Language
Python agents
56,457 Python AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
56,457 agents · ranked by popularity · refine in the directory →
Python agents — page 443 of 565
A C++ AI engine with Python bindings
Open-source LLM evaluation framework — 50+ metrics for RAG, agents, safety, async eval, regression tracking, custom benchmarks, and exportable reports
Create knowledge graphs with LLMs
Plug-and-play LLM connector via YAML config
Open-source LLM prompt injection defense — protect any AI app in 2 lines of Python
大模型辅助函数库
Python library for interacting with Large Language Models.
Your Personal AI Cloud -- intelligent proxy, router, and cache for LLMs
Git blame for prompts: incident archaeology, git-native prompt versioning, and a no-SaaS production runtime for LLM workflows
Release engineering infrastructure for AI behavior - bundle, promote, evaluate, and replay agent behavior artifacts
LLMHub is a lightweight management platform designed to streamline working with LLMs.
LLMHub - Open-source multi-provider LLM gateway
A lightweight runtime for LLMHub that delegates to any-llm
LLMHub - Open-source multi-provider LLM gateway
light weight llm utilities for scalable AI apps
LLM-ify: create LLM-ready markdown and text from websites.
Library for replacing function calls with LLM inference.
Parse and match .llmignore files — the .gitignore for AI. Supports .cursorignore, .aiignore, .aiexclude, .claudeignore, .codeiumignore, .geminiignore, .aiderignore, .clineignore, .rooignore, .augmentignore, .copilotignore, .repomixignore.
Embed signed semantic-metadata layers into images, PDFs, and audio files
Where JavaScript, Python, and AI agents speak the same language
Document plugin system — charts, tables, presentations, export via MCP
Isolated Python code execution with resource limits
Document-knowledge MCP agents — full-text search, parsers, blob sync
Real-time pluggable dashboard with live widgets
Full-stack AI chat platform — multi-provider LLM, MCP tools, voice, budget
LLM execution engine — multi-provider streaming, MCP tools, and budget management
No-code pipeline automation — visual DAG builder with 112+ blocks
AI-native frontend development where AI builds, inspects, and operates real apps, dashboards, and tools
Llmint python library
Easily connect large language models into your application
MCP server for llmion — AI brand visibility monitoring & optimization
Core message and tool IR for LLM pipelines
A library to use Large Language Models (LLMs) as numerical optimizers
A code obfuscator to confuse LLMs
A package for evaluating language model outputs.
A library for evaluating Language Models using Knowledge Graphs
A library for evaluating Language Models using Knowledge Graphs
A knowledge graph generator using LLMs.
A chain message bot based on OpenAI
Unified LLM API client (placeholder)
Production-grade LLM client for Python - 100+ providers, 11,000+ models. Rust-powered.
Unified LLM API client (placeholder)
AI API gateway SDK with cost tracking, budget enforcement, and multi-provider routing for LLM applications
Unified LLM testing lab - test, compare, and interact with multiple AI providers through a single UI
Official Python SDK for the LLMLayer Search & Answer API
Security tool for detecting exposed LLM/AI API keys in public repositories
Portability lib for OpenAI, Hugging Face, and FastChat local model APIs
A simple library for making requests to LLMs
A Python library for interacting with Large Language Models (LLMs).
A backend for pydantic-AI agents and MCP servers.
Pydantic-AI based Multi-Agent Framework with YAML-based Agents, Teams, Workflows & Extended ACP / AGUI integration
Pydantic-AI models for AgentPool
LLMling provider based on the package 'llm'
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
LLMLink is a Python package that allows users to easily create LLM-powered Gradio applications
Add your description here
A library helps to chat with all kinds of LLMs consistently.
Loads a Langchain LLM by model name as a string.
High-performance columnar scan engine for LLM logs stored as JSONL
A Python package for manuscript management, designed to handle hierarchical structures of sections and subsections.
A unified interface for interacting with multiple LLMs and generative AIs.
A Shiny app to convert LLM Markdown exports to PDF with Quarto
A custom LLM-based git merge driver.
SDK for interfacing with core models hosted by LLM Solutions
A library designed to harness the diversity of thought by combining multiple LLMs.
AI pair programmer
Automatic cost tracking and observability for LLM applications
Automatic cost tracking and observability for LLM applications
Professional open source client for running large language models locally
Zero-cost local mock server for LLM API resilience testing
An LLM-powered mock API server that dynamically generates realistic API responses based on OpenAPI/Swagger specifications.
Making agents cuter
LLM-powered bioinformatics pipeline generation from natural language
Compositional framework for LLMs
Observability and monitoring for AI apps
A library to talk to different language models
AI pipeline framework for Python.
Create a Python package.
Reduce LLM costs by 90% - AI recommendations with NO API keys needed!
Predictive resource-pressure instrumentation and runtime guardrails for systems processing untrusted inputs
Llmovoice python library
A test package for llm
Extract structured, LLM-ready content from any website — adaptive engine, no LLMs required
LLM-powered FFmpeg command assistant
A CLI tool for LLM performance testing
LLM-powered chart generation Python SDK — create charts with natural language
LLMPipeline is a Python package designed to optimize the performance of tasks related to Large Language Models (LLMs)
Runtime prompt control, versioning, and user management for production apps
A package for using llm models with api
LLM Package Manager — download, run, and share AI models from the command line
Large Language Models' pool management library
The Python library that lets you spin up any LLM with a single function. Route between local and remote LLMs with a unified interface.
Node execution agent for llm-port cluster-managed runtimes.
CLI installer and management tool for the llm.port platform