🚀 Annukriti
AI Software Engineer in Your Terminal
Build • Debug • Explain • Improve • Automate
An open-source AI Software Engineering CLI powered by LangGraph and modern LLMs.
✨ What is Annukriti?
Annukriti is an AI Software Engineer that helps developers create, debug, understand, and improve software projects directly from the terminal.
Instead of simply chatting with an AI, Annukriti acts like an intelligent software engineer capable of planning architectures, generating code, fixing bugs, reviewing projects, and automating development workflows.
🚀 Features
🏗 AI Project Generator
Generate complete applications using natural language.
annukriti create "E-Commerce Website"
🐞 AI Debugger
Analyze your project and automatically identify errors.
annukriti debug
📖 Code Explainer
Understand unfamiliar code instantly.
annukriti explain app.py
💬 AI Chat
Ask programming questions directly from your terminal.
annukriti chat
📂 Project Scanner
Analyze an existing codebase.
annukriti scan
🤖 Multi-Agent Workflow
Powered by LangGraph agents.
- Planning Agent
- Coding Agent
- Debug Agent
- Review Agent
- Documentation Agent
⚙ Installation
pip
pip install Annukriti
uv
uv tool install Annukriti
🚀 Quick Start
Create a project
annukriti create "Netflix Clone"
Debug project
annukriti debug
Explain code
annukriti explain main.py
Chat with AI
annukriti chat
🖥 Example
> annukriti create "Portfolio Website"
✔ Understanding Requirements
✔ Planning Architecture
✔ Selecting Tech Stack
✔ Building Frontend
✔ Building Backend
✔ Creating Project Structure
✔ Writing Files
✔ Project Generated Successfully 🎉
🏛 Architecture
User
│
▼
CLI (Typer)
│
▼
LangGraph Workflow
│
┌──────────────┐
│ Planner │
│ Generator │
│ Debugger │
│ Reviewer │
│ Documentation│
└──────────────┘
│
▼
LLM (Groq / Gemini / OpenAI)
📦 Tech Stack
- Python
- LangGraph
- LangChain
- Typer
- Rich
- FastAPI
- Google Gemini
- Groq
- OpenAI
🔑 Environment Variables
Create a .env file.
GROQ_API_KEY=your_key
GOOGLE_API_KEY=your_key
OPENAI_API_KEY=your_key
🗺 Roadmap
Version 0.1
- CLI
- Project Generator
- Chat Assistant
Version 0.2
- AI Debugger
- Project Scanner
- Code Explainer
Version 0.3
- AI Code Reviewer
- File Editing
- Documentation Generator
Version 0.4
- React Generator
- FastAPI Generator
- Next.js Generator
Version 0.5
- GitHub Integration
- Test Generation
- Deployment Support
Version 1.0
- Autonomous AI Software Engineer
- End-to-End Project Development
- Automatic Bug Fixing
- Multi-Agent Collaboration
🤝 Contributing
Contributions are welcome.
git clone https://github.com/sumit-069/Annukriti
cd Annukriti
pip install -e .
📜 License
MIT License
👨💻 Author
Sumit Kumar Bajpai
GitHub
🌟 Vision
Annukriti aims to become an autonomous AI Software Engineer capable of understanding software projects, generating applications, debugging code, reviewing pull requests, writing documentation, creating tests, and automating the complete software development lifecycle.
The long-term goal is to provide developers with an intelligent engineering partner that works directly from the terminal.
⭐ If you like this project
Give it a ⭐ on GitHub.
Metadata
Release files for Annukriti 0.1.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| annukriti-0.1.8.tar.gz | 137.3 kB | Without provenance | Details for annukriti-0.1.8.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| annukriti-0.1.8-py3-none-any.whl | Python 3 | none | any | Details for annukriti-0.1.8-py3-none-any.whl |
Total release size: 157.3 kB
Release files / annukriti-0.1.8.tar.gz
| Download URL | annukriti-0.1.8.tar.gz |
|---|---|
| Size | 137.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ef6e27e2c71446ec4cf2cfff707c6bdd9d1842219dd5d9f5fc310340b3c3d987
|
|
BLAKE2b-256 checksum How to use checksums |
bf2a823701fc9602c05ebad6a838fff0d609e827e80233c618abdd43c0b5e2a3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.0
|
Release files / annukriti-0.1.8-py3-none-any.whl
| Download URL | annukriti-0.1.8-py3-none-any.whl |
|---|---|
| Size | 20.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d9cf7496159513d373c83c289de3ad29c51caa7601654e27eb20067036d3a0dc
|
|
BLAKE2b-256 checksum How to use checksums |
322d4d33d28f891cc51c091f71fc806d9c4ef58d6f61e513449e13ab4e6af2f7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.0
|
Security for Annukriti 0.1.8
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.