is Nikolay Nikitin, PhD. I’m the Analysis Lead on the AI Institute of ITMO College and an open-source fanatic. I typically see a lot of my colleagues failing to seek out the time and vitality to create open repositories for his or her analysis papers and to make sure they’re of correct high quality. On this article, I’ll talk about how we may also help clear up this drawback utilizing OSA, an AI software developed by our staff that helps the repository develop into a greater model of itself. When you’re sustaining or contributing to open supply, this submit will prevent effort and time: you’ll find out how OSA can routinely enhance your repo by including a correct README, producing documentation, organising CI/CD scripts, and even summarizing the important thing strengths and weaknesses of the mission.
There are numerous totally different documentation enchancment instruments. Nonetheless, they give attention to totally different particular person elements of repository documentation. For instance, the Readme-AI software generates the README file, but it surely doesn’t account for added context, which is vital, for instance, for repositories of scientific articles. One other software, RepoAgent, generates full documentation for the repository code, however not README or CI/CD scripts. In distinction, OSA considers the repository holistically, aiming to make it simpler to know and able to run. The software was initially made for our colleagues in analysis, together with biologists and chemists, who typically lack expertise in software program engineering and fashionable growth practices. The principle intention was to assist them make the repository extra readable and reproducible in a number of clicks. However OSA can be utilized on any repository, not solely scientific ones.
Why is it wanted?
Scientific open supply faces challenges with the reuse of analysis outcomes. Even when code is shared with scientific papers, it’s not often obtainable or full. This code is often troublesome to learn; there is no such thing as a documentation for it, and generally even a primary README is lacking, because the developer meant to write down it on the final second however didn’t have time. Libraries and frameworks typically lack primary CI/CD settings akin to linters, automated assessments, and different high quality checks. Subsequently, it’s unattainable to breed the algorithm described within the article. And this can be a huge drawback, as a result of if somebody publishes their analysis, they do it with a need to share it with the group
However this drawback isn’t restricted to science solely. Skilled builders additionally typically postpone writing readme and documentation for lengthy intervals. And if a mission has dozens of repositories, sustaining and utilizing them could be difficult.
Ideally, every repository needs to be straightforward to run and user-friendly. And infrequently the posted developments typically lack important components akin to a transparent README file or correct docstrings, which could be compiled into full documentation utilizing customary instruments like mkdocs.
Primarily based on our expertise and evaluation of the issue, we tried to counsel an answer and implement it because the Open Supply Advisor software – OSA.
What’s the OSA software?
OSA is an open-source Python library that leverages LLM brokers to enhance open-source repositories and make them simpler to reuse.
The software is a bundle that runs by way of a command-line interface (CLI). It may also be deployed regionally utilizing Docker. By specifying an API key on your most well-liked LLM, you’ll be able to work together with the software by way of the console. You can even attempt OSA by way of the general public internet GUI. There’s quick introduction to principal concepts of repository enchancment with OSA:
How does OSA work?
The Open Supply Advisor (OSA) is a multi-agent software that helps enhance the construction and value of scientific repositories in an automatic approach. It addresses frequent points in analysis tasks by dealing with duties akin to producing documentation (README recordsdata, code docstrings), creating important recordsdata (licenses and necessities), and suggesting sensible enhancements to the repository. Customers merely present a repository hyperlink and may both obtain an routinely generated Pull Request (PR) with all beneficial modifications or overview the options regionally earlier than making use of them.
OSA can be utilized in two methods: by cloning the repository and operating it by a command-line interface (CLI), or by way of an internet interface. It additionally provides three working modes: primary, automated, and superior, that are chosen at runtime to suit totally different wants. In primary mode, OSA applies a small set of normal enhancements with no additional enter: it generates a report, README, group documentation, and an About part, and provides frequent folders like “assessments” and “examples” in the event that they’re lacking. Superior mode provides customers full handbook management over each step. In automated mode, OSA makes use of an LLM to research the repository construction and the prevailing README, then proposes an inventory of enhancements for customers to approve or reject. An experimental multi-agent conversational mode can be being developed, permitting customers to specify desired enhancements in free-form pure language by way of the CLI. OSA interprets this request and applies the corresponding modifications. This mode is at present beneath lively growth.
