oneShotCodeGen

Name: oneShotCodeGen
Author: vivek100

253stars28forks

How to install oneShotCodeGen?

vivek100/oneshotcodegen

$git clone https://github.com/vivek100/oneShotCodeGen

Installs into the current project.

Summary

A modular agent-based system for generating and editing app configurations through AI-driven steps organized in flows.

Files · 1

View on GitHub

README.md

1	# oneShotCodeGen - AI Retool/ERP App Generation
2
3	A modular agent-based system for generating and editing app configurations through AI-driven steps organized in flows.
4
5	## Overview
6
7	This project provides an advanced AI-powered platform for automatically generating and editing enterprise application configurations through a series of intelligent agent flows. Built with a modular architecture, it leverages OpenAI's APIs and structured generation to produce consistent, high-quality app specifications.
8
9	Repository: [https://github.com/vivek100/oneShotCodeGen](https://github.com/vivek100/oneShotCodeGen)
10
11	## Project Structure
12
13	- backend/: Modular FastAPI backend with agent flow system
14	- frontend/: React-based frontend interface with real-time updates
15
16	## Quick Start
17
18	### Backend Setup
19
20	1. Clone the repository:
21	```bash
22	git clone https://github.com/vivek100/oneShotCodeGen.git
23	cd oneShotCodeGen
24	```
25
26	2. Set up Python environment:
27	```bash
28	cd backend
29	python -m venv venv
30	# On Windows
31	venv\Scripts\activate
32	# On macOS/Linux
33	source venv/bin/activate
34	```
35
36	3. Install dependencies:
37	```bash
38	pip install -r requirements.txt
39	```
40
41	4. Create environment file:
42	```bash
43	cp sample.env .env
44	```
45
46	5. Configure your environment variables in `.env`:
47	```
48	# API Configuration
49	HOST=0.0.0.0
50	PORT=8000
51
52	# Database Configuration
53	DB_URL=sqlite:///./agent.db
54
55	# OpenAI API Configuration
56	OPENAI_API_KEY=your_openai_api_key_here
57	OPENAI_MODEL_NAME=gpt-4.1-nano
58
59	# Frontend Configuration (for CORS)
60	FRONTEND_ORIGIN=http://localhost:3000
61	```
62
63	6. Start the backend server:
64	```bash
65	# Development mode with auto-reload
66	python main.py
67	# Or using uvicorn directly
68	uvicorn main:app --host 0.0.0.0 --port 8000 --reload
69	```
70
71	The backend API will be available at `http://localhost:8000`.
72
73	### Frontend Setup
74
75	1. Navigate to the frontend directory:
76	```bash
77	cd frontend
78	```
79
80	2. Install Node.js dependencies:
81	```bash
82	npm install
83	```
84
85	3. Create environment file:
86	```bash
87	cp .env.example .env.local
88	```
89
90	4. Configure your environment variables in `.env.local`:
91	```
92	NEXT_PUBLIC_BACKEND_URL=http://localhost:8000
93	```
94
95	5. Start the development server:
96	```bash
97	npm run dev
98	```
99
100	The frontend will be available at `http://localhost:3000`.
101
102	## Backend Architecture
103
104	The backend is built with a modular architecture focused on managing agent flows and step execution:
105
106	### Core Modules
107
108	1. Agent Router: Routes user messages to appropriate flows based on the main agent decision.
109	2. Flow Registry: Manages flow definitions and their steps.
110	3. Flow Runner: Orchestrates flow execution by running steps in sequence.
111	4. Step Executor: Executes individual steps (AI or tool calls).
112	5. Tool Call Module: Executes non-AI operations like entity reorganization, merging, etc.
113	6. Prompt & Schema Store: Manages prompt templates, schemas, and examples.
114	7. Message Dispatcher: Handles system messages during flow execution.
115	8. Replay Engine: Re-runs steps with original or modified inputs for testing and debugging.
116	9. WebSocket Manager: Provides real-time communication for chat messages and flow status updates.
117
118	### Flow Types
119
120	- Main Agent Flow: Decides what to do with user input
121	- Create App Flow: Generates a complete app configuration
122	- Edit Decision Flow: Decides how to handle edit requests
123	- Partial Edit Flow: Updates specific parts of an app configuration
124
125	### Database Structure
126
127	The system uses SQLite with the following key tables:
128
129	- Projects: Stores project metadata
130	- Messages: Stores chat messages for each project
131	- AppVersions: Stores app configuration versions
132	- Flows: Stores flow definitions
133	- Steps: Stores step definitions within flows
134	- FlowRuns: Tracks executions of flows
135	- StepRuns: Tracks executions of individual steps
136	- Prompts: Stores prompt templates
137	- Schemas: Stores JS

People who liked this also viewed

6 picks

Type

components-helperBased on the docs to provide code prompt files for vue component libraryPromptsNov 202312k36
VibeCode-Protocol-SuiteA comprehensive suite of protocols, meta-prompts, and orchestration tools designed to streamline software development workflows, project management, and team collaboration. Includes the VibeCode Protocol Suite with web interface, user manuals, and reusable templates for efficient development processes.PromptsJul 20262.3k24
Promptable-web-sdkWeb SDK for Promptable Website.PromptsDec 20221.3k37
LLMFlexA python package for developing AI applications with local LLMs.PromptsJan 2025151150
cli-repo-to-promptexport any codebase to a single LLM-ready markdown promptPromptsJul 202610653
Files2PromptVS Code extension to copy files for an LLM promptPromptsApr 20255923

oneShotCodeGen

253stars28forks

View on GitHub

How to install oneShotCodeGen?

vivek100/oneshotcodegen

$git clone https://github.com/vivek100/oneShotCodeGen

Installs into the current project.

