Python agents

llama-index vector_stores openGauss integration

llama-index vector_stores opensearch integration

llama-index vector_stores oracle database integration

llama-index vector_stores pgvecto rs integration

llama-index vector_stores pinecone integration

LlamaIndex VectorStore integration for Pixeltable multimodal data infrastructure.

llama-index vector_stores postgres integration

llama-index vector_stores qdrant integration

llama-index vector_stores redis integration

llama-index vector_stores relyt integration

llama-index vector_stores rocksetdb integration

llama-index vector_stores s3Vectors integration

llama-index vector_stores singlestoredb integration

llama-index vector_stores Apache Solr integration

llama-index vector_stores sqlalchemy integration

llama-index vector_stores supabase integration

llama-index vector_stores tablestore integration

llama-index vector_stores tair integration

llama-index vector_stores tencentvectordb integration

llama-index vector-stores tidbvector integration

llama-index vector_stores timescalevector integration

llama-index vector stores txtai integration

llama-index vector_stores typesense integration

llama-index vector stores upstash integration

llama-index vector_stores vearch integration

LlamaIndex VectorX vector store integration

LlamaIndex VectorStore for VelesDB: The Local AI Memory Database. Microsecond RAG retrieval.

llama-index vector_stores Vertex AI Vector Search integration

llama-index vector_stores vespa integration

llama-index vector_stores Volcengine MySQL integration

llama-index vector_stores weaviate integration

llama-index vector_stores wordlift integration

llama-index vector_stores yugabytedb integration

llama-index vector_stores zep integration

ZeroDB vector store for LlamaIndex - AI-native vector database with free embeddings, semantic search, and RAG support. Pinecone alternative.

LlamaIndex integration for ZeusDB vector database. Enterprise-grade RAG with high-performance vector search.

LlamaIndex x ElevenLabs integration

LlamaIndex x Gemini Live integration

LlamaIndex x OpenAI Realtime integration

Lightweight fork of LlamaIndex's workflow module, offering powerful event-driven orchestration without the full llama-index-core dependencies.

An event-driven, async-first, step-based way to control the execution flow of AI applications like Agents.

LlamaIndex tool for x402 service discovery — find any x402-payable API endpoint at runtime

Unified interface for multiple LLM providers with advanced features (routing, privacy, logging).

Enable IPFS model loading for llama-cpp-python

Interface between LLMs and your data

Train a speech-to-speech model using your own language model

Utilities for indexing a corpus with llama-index

Explainable AI with Large Language Models

Build on large language models faster

MCP server for document parsing with LlamaCloud multimodal understanding

Easy deployment of quantized llama models on cpu

Metasearch engine aggregating and ranking results from multiple LlamaAI sources.

Data processing pipeline using MLX (scraper, chunker, extractor).

Data processing pipeline using MLX (scraper, chunker, extractor).

Llama models

An opinionated library for writing MQTT services

Notification system for the LlamaAI Ecosystem (push, email, SMS).

OCR using LLAMA vision model, allowing configuring any OpenAI compliant endpoints and model names.

A package for document extraction using Ollama Vision model

llama-optimus is a lightweight Python tool to automatically optimize llama.cpp performance flags for maximum tg & pp token/s throughput. Powered by Bayesian optimization with Optuna

Parse files into RAG-Optimized formats.

Parse files into RAG-Optimized formats.

A tool for migrating and optimizing prompts

Prompt templating and structured LLM output for llama_cpp.

Proxy service for the LlamaAI ecosystem.

This is a compatibility package to keep projects build on llama-recipes compatible with the new name llama-cookbook. If you're updating your project or starting a new one please use llama-cookbook package

Privacy-preserving multi-modal recommendation system

LlamaIndex tools for RecourseOS - evaluate consequences before destructive actions

Unofficial python bindings for llama-rs. 🐍❤️🦀

A tool for converting PDFs to text files using Ollama.

General-purpose job scheduling service for the LlamaAI Ecosystem.

Official Python SDK for Llama Search AI Platform

A powerful, modular RAG-orchestrator that aggregates 10+ search engines (Google, Bing, Firecrawl, Exa, Tavily) into LLM-ready markdown.

LLaMA Server combines the power of LLaMA C++ with the beauty of Chatbot UI.

A ZMQ client interface for llama server

A comprehensive simulation framework for AI research and testing scenarios

Slobr utilities

Open-source, OpenAI-compatible API server with pluggable providers for any model and any infrastructure

API and Provider specifications for Llama Stack - lightweight package with protocol definitions and provider specs

The official Python library for the llama-stack-client API

Llama Stack Evals

Use Llama Stack framework for text generation

Llama Stack Provider for Distributed InstructLab Training using KFT

Add your description here

Ragas evaluation as an out-of-tree Llama Stack provider

Remote safety provider for Llama Stack integrating FMS Guardrails Orchestrator and community detectors

Garak red-teaming evaluation adapter for eval-hub

A Quick Llama Text2SQL Evaluation Library

A Quick Library with Llama 3.1/3.2 Tokenization - source https://github.com/jeffxtang/llama-tokens

Native tool parser for llamas pythonic format

Llama Stack

Utility for building and running llama.cpp

Utility for building and running llama.cpp

Llama trainer utility

LLM utilities for the Llama project

Llama Verifications

Temporal video support for llama.cpp — frame extraction, preprocessing, and captioning service for Qwen3.5 GGUF models

On-device voice processing pipeline for fast, private voice interaction

On-device voice processing pipeline for fast, private voice interaction

Web scraping tool potentially using Llama models.