Skip to main content

LLM driven development and automatic repair kit.

Project description

ESBMC AI

AI Augmented ESBMC processing. Passes the output from ESBMC to an AI model that allows the user to use natural language to understand the output. As the output from ESBMC can be quite technical in nature. The AI can also be asked other questions, such as suggestions on how to fix the problem outputted by ESBMC, and to offer further explanations.

This is an area of active research.

ESBMC-AI Visual Abstract

Demonstration

Basic Usage Demo

demo.webm

Fix Code Demo

demo_fix_code.webm

YouTube Channel

More videos can be found on the ESBMC-AI Youtube Channel

ESBMC

From the ESBMC website:

ESBMC is an open source, permissively licensed, context-bounded model checker based on satisfiability modulo theories for the verification of single and multi-threaded C/C++ programs. It does not require the user to annotate the programs with pre- or postconditions, but allows the user to state additional properties using assert-statements, that are then checked as well. Furthermore, ESBMC provides two approaches (lazy and schedule recording) to model check multi-threaded programs. It converts the verification conditions using different background theories and passes them directly to an SMT solver.

From the ESBMC GitHub repo

The efficient SMT-based context-bounded model checker (ESBMC)

Wiki

For full documentation, see the ESBMC-AI Wiki. The README file contains quick setup instructions. For more detailed setup instructions, see the Initial Setup page.

Initial Setup

See Initial Setup Wiki Page.

Configuration/Settings

See Configuration Wiki page.

Usage

Read about how to run and use ESBMC-AI in this wiki page.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

  1. Keep the coding style consistent. Use the Black code formatter.
  2. Keep the righting style professional.
  3. Include comments and function doc-strings.
  4. Make sure to update tests as appropriate.

Acknowledgments

ESBMC-AI is made possible by the following listed entities:

License

GNU Affero General Public License v3.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

esbmc_ai-0.4.0.dev0.tar.gz (47.1 kB view hashes)

Uploaded Source

Built Distribution

esbmc_ai-0.4.0.dev0-py3-none-any.whl (41.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page