Project Info

Lentil

Devpost

Terminal output messages often vary significantly in clarity and usefulness. Many developers know the frustration of compiling a program only to be overwhelmed by hundreds of lines of cryptic or irrelevant messages. Lentil is a tool that enhances command-line output by filtering unnecessary noise and emphasising the most relevant information. It goes a step further by suggesting potential fixes based on the context of your project files. Lentil empowers developers to navigate complex compiler outputs more efficiently, reducing time spent on debugging. Usage Just type lentil before your usual compilation command! Instead of sifting through a sea of cryptic messages, view it through Lentil. Lentil captures both stdout and stderr, then uses retrieval-augmented generation (RAG) techniques to contextualise the output. By analysing your project files recursively, it converts compiler messages into a standardised intermediate representation (IR), which is then presented in a clear and structured format on the webapp. Key Features Live updates: Continuously reflects changes as you code. Language agnostic: Works with any programming language and integrates seamlessly with various editors. Flexible integration: Can be used as a standalone command or integrated into existing tools via its IR. Architecture Overview Core application The core is built with OCaml and is responsible for: Capturing stdout, stderr, and the context of the current working directory Producing a standardised IR that powers the frontend Starting the web server Web server Lentil also includes a web server written in Python, serving three main functions: RAG facilitation: Using a Chroma vector database for contextual analysis LLM inference: Generating AI-driven explanations and recommendations Web interface: Offering a modern, browser-based view for enhanced user experience To start the web server: Get Started Explore the code and contribute to the project on GitHub.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • FlaskIn code
  • HTMLIn code
  • JavaScriptIn code
  • OllamaIn code
  • OpenAIIn code
  • PythonIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code

10 of 10 appear in the indexed code.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

22 KB

Source files

22

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars