120 dependents
| Package | Description | Downloads/month |
|---|---|---|
| SWE-bench: Can Language Models Resolve Real-world Github Issues? | 38.3M | |
| An enterprise friendly way of detecting and preventing secrets in code. | 4.6M | |
| Python linting made easy. Also a casual yet honorific way to address individuals... | 327K | |
| Selectively run tests based on the current git diff and the collected data from ... | 227K | |
| Client for codeflash.ai - automatic code performance optimization, powered by AI | 184K | |
| Linting and Fixing Code for All Languages | 132K | |
| The Continuous Integration Framework | 54K | |
| Python wrapper for the Codegen API - run code agents at scale | 24K | |
| Convert black --diff output into a Code Climate report | 14K | |
| Secure AWS-hosted remote AI coding workstation with a provider-agnostic local CL... | 14K | |
| Automatic NAMD System Builder | 12K | |
| A realtime logging and aggregation server. | 11K | |
| Another best practice scanner for Ansible roles and playbooks | 11K | |
| The official SWE-fficiency package - a benchmark for evaluating LMs on automated... | 10K | |
| A tool for mapping spec markdowns to code change on PRs | 8K | |
| Run one or more linters on changed code | 8K | |
| Pytest plugin to get the coverage of the new lines (based on git diff) only | 6K | |
| Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving | 6K | |
| Composio powers 1000+ toolkits, tool search, context management, authentication,... | 5K | |
| Python utilities for Software Engineering + Machine Learning research. | 5K | |
| AI chat for JupyterLab | 4K | |
| A commanding (terminal) view of your test-coverage. | 4K | |
| This tool helps you rebase your package to the latest version | 4K | |
| Versioned file systems, graph retrieval, and vector search for AI agents. | 3K | |
| An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, ... | 3K | |
| Docker based continuous integration and code lint review system for BitBucket | 3K | |
| AI code review tool that works with any language model provider. It detects issu... | 3K | |
| ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬 | 3K | |
| An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, ... | 3K | |
| Scriptable interface to a powerful, multi-lingual language server built on top o... | 2K | |
| AI-powered CLI that decomposes PR diffs into causal threads for human code revie... | 2K | |
| AI automatic commit message | 2K | |
| Airfold CLI | 2K | |
| Two-column web-based git difftool | 2K | |
| A minimalistic wiki powered by python, markdown and git. | 2K | |
| An autonomous AI agent that learns your workflows. Chat-first, single binary, ze... | 2K | |
| Dev Assistant client | 2K | |
| AI-powered code review tool with local Git, remote MR/PR analysis, and CI integr... | 2K | |
| Run Ruff, but only on modified lines | 2K | |
| Multi-API Intelligent Router CLI — Claude Code-level capabilities with cost-opti... | 1K | |
| An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, ... | 1K | |
| Moulti is a CLI-driven Terminal User Interface (TUI) displaying arbitrary output... | 1K | |
| AI-powered CLI for developers using Claude with multi-API routing, test generati... | 1K | |
| Versioned file systems, graph retrieval, and vector search for AI agents. | 1K | |
| Development tools for template authors using Flexlate | 1K | |
| Vanir is a source code-based static analysis tool that automatically identifies ... | 973 | |
| A Git repository for difflicious | 911 | |
| A cross-platform code review tool using Gemini AI for GitHub, GitLab, and Azure ... | 856 | |
| A tool that builds executable code datasets with GitHub Actions. | 828 | |
| Official plugins for Sentry server | 827 |
