Data agents

Async multi-provider LLM client with typed tool calling, lazy output parsing, and Azure/Databricks/OpenRouter/LiteLLM/DeepSeek/local backends

A proxy server to intercept and store LLM API calls for fine-tuning dataset collection

Fuzzy join pandas DataFrames using LLM scoring and embedding retrieval — record linkage, entity resolution, approximate join

A minimal, notebook-first framework for running reproducible LLM experiments and comparing multiple models over JSONL/CSV datasets.

LLM Labeling UI is an open source project for large language model data labeling

Mask sensitive data in documents using a local OpenAI-compatible LLM

A tool for harvesting metadata from dataset landing pages using Large Language Models.

Generates LLM context by scraping and summarizing documentation for Python libraries listed in a requirements.txt file.

Access Nous Research models via API

Multi-agent debate for better AI decisions. Research-backed, local-first.

Parse data from documents optimised for downstream llm tasks.

LLM Patch Driver is a framework for patching data objects using LLMs. It can generate and apply a single patch, or start the patching loop to fix complex validation issues.

Pricing + release metadata and cost estimation for LLMs

A library for scraping and managing LLM pricing information

A comprehensive framework for systematic A/B testing, optimization, performance analytics, security, and monitoring of LLM prompts across multiple providers with enterprise-ready API

Pydantic data models and adapters for the LLM Protocol Suite.

Privacy-first text redaction using local LLM models with rule generation capabilities

A minimum Python package built on top of the LangChain framework to interact with LLM.

LLM plugin for comprehensive research using Jina AI's Search Foundation APIs

Salvage structured data from LLM responses that didn't follow instructions.

Turn any webpage into structured data using LLMs

Generate Data from LLM easily using LLMKit

This package would process text input, such as a research paper title or abstract snippet, and generate a structured summary of the core idea or problem addressed. It uses an LLM to interpret the inpu

A lightweight, rule-based text splitter for LLM context window management, handles multiple file formats and enriches chunks with metadata.

Expose Datasette instances to LLM as a tool

LLM data collection and synthetic fine-tuning dataset pipeline

A precision-focused LLM-powered web research tool that prioritizes accuracy over quantity

A comprehensive Python wrapper for Large Language Models with database integration and usage tracking

A comprehensive Python wrapper for Large Language Models with database integration and usage tracking

Plugin for LLM that adds support for fetching transcripts from YouTube videos using Supadata API

Enable large language models to output structured data.

LLM extraction from documents

Directly Connecting Python to LLMs - Dataclasses & Interfaces <-> LLMs

Talk to your CSV data with your huggingface llm models

🪄 Dataset augmentation using LLMs

A comprehensive toolkit for building, training, and deploying language models

Calculate LLM token costs from litellm pricing data

Research library for black-box experiments on language models.

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.

rubrics

llm dataset

Agent-first documentation platform (CLI and server)

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

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

A filesystem-metaphor memory layer for LLMs and AI agents

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

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

Embed signed semantic-metadata layers into images, PDFs, and audio files

Observability and monitoring for AI apps

LLM-powered chart generation Python SDK — create charts with natural language

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

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

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

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.

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

Shields your confidential data from third-party LLM providers.

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

CLI tool for preparing project data for LLM context

LLM-powered personal knowledge base — raw data goes in, an LLM compiles it into a structured, interlinked wiki

Knowledge + Chat + Research Assistant - LLM-maintained knowledge bases with chat & general research capabilities

Effortlessly harness the power of LLMs on Excel and DataFrames—seamless, smart, and efficient!

Interface between LLMs and your data.

fake_useragent use local data

A familiar API from the Web, adapted to storing data locally with Python.

A familiar API from the Web, adapted to storing data locally with Python.

Load test + test data distribution & launching tool for Locust

Log handler to store messages with a database record and optional file storage.

A modular text-based database manager for retrieval-augmented generation (RAG), seamlessly integrating with the LoLLMs ecosystem.

A research prototype of a human-centered interface powered by a multi-agent system

A lightweight framework for LLM-based agents with database persistency

Perform magnetoentropic mapping of magnetic materials based on DC magnetization data.

Privacy-safe LLM data cleaning for fine-tuning datasets

A powerful Python framework for building intelligent agents with structured outputs, document generation, database integration, and advanced hook-based customization.

Ferramenta de consulta de bases de dados usando linguagem natural com agente inteligente

AI Agent Python SDK - 让任何后台系统快速接入 AI Agent 能力

MCP server for Google Gemini AI - text, image, video, research, and more

Live data layer for agents. Expose canonical business objects as database-consistent, instantly-queryable SQL views via Model Context Protocol

Query webpages and extract structured data using natural language

Bridge legacy MySQL/MariaDB data into RAG pipelines without migration

Utilities for managing multi-shot conversations and structured data handling in LLM applications

Metadata Automation Edge Agent

Mnubo Data Science Library

Privacy-first, memory-enabled AI assistant with workflow engine, knowledge graph, multi-agent systems, multi-backend LLM support (Ollama, LM Studio), vector search, and analytics - 100% local and production-ready

Common Crawl import support for Meshagent datasets

Scrapy spider imports for Meshagent datasets

Agent-native database with causal memory, composite-scored recall, and a tamper-evident integrity chain

Meta Agents Research Environments is a research-driven environment designed to simulate complex, real-life tasks that span several minutes and require multiple steps to be solved. Unlike static simulation environments, this platform introduces a dynamic setting where the state of the environment evolves and new information is continuously integrated.

AI agent memory system powered by Modern Hopfield Networks — no LLM calls, no database, one matrix multiply

Utilities for managing multi-shot conversations and structured data handling in LLM applications

Utilities for managing multi-shot conversations and structured data handling in LLM applications

Meta-package that installs the core Mighty Data LLM utility packages

Python bindings for milvus-storage - a high-performance storage engine using Apache Arrow Parquet

Minimal AI agent with Python sandbox for data analysis

Fast, inexpensive document storage backed by a standard database connector.

A lightweight GPT-style transformer for research and inference.