One other key power of OSA is its flexibility with language fashions. It really works with standard suppliers like OpenRouter and OpenAI, in addition to native fashions akin to Ollama and self-hosted LLMs operating by way of FastAPI.
OSA additionally helps a number of repository platforms, together with GitHub and GitLab (each GitLab.com and self-hosted situations). It will probably modify CI/CD configuration recordsdata, arrange documentation deployment workflows, and accurately configure paths for group documentation.
an experimental multi-agent system (MAS), at present beneath lively growth, that serves as the idea for its automated and conversational modes. The system decomposes repository enchancment right into a sequence of reasoning and execution phases, every dealt with by a specialised agent. Brokers talk by way of a shared state and are coordinated by a directed state graph, enabling conditional transitions and iterative workflows.
README era
OSA features a README era software that routinely creates clear and helpful README recordsdata in two codecs: a normal README and an article-style README. The software decides which format to make use of by itself, for instance, if the person supplies a path or URL to a scientific paper by the CLI, OSA switches to the article format. To begin, it scans the repository to seek out an important recordsdata, specializing in core logic and mission descriptions, and takes under consideration the folder construction and any present README.
For the usual README, OSA analyzes the important thing mission recordsdata, repository construction, metadata, and the primary sections of an present README if one is current. It then generates a “Core Options” part that serves as the inspiration for the remainder of the doc. Utilizing this data, OSA writes a transparent mission overview and provides a “Getting Began” part when instance scripts or demo recordsdata can be found, serving to customers rapidly perceive tips on how to use the mission.
In article mode, the software creates a abstract of the related scientific paper and extracts related data from the primary code recordsdata. These items are mixed into an Overview that explains the mission targets, a Content material part that describes the primary elements and the way they work collectively, and an Algorithms part that explains how the applied strategies match into the analysis. This method retains the documentation scientifically correct whereas making it simpler to learn and perceive.
Documentation era
The documentation era software produces concise, context-aware documentation for features, strategies, courses, and code modules. The documentation era course of is as follows:
(1) Reference parsing: Initially, a TreeSitter-driven parser fetches imported modules and resolves paths to them for every explicit supply code file, forming an import map that may additional be used to find out methodology and performance requires the international modules utility. By implementing such an method, it’s comparatively straightforward to rectify interconnections between totally different elements of the processed mission and to tell apart between inside aliases. Together with the import maps, the parser additionally preserves common data such because the processing file, an inventory of occurring courses, and standalone features. Every class incorporates its identify, attributes listing, decorators, docstring, listing of its strategies, and every methodology has its particular particulars that are of the identical construction as standalone features, that’s: methodology identify, docstring, return sort, supply code and alias resolved international methodology calls with a reputation of the imported module, class, methodology, and path to it.
(2) Preliminary docstrings era for features, strategies, and courses: With a parser having a construction fashioned, an preliminary docstrings era stage is ongoing. Solely docstrings that lack courses, strategies, and features are processed at this stage. Here’s a common description of what the ‘what’ methodology does. The context is generally the tactic’s supply code, since at this level, forming a common description of the performance is essential. The onward immediate contains details about the tactic’s arguments and interior decorators, and it trails with the supply code of the known as international strategies to supply further context for processing methodology utility. A neat second right here is that class docstrings are generated solely in any case their docstring-lacking strategies are generated; then class attributes, their strategies’ names, and docstrings are supplied to the mannequin.
(3) Era of “the primary thought” of the mission utilizing descriptions of elements derived from the earlier stage.
(4) Docstrings replace utilizing generated “principal thought”: Therefore, all docstrings for the mission are presumably current, era of the primary thought of the mission could be carried out. Primarily, the immediate for the concept consists of docstrings for all courses and features, together with their significance rating primarily based on the speed of prevalence of every element within the import maps talked about earlier than, and their place within the mission hierarchy decided by supply path. The mannequin response is returned in markdown format, summarizing the mission’s elements. As soon as the primary thought is acquired, the second stage of docstring era begins, throughout which the entire mission’s supply code elements are processed. At this second, the important thing focus is on offering the mannequin with an unique or generated docstring on the preliminary stage docstring with the primary thought to elaborate on ‘why’ this element is required for the mission. The supply code for the strategies can be being supplied, since an expanded mission narrative might immediate the mannequin to right some factors within the unique docstring.
