Python agents

A package for calculating perplexity using various language models

Fast, offline-first LLM pricing lookup with auto-sync from LiteLLM data. Get token costs, context windows, and capabilities for 2500+ models.

Compare LLM API costs across providers from the command line

CLI tool to print directory structure and file contents for LLM context generation

A simple framework for LLM-powered applications

A Python package for creating and running LLM programs.

A unified framework for interacting with various LLM providers through a consistent interface with batch processing, templating, and rate limiting.

Static security scanner for LLM and agentic source code — finds prompt-injection, context-leak, PII, RAG, and agent-tool vulnerabilities before deployment.

A comprehensive LLM Prompt Management System

Version, compare, and manage your LLM prompts. No API keys required. Bring your own model.

A lightweight set of tools to use several llm and embeddings apis

OpenAI-compatible LLM reverse proxy with real-time conversation analytics

Easily interact with all main LLMs

Automatically generated LLM models for llmpy-lib

todo

LLM Quality Gate - A provider-agnostic evaluation framework for LLM applications

A package for querying various LLM providers

LLMRails SDK

Intercept OpenAI inputs

A CLI tool to check if your local hardware can run a Hugging Face LLM.

Recommendation systems with LLMs from Shaped.ai

Prompt regression testing for RAG pipelines. Like git diff, but for AI.

A lightweight Python library providing easy access to popular LLM model names, metadata (context windows, capabilities, pricing tiers), and support definitions. Born from a failed experiment on context data compression for LLMs with finite context windows, this library helps developers manage model names, validate support, search by capabilities, and find models by requirements without hardcoding strings or maintaining spreadsheets.

Deterministic replay debugger for LLM agents

A package for building and managing tools for Large Language Models

轻量级的 LLM 响应格式化工具，支持标准响应和流式响应

Unified Python interface for OpenAI, Anthropic, Google, and Ollama LLMs

LLMRing public model registry CLI and tools (manual curation workflow)

LLMRing core server: alias sync, receipts, and usage logging (key-scoped, no users)

A professional Git-based Skill management library for LLM agents.

A unified framework for LLM routing and evaluation.

LLM Stack Python SDK

LlmRush: A Python package for training and Inference language models

A unified interface for multiple LLM providers

MCP server to bridge LLM calls via Model Context Protocol

A simple example package

Fuzzy search LLM models from models.dev

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A lightweight CLI tool and OpenAI-compatible server for querying multiple Large Language Model (LLM) providers

AI-friendly llms.txt & sitemap generator for websites. Crawl or import sitemaps, filter pages, and generate curated indexes for LLMs.

The /llms.txt file, helping language models use your website

GitHub Action to make documentation more accessible to LLMs.

Lean MCP server for minimal-context docs via llms.txt

Module for parsing llms.txt files

Package for simple usage of diverse LLMs and configuring them using human readable config files

LLMs4PCG is a python package containing required and utility functions as a part of LLMs4PCG competition.

LLMSanitize: a package to detect contamination in LLMs

One-line LLM queries with smart routing and provider failover

Generate llms-brief.txt files from documentation websites using AI

A fast, modern CLI that shows which local LLMs fit on your machine

A structured response wrapper for LLMs using Pydantic.

a Python library designed to simplify interactions with Large Language Models (LLMs) by providing a stateful, fluent interface for managing conversation history, tool usage, and response parsing. It leverages libraries like `mirascope` for LLM calls and `pydantic` for data validation and parsing.

Regression-based LLM benchmark ratings + publication-ready scorecards.

An LLM-powered tool for discovering and analyzing research papers

LLM-powered web scraping in Python

Find the Best Generation Parameters for your LLM & Dataset

A high-performance static internet index for LLM RAG applications

A Python library for LLM security

A lightweight, production-ready service layer for modular, rate-aware LLM integrations

Runtime monitor for LLM agent interaction protocols based on session type theory

Command-line tool to use Large Language Models in your shell,including OpenAI, Anthropic, PalM, Mistral, Cohere, and more.

Comprehensive analysis tool for LLM streaming traffic from PCAP files

Convert natural language to shell commands using LLMs (GPT4All, OpenAI, Ollama)

Strategic APIs to Accelerate LLM Use Cases

Shields your confidential data from third-party LLM providers.

Lightweight validation, repair, and retry helpers for LLM outputs.

Spanish language corpus for LLMShield entity detection.

Multi-provider LLM gateway — one interface, every provider

Client and Tools for LLMs

LLM unified interface

Know where your AI money goes. Track LLM API costs per feature, per model, per user.

A Text2SQL benchmark for evaluation of Large Language Models

Low-code platform to build generative AI apps, chatbots and agents with your data

One command. Full LLM stack. Zero config.

A Python library for building GPT-powered agents with state machine logic and chat history memory.

llmster

A provider-agnostic LLM toolkit with tool calling, skills, and parallel execution.

Adversarial security testing framework for LLM-powered applications

A Python library for reliably extracting structured JSON from text and validating it with Pydantic models.

Prompt Perfection at Your Fingertips

LLMStudio core capabilities for routing llm calls for any vendor. No proxy server required. For that use llmstudio[proxy]

LLMstudio Proxy is the module of LLMstudio that allows calling any LLM as a Service Provider in proxy server. By leveraging LLMstudio Proxy, you can have a centralized point for connecting to any provider running independently from your application.

LLMstudio Tracker is the module of LLMstudio that allows monitoring and logging your LLM calls. By leveraging LLMstudio Tracker, users can gain insights on model performance and streamline development workflows with actionable analytics.

Design and build LLMs.txt knowledge structures by extracting and summarizing web content

AST-aware llms.txt generator for Python and JavaScript/TypeScript codebases

Generate llms.txt from built HTML documentation

Convert llms.txt to Claude Code Skill format

Python SDK, CLI, and Arena for 10 LLM providers. Compare models, synthesize a privacy-aware Best Answer, use MCP tools, fallback, caching, and direct BYOK access.

LLMT aims to make it easy to programatically connect OpenAI and HuggingFace models to your data pipelines, CI/CD, or personal workspaces.

Use LLMs to label any textual dataset

LLM Downstream Task Evaluation Tool.

LLM任务难度评分工具，支持百炼、OpenRouter和Gemini等大模型

A Python bookstore to simplify the definition, execution and chaining of tasks using LLMS.

Enterprise AI Workflow Runtime - Multi-agent LLM pipelines with security, orchestration, and workflow capabilities

A CLI tool that sends prompts to an LLM and outputs responses

Intentionally Simple. Generic LLM interface

Gemini provider for LLMterface