Python agents

Implementation of LLMs in pytorch

Research library for black-box experiments on language models.

LLMCompiler

A library for compressing large language models utilizing the latest techniques and research in the field for both training aware and post training techniques. The library is designed to be flexible and easy to use on top of PyTorch and HuggingFace Transformers, allowing for quick experimentation.

A library for compressing large language models utilizing the latest techniques and research in the field for both training aware and post training techniques. The library is designed to be flexible and easy to use on top of PyTorch and HuggingFace Transformers, allowing for quick experimentation.

LLMConf unifies the loading and generation configurations of various LLM backends (e.g. `openai`, `transformers`, `vllm`), simplifying parameter control for experiments and testing.

Python SDK for the LLM Conveyors AI Agent Platform API

LLMCore: Essential tools for LLM development - models, prompts, embeddings, agents, chains, and more.

Active memory and executive control for AI coding agents. Classifies user prompts against a curated tripwire store, injects the matched lessons into the agent's working context via a Claude Code UserPromptSubmit hook, before the agent reasons about the task.

llmcost

A framework for selectively invoking LLMs and distilling repeated workloads into smaller models

A minimal CLI for interacting with LLMs via LiteLLM and MCP

Specwright - Python framework for LLM-assisted development with runtime spec validation

A professional CLI tool for interacting with OpenAI and Anthropic LLMs with cost tracking

A tool to manage and generate context for Large Language Models from project files

Cycle through multiple LLM providers with smart fallback, load balancing, and unified API with real-time FastAPI dashboard, resilient streaming failover, Pydantic structured output, prompt caching, token budgets, and local/cloud key rotation.

CLI tool for generating LLM context from GitHub repositories

LLMdantic is a Python package that provides structured interaction with LLMs.

rubrics

llm dataset

A simple interface to models.dev, the open database of AI model specs, pricing and capabilities

Structured debug snapshots for LLM-assisted debugging

Distributed LLM Evaluation Benchmark Server

triton inference service of llama

LLMDet: A Large Language Models Detection Tool

Tools for LLM applications development

git diff for LLM prompts

A simple directory tree generator for llm

LLM Development Kit for common APIs

Ask GPT to run a command

MCP server with RAG for llms.txt documentation

Automate documentation generation using the LLM of your choice!

Using LLM to parse PDF and get better chunk for retrieval

Agent-first documentation platform (CLI and server)

Find LLM cost leaks before your bill does. Static analysis for Anthropic and OpenAI client code.

轻量级 LLM 命令行工具与 Python 库，支持兼容 OpenAI Chat Completions 格式的任意 API 端点。

LLM Detection and Response — tamper-evident audit trails for LLM traffic

Cross-LLM memory portability tool — user-owned context vault across Claude, ChatGPT, Gemini, and Ollama

Security analysis framework for LLM-generated content in software development

A command-line interface for language models

Easy to use LLM interface

A Flexible Framework for Accelerating LLMs Benchmarking

Read through cache for OpenAI's API.

High-performance document memory system with vector search capabilities for Python applications

llments

llmer is a lightweight Python library designed to streamline the development of applications leveraging large language models (LLMs). It provides high-level APIs and utilities for parallel processing, runtime management, file handling, and prompt generation, reducing the overhead of repetitive tasks.

HPE LLM Agentic Tool Mesh Platform is an innovative platform designed to streamline and enhance the use of AI in various applications. It serves as a central hub to orchestrate 'Intelligent Plugins,' optimizing AI interactions and processes.

Reserved name — lldesign: UI/Web/diagram design tooling for the FullSense LLM family. Reference implementation in development.

Reserved name — lleval: LLM eval framework for the FullSense LLM family (on-prem + cloud unified A/B, progressive size matrix, honest disclosure). Reference implementation in development.

Self-evolving modular memory LLM framework — biological memory × formal verification × industrial IoT mesh × TUI HITL

llove — a cute, terminal-first Artifact for inspecting LLMesh data with llove

Reserved name — llrepr: typed Representation IR ("LLVM-for-expression") for the FullSense ecosystem. Reference implementation currently lives in llmesh as llmesh.llrepr.

Reserved name — lltrade: trading research for the FullSense LLM family (PAPER-TRADING ONLY, v0.x). Reference implementation in development.

Secure LLM Mesh over MCP — multi-LLM swarm + industrial IoT + privacy gateway

A less pager that uses LLMs to hallucinate infinite file continuations

A lightweight, cross-platform latency and throughput profiler for LLMs

A metrics and evaluation library for LLMs

Python SDK for the evaluate LLM evaluation framework

LLM evaluation, hallucination detection, AI content detection, compliance, document parsing, governance, security, observability, ground truth testing, conversation evaluation, red team testing, and anomaly detection. 78 metrics across 13 modules. Works with or without API.

Eval

Execute LLM-Generated Python Code Automatically

llmexport: A toolkit to export llm to onnx or mnn.

A library to extract structured information from unstructured text using LLMs, powered by LangChain.

Financial Data Assistant - A PocketFlow-based LLM library for financial data chat with tool calling

In-process LLM client faker that patches OpenAI, Anthropic, LiteLLM, and LangChain for fast, deterministic testing without network calls

It's a Python LLM package

A Python client for interacting with llamafile local LLM instances

Package to integrate feedback into LLMs

WIP

Hundreds of models & providers. One command to find what runs on your hardware.

Fleet-level batch dispatcher for LLM APIs. Pool requests across coroutines, route to provider Batch APIs, save 50% on cost without rewriting your agent loops.

A python package for developing AI applications with local LLMs.

Deploy /implement workflow templates for Claude and Gemini AI assistants

Deterministic LLM workflow engine

LLMFlows - Simple, Explicit and Transparent LLM Apps

CLI tool for running LLM batch processing jobs on HPC systems

Simple tool for formatting code for LLMs.

Automatically make the OpenAI tool JSON Schema, parsing call and constructing the result to the chat model.

Placeholder package to reserve the llmforge name

Format LLM language by using LALR(1) grammar. Supports JSON, XML, etc.

OpenAI-first hexagonal Python application scaffold for llmframe.

A filesystem-metaphor memory layer for LLMs and AI agents

llmfsd: LLM Fake Structured Data, faking Structured Data from any LLM

Dynamically generate JSON Schema from Python code.

Unified interface for multiple LLM providers

`LLMfy` is a framework for developing applications with large language models (LLMs).

Lightweight, provider-agnostic LLM calling library — OpenAI, Gemini, Anthropic, Groq, Mistral, Cohere, Azure, Bedrock, Ollama

Semantic caching library for LLM and RAG systems

LLMGateway Python SDK Client

Protect OpenAI and Anthropic API calls from prompt injection, jailbreaks, and data-extraction attacks.

Create Google Calendar event URLs interactively from a natural language description, leveraging LLMs with an OpenAI Chat Completions-compatible API and user edits.

Effortlessly generate LLM APIs by simply defining input and output schemas.

An application framework for building LLM-powered applications.

Sync LLM agent configuration files (AGENTS.md, skills/) across different coding assistants

LLMGovernor — anomaly engine for LLM apps (core SDK with optional LiteLLM bundle)