(5) Hierarchical modules description era ranging from the underside to the highest.
(6) Utilizing Mkdocs and GitHub pages for automated documentation pushing and streaming: Remaining stage of the docstring pipeline, contemplating a recursive traversal throughout the mission’s modules and submodules. Hierarchy is predicated on the supply path; at every leaf-processing degree, a beforehand parsed construction is used to create an outline of which submodule is used, in accordance with the primary thought. As processing strikes to greater ranges of the hierarchy, generated submodules’ summaries are additionally used to supply further context. The mannequin returns summaries in Markdown to make sure seamless integration with the mkdocs documentation era pipeline. The entire schema of the method is described within the picture under.
CI/CD and construction group
OSA provides an automatic CI/CD setup that works throughout totally different repository internet hosting platforms. It generates configurable workflows that make it simpler to run assessments, verify code high quality, and deploy tasks. The software helps frequent utilities akin to Black for code formatting, unit_test for operating assessments, PEP8 and autopep8 for type checks, fix_pep8 for automated type fixes, pypi_publish for publishing packages, and slash_command_dispatch for dealing with instructions. Relying on the platform, these workflows are positioned within the applicable areas, for instance, .github/workflows/ for GitHub or a .gitlab-ci.yml file within the repository root for GitLab.
Customers can customise the generated workflows utilizing choices like –use-poetry to allow Poetry for dependency administration, –branches to outline which branches set off the workflows (by default, principal and grasp), and code protection settings by way of --codecov-token and --include-codecov.
To make sure dependable testing, OSA additionally reorganizes the repository construction. It identifies take a look at and instance recordsdata and strikes them into standardized assessments and examples directories, permitting CI workflows to run assessments persistently with out further configuration.
Workflow recordsdata are created from templates that mix project-specific data with user-defined settings. This method retains workflows constant throughout tasks whereas nonetheless permitting flexibility when wanted.
OSA additionally automates documentation deployment utilizing MkDocs. For GitHub repositories, it generates a YAML workflow within the .github/workflows listing and requires enabling learn/write permissions and deciding on the gh-pages department for deployment within the repository settings. For GitLab, OSA creates or updates the .gitlab-ci.yml file to incorporate construct and deployment jobs utilizing Docker photos, scripts, and artifact retention guidelines. Documentation is then routinely printed when modifications are merged into the primary department.
The right way to use OSA
To start utilizing OSA, select your repository with draft code that’s incomplete or underdocumented. Optionally, embrace a associated scientific paper or one other doc describing the library or algorithm applied within the chosen repo. The paper is uploaded as a separate file and used to generate the README. You can even specify the LLM supplier (e.g., OpenAI) and the mannequin identify (akin to GPT-4o).
OSA generates suggestions for bettering the repository, together with:
- A README file generated from code evaluation, utilizing customary templates and examples
- Docstrings for courses and strategies which can be at present lacking, to allow automated documentation era with MkDocs
- Fundamental CI/CD scripts, together with linters and automatic assessments
- A report with actionable suggestions for bettering the repository
- Contribution pointers and recordsdata (Code of Conduct, pull request and challenge templates, and so forth.)
You’ll be able to simply set up OSA by operating:
pip set up osa_toolAfter organising the surroundings, you must select an LLM supplier (akin to OpenAI or an area mannequin). Subsequent, you must add GIT_TOKEN (GitHub token with customary repo permissions) and OPENAI_API_KEY (in case you use OpenAI-compatible API) as surroundings variables, or you’ll be able to retailer them within the .env file as nicely. Lastly, you’ll be able to launch OSA immediately from the command line. OSA is designed to work with an present open-source repository by offering its URL. The essential launch command contains the repository deal with and elective parameters such because the operation mode, API endpoint, and mannequin identify:
osa_tool -r {repository} [--mode {mode}] [--api {api}] [--base-url {base_url}] [--model {model_name}]OSA helps three working modes:
- auto (default) – analyzes the repository and creates a personalized enchancment plan utilizing the specialised LLM agent.
- primary – applies a predefined set of enhancements: generates a mission report, README, group pointers, an “About” part, and creates customary directories for assessments and examples (if they’re lacking).
- superior – permits handbook choice and configuration of actions earlier than execution.
