Llama Index Python Packages

opik

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

gptcache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

judgeval

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

pygpt-net

Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - chat, agents, tools, MCP, plugins, RAG, vision, voice, image and video generation, speech synthesis and speech recognition, web search, memory, presets, canvas, assistants, themes, computer use. Windows, Linux, and Mac.

opik-optimizer

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

helicone-helpers

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

axon-rag

Local-first RAG engine with cited answers from your own docs. GraphRAG, sealed sharing, MCP-native, VS Code Copilot integration. Nothing leaves your machine.

llama-index-tools-insumer

LlamaIndex tool spec for InsumerAPI: wallet auth and condition-based access across 37 blockchains. Booleans signed twice (ES256 and a post-quantum ML-DSA-65 signature), JWKS-verifiable offline. Boolean, not balance.

leann

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

coordinode-embedded

Python SDK + LangChain GraphStore & LlamaIndex PropertyGraphStore for CoordiNode — AI-native graph + vector + full-text database

helicone

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

mlcagent

Machine Learning Copilot Agent

comet-llm

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

ontorag

ontorag cli and core library

langchain-coordinode

Python SDK + LangChain GraphStore & LlamaIndex PropertyGraphStore for CoordiNode — AI-native graph + vector + full-text database

coordinode

Python SDK + LangChain GraphStore & LlamaIndex PropertyGraphStore for CoordiNode — AI-native graph + vector + full-text database

llama-index-memory-geniffy

Geniffy for LlamaIndex: a memory block that remembers each of your users, with where every fact came from.

autollm

Ship RAG based LLM web apps in seconds.

llama-index-graph-stores-coordinode

Python SDK + LangChain GraphStore & LlamaIndex PropertyGraphStore for CoordiNode — AI-native graph + vector + full-text database

llama-index-readers-urlpipe

LlamaIndex reader for URLpipe: load any web page as clean Markdown, rendered in real Chrome, ready to index.

fastapi-agents

A FastAPI extension for integrating common AI agent frameworks.

llama-index-vector-stores-infino

LlamaIndex integration for Infino — vector, BM25, hybrid (RRF), and SQL retrieval over one engine on object storage.

helicone-async

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

rag-colls

Collection of recent advanced RAG techniques.