Eval Python Packages

asteval

minimalistic evaluator of python expression using ast module

evalidate

Safe and fast evaluation of untrusted user-supplied python expressions

swival

A small, powerful, open-source CLI coding agent that works with open models.

pixie-qa

Agent skill for AI agent development

litereval

Wrapper around ast.literal_eval with additional {foo='bar', key=None} dict syntax. + Deep merge two dictionaries.

oddish

Run Harbor tasks in the cloud with scheduling, monitoring, and persistent state

twinkle-eval

High-performance LLM evaluation framework with parallel API calls — up to 17× faster than sequential tools. Supports box, math, and logit-based evaluation.

proofagent

pytest for AI agents — test safety, accuracy, tool use, and cost. No YAML, no telemetry, just Python.

fieldtest

LLM evaluation framework — define what correct, well-formed, and safe means before you measure

coii-sdk

agents team

codesafe

An open-source Python library for code encryption, decryption, and safe evaluation using Python's built-in AST module, complete with allowed functions, variables, built-in imports, timeouts, and blocked access to attributes.

cval

A layer of protection for python's eval

sphinxcontrib-eval

Evaluate shell command or python code in sphinx and myst

agenttrace

AgentTrace is a lightweight observability library to trace and evaluate agentic systems.

rag-evaluator

A library for evaluating Retrieval-Augmented Generation (RAG) systems (The traditional ways).

promptmin

Prompt minimizer for LLM evals — shrink prompts to minimal failing inputs using delta debugging

aigc-evals

aigc_evals

safe-exec

Deobfuscate and inspect code passed into exec() and eval()

flashvm

Eval untrusted code in any language. No containers, no VMs, no setup. Just Linux.

no-subclasses

A library that removes the __subclasses__() list from all classes.一个清除所有类的__subclasses__()列表的库。