntax-aware code search
RAG-based question answering over source code
Dependency graph generation
Method and class-level indexing
Incremental indexing for changed files
Structured metadata extraction
Support for backend and frontend codebases
Java, Angular and TypeScript analysis
Architecture and business-logic exploration through natural language
I designed the architecture, indexing pipeline, retrieval strategy, dependency analysis, and AI interaction layer with a focus on making large codebases easier to navigate and understand.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
AI Fashion Shopping & Outfit Recommendation Platform
Designed a modern AI-powered fashion shopping platform that helps users discover personalized outfits and shop smarter.
The concept combines AI-driven outfit recommendations, style matching, virtual outfit previews, and a personalized wardrobe experience in a clean, premium interface.
Nice work
We’re choosing the motion for an AI analytics product demo, and I can’t decide.
Both clips show the same flow. Someone asks a question in plain English. The agent checks permissions, plans the query, runs it past guardrails and builds the dashboard.
1. A walks you through each step as it happens.
2. B skips the steps and drops you straight onto the result.
A shows the work. B shows the speed. For a landing page I keep going back and forth.
Which one would make you trust the product more? Comment A or B, and tell me why.
3 voted
100%
0 voted
0%
3 votes
Closed
I think according to your query the output should consist on a list of clients with late invoices rather then showing charts etc,
Aequa — AI-Powered Legal Navigator Design
A smarter way to navigate legal questions.
Aequa turns complex information into clear guidance, helping people understand their options and take the next step with confidence.