Further CLI choices can be found right here. You’ll be able to customise OSA by passing these choices as arguments to the CLI, or by deciding on desired options within the interactive command-line mode.
As soon as launched, OSA performs an preliminary evaluation of the repository and shows key data: common mission particulars, the present surroundings configuration, and tables with deliberate and inactive actions. The person is then prompted to both settle for the urged plan, cancel the operation, or enter an interactive modifying mode.
In interactive mode, the plan could be modified: actions toggled on or off, parameters (strings and lists) adjusted, and extra choices configured. The system guides the person by every motion’s description, doable values, and present settings. This course of continues till the person confirms the ultimate plan.
This CLI-based workflow ensures flexibility, from absolutely automated processing to specific handbook management, making it appropriate for each fast preliminary assessments and detailed mission refinements.
OSA additionally contains an experimental conversational interplay mode that enables customers to specify desired repository enhancements utilizing free-form pure language by way of the CLI. If the request is ambiguous or insufficiently associated to repository processing, the system iteratively requests clarifications and permits the connected supplementary file to be up to date. As soon as a legitimate instruction is obtained, OSA analyzes the repository, selects the suitable inside modules, and executes the corresponding actions. This mode is at present beneath lively growth.
When OSA finishes, it creates a pull request (PR) within the repository. The PR contains all proposed modifications, such because the README, docstrings, documentation web page, CI/CD scripts, сontribution pointers, report, and extra. The person can simply overview the PR, make modifications if wanted, and merge it into the mission’s principal department.
Let’s have a look at an instance. GAN-MFS is a repository that gives a PyTorch implementation of Wasserstein GAN with Gradient Penalty (WGAN-GP). Right here is an instance of a command to launch OSA on this repo:
osa_tool -r github.com/Roman223/GAN_MFS --mode auto --api openai --base-url https://api.openai.com/v1 --model gpt-4.1-miniOSA made a number of contributions to the repository, together with a README file generated from the paper’s content material.
OSA additionally added a License file to the pull request, in addition to some primary CI/CD scripts.
OSA added docstrings to all courses and strategies the place documentation was lacking. It additionally generated a structured, web-based documentation website utilizing these docstrings.
The generated report contains an audit of the repository’s key elements: README, license, documentation, utilization examples, assessments, and a mission abstract. It additionally analyzes key sections of the repository, akin to construction, README, and documentation. Primarily based on this evaluation, the system identifies key areas for enchancment and supplies focused suggestion.
Lastly, OSA interacts with the goal repository by way of GitHub. The OSA bot creates a fork of the repository and opens a pull request that features all proposed modifications. The developer solely must overview the options and modify something that appears incorrect. In my view, that is a lot simpler than writing the identical README from scratch. After overview, the repository maintainer efficiently merged the pull request. All modifications proposed by OSA can be found right here.
Though the variety of modifications launched by the OSA is critical, it’s troublesome to evaluate the general enchancment in repository high quality. To do that, we determined to look at the repository from a safety perspective. The scorecard software permits us to guage the repository utilizing the aggregated metric. Scorecard was created to assist open supply maintainers enhance their safety finest practices and to assist open supply customers choose whether or not their dependencies are protected. The mixture rating takes under consideration many repository parameters, together with the presence of binary artifacts, CI/CD assessments, the variety of contributors, and a license. The aggregated rating of the unique repository was 2.2/10. After the processing by OSA, it rose to three.7/10. This occurred as a result of addition of a license and CI/CD scripts. This rating should appear too low, however the repository being processed isn’t meant for integration into giant tasks. It’s a small software for producing artificial information primarily based on a scientific article, so its safety necessities are decrease.
What’s Subsequent for OSA?
We plan to combine a RAG system into OSA, primarily based on finest practices in open-source growth. OSA will evaluate the goal repository with reference examples to determine lacking elements. For instance, if the repository already has a high-quality README, it received’t be regenerated. Initially, we used OSA for Python repositories, however we plan to help further programming languages sooner or later.
If in case you have an open repository that requires enchancment, give OSA a attempt! We might additionally admire concepts for brand spanking new options that you could depart as points and PRs.
When you want to use OSA in your works, it may be cited as:
Nikitin N. et al. An LLM-Powered Device for Enhancing Scientific Open-Supply Repositories // Championing Open-source DEvelopment in ML Workshop@ ICML25.
