lever

niansong1996/lever

Supports learning to verify language-to-code generation with execution

GitHub Website

GraphCanon updated 2w · GitHub synced 2w

90 stars8 forksLast push 3y Python MIT

Decision brief

Lever offers support for verifying language-to-code generation through actual code execution.

Good fit when

When the development team needs to verify accuracy of generated code from language inputs based on execution, and has access to Linux machines to ensure seamless functionality.
If you are working on projects that require rigorous testing and validation of code derived from natural language descriptions.

Avoid when

Avoid Lever if developing in an environment other than Linux as it requires the use of tree-sitter parsers, which may not be compatible with your system.
Do not choose Lever if you seek a tool that does not require setting up a conda environment and installing specific dependencies to operate.

Requirements:: All of the pipelines have been tested on Linux machines only, requiring possibly custom `tree-sitter` parsers for other platforms.

Observed Jul 17, 2026 · Source: enrich:decision_facts

lever alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (1127d since push); As of 2w
Provenance: Not a fork · Personal account; As of 2w
Security (OSV): No criticals; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install lever

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

open-code-review

Hybrid architecture code review tool with LLM Agent for precise line-level comments and built-in security rule checks.

21k★

pua

A skill package for enhancing the functionality of AI agents within development environments

19k★

CodeGeeX

CodeGeeX is an open multilingual code generation model implemented in Mindspore and available via PyTorch.

8.8k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Provides code for the paper LEVER from ICML'23 that focuses on verifying language-to-code generation through execution.

Capability facts

Languages: python
Source: github.language · Aug 5, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 5, 2026)

conda create -n lever python=3.8

Source link

README

Installation

(Recommended) Create a new conda environment

conda create -n lever python=3.8
conda activate lever

Install the dependencies

pip install -r requirements.txt

NOTE: all of the pipelines are only tested on Linux machines, you may need to build your own tree-sitter parsers if a different platform is used.

For agents

This page has a .md twin and JSON over the API.

/tools/niansong1996-lever.md GET /api/graphcanon/tools/niansong1996-lever GET /api/graphcanon/graph?tool=niansong1996-lever