Summary

A modular agent-based system for generating and editing app configurations through AI-driven steps organized in flows.

Files · 1

View on GitHub

README.md

1	# oneShotCodeGen - AI Retool/ERP App Generation
2
3	A modular agent-based system for generating and editing app configurations through AI-driven steps organized in flows.
4
5	## Overview
6
7	This project provides an advanced AI-powered platform for automatically generating and editing enterprise application configurations through a series of intelligent agent flows. Built with a modular architecture, it leverages OpenAI's APIs and structured generation to produce consistent, high-quality app specifications.
8
9	Repository: [https://github.com/vivek100/oneShotCodeGen](https://github.com/vivek100/oneShotCodeGen)
10
11	## Project Structure
12
13	- backend/: Modular FastAPI backend with agent flow system
14	- frontend/: React-based frontend interface with real-time updates
15
16	## Quick Start
17
18	### Backend Setup
19
20	1. Clone the repository:
21	```bash
22	git clone https://github.com/vivek100/oneShotCodeGen.git
23	cd oneShotCodeGen
24	```
25
26	2. Set up Python environment:
27	```bash
28	cd backend
29	python -m venv venv
30	# On Windows
31	venv\Scripts\activate
32	# On macOS/Linux
33	source venv/bin/activate
34	```
35
36	3. Install dependencies:
37	```bash
38	pip install -r requirements.txt
39	```
40
41	4. Create environment file:
42	```bash
43	cp sample.env .env
44	```
45
46	5. Configure your environment variables in `.env`:
47	```
48	# API Configuration
49	HOST=0.0.0.0
50	PORT=8000
51
52	# Database Configuration
53	DB_URL=sqlite:///./agent.db
54
55	# OpenAI API Configuration
56	OPENAI_API_KEY=your_openai_api_key_here
57	OPENAI_MODEL_NAME=gpt-4.1-nano
58
59	# Frontend Configuration (for CORS)
60	FRONTEND_ORIGIN=http://localhost:3000
61	```
62
63	6. Start the backend server:
64	```bash
65	# Development mode with auto-reload
66	python main.py
67	# Or using uvicorn directly
68	uvicorn main:app --host 0.0.0.0 --port 8000 --reload
69	```
70
71	The backend API will be available at `http://localhost:8000`.
72
73	### Frontend Setup
74
75	1. Navigate to the frontend directory:
76	```bash
77	cd frontend
78	```
79
80	2. Install Node.js dependencies:
81	```bash
82	npm install
83	```
84
85	3. Create environment file:
86	```bash
87	cp .env.example .env.local
88	```
89
90	4. Configure your environment variables in `.env.local`:
91	```
92	NEXT_PUBLIC_BACKEND_URL=http://localhost:8000
93	```
94
95	5. Start the development server:
96	```bash
97	npm run dev
98	```
99
100	The frontend will be available at `http://localhost:3000`.
101
102	## Backend Architecture
103
104	The backend is built with a modular architecture focused on managing agent flows and step execution:
105
106	### Core Modules
107
108	1. Agent Router: Routes user messages to appropriate flows based on the main agent decision.
109	2. Flow Registry: Manages flow definitions and their steps.
110	3. Flow Runner: Orchestrates flow execution by running steps in sequence.
111	4. Step Executor: Executes individual steps (AI or tool calls).
112	5. Tool Call Module: Executes non-AI operations like entity reorganization, merging, etc.
113	6. Prompt & Schema Store: Manages prompt templates, schemas, and examples.
114	7. Message Dispatcher: Handles system messages during flow execution.
115	8. Replay Engine: Re-runs steps with original or modified inputs for testing and debugging.
116	9. WebSocket Manager: Provides real-time communication for chat messages and flow status updates.
117
118	### Flow Types
119
120	- Main Agent Flow: Decides what to do with user input
121	- Create App Flow: Generates a complete app configuration
122	- Edit Decision Flow: Decides how to handle edit requests
123	- Partial Edit Flow: Updates specific parts of an app configuration
124
125	### Database Structure
126
127	The system uses SQLite with the following key tables:
128
129	- Projects: Stores project metadata
130	- Messages: Stores chat messages for each project
131	- AppVersions: Stores app configuration versions
132	- Flows: Stores flow definitions
133	- Steps: Stores step definitions within flows
134	- FlowRuns: Tracks executions of flows
135	- StepRuns: Tracks executions of individual steps
136	- Prompts: Stores prompt templates
137	- Schemas: Stores JS

People who liked this also viewed

6 picks

Type