# knownsec/aipyapp

AI-Powered Python & Python-Powered AI (Python-Use)

Repository: https://github.com/knownsec/aipyapp
Canonical: https://ross.abutalabs.com/products/aipyapp
Homepage: https://aipy.app
Language: HTML
License: NOASSERTION
License Family: other
Last push: 2026-02-15T22:56:49+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 71, longevity 36
- inputs: {"age_days": 514, "days_push": 199, "days_rel": 199, "gap_med": 2.0, "n_releases_24m": 29}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4017, forks 407 (observed 2026-08-28T04:08:32.445955+00:00)

## What it is
AiPy (Python-Use) is an AI desktop assistant from Knownsec that implements a 'Code is Agent' paradigm: it gives an LLM a full Python execution environment so it can plan, write, run, and debug code to complete real-world tasks from natural-language instructions. It runs locally on Windows, macOS, and Linux, supporting data analysis, office automation, web scraping, and API orchestration without plugins, MCP servers, or workflow editors.

## Use cases
- automate data analysis and generate reports from natural language
- batch process Word, PPT, and PDF documents
- scrape and organize web data with browser control
- call online and private business APIs from plain-language commands
- run an AI agent that executes code locally for privacy
- replace tool/plugin-based agent frameworks with direct code execution

## When to choose
- you want a task-driven AI assistant that actually executes code on your machine
- you prefer avoiding MCP servers, tool registration, and workflow editors
- you need local data processing for security and control
- your tasks involve Python's ecosystem: data, automation, web, files

## When to avoid
- you need a lightweight library to embed in your own application
- you require a permissively licensed dependency (license is non-standard)
- you want a sandboxed, cloud-only agent that cannot touch your local environment
- you need fine-grained, auditable tool-calling workflows rather than autonomous code execution

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, interpreter, web-scraping, data-science, workflow-automation, cli, gui
- domain: artificial-intelligence, large-language-models, developer-tools, data-science
- platform: windows, python, cross-platform
- tags: python-use, code-as-agent, ai-assistant, task-automation, natural-language-commands, desktop-assistant, no-mcp, ai-agents, automation, macos, linux, desktop

## Member repositories
- knownsec/aipyapp (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:32.445955+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:57.958938+00:00, confidence not recorded.
  - readme: https://github.com/knownsec/aipyapp (fetched 2026-08-28T04:08:32.445955+00:00, sha 97b2b93a4dad)
  - homepage: https://aipy.app (fetched 2026-08-29T09:16:53.347301+00:00, sha c00f2595143b)
  - site_page: https://www.aipy.app/faq.html (fetched 2026-08-29T09:16:53.356682+00:00, sha a4aa7ffdd66d)
- Data as of 2026-08-30T08:39:29.467469+00:00.