Software Engineering Python Packages

swebench

SWE-bench: Can Language Models Resolve Real-world Github Issues?

swesmith

[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

pydriller

Python Framework to analyse Git repositories

sf-hamilton

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

python-scalpel

Scalpel: The Python Static Analysis Framework

apache-hamilton

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

sf-hamilton-sdk

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

swefficiency

Benchmark harness and code for "SWE-fficiency: Can Language Models Optimize Real World Repositories on Real World Workloads?"

sf-hamilton-ui

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

scinexus

composable apps for scientific programming

sf-hamilton-lsp

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

tiferet

Build an app, the beautiful way.

gemstack

Opinionated AI agent orchestration framework for Gemini CLI and Antigravity

gito-bot

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

ai-code-review

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

ai-cr

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

agent-feed

Turn AI coding chats into a source-controlled workflow: AGENTS.md, rules, skills, verification gates, and adapters for Codex, Claude Code, and Cursor.

dioxide

Opinionated, Zero-ceremony, Rust-backed dependency injection for Python

pepip

Shared global environment package installer using symlinks — like pnpm for Python

ra-aid

Develop software autonomously.

seutil

Python utilities for Software Engineering + Machine Learning research.

tree-plus

A `tree` util enhanced with tokens, lines, and components. `pip install -U tree_plus`

super-dev

Engineering workflow layer for AI coding tools with specs, review, quality gates, and traceability.为 AI 编程工具提供工程化流程、质量门禁与可追溯能力。

raise-cli

RaiSE Framework — Reliable AI-assisted Software Engineering. Lean methodology + deterministic toolkit for building production software with AI.