run-llama/llama_index
LlamaIndex is a leading data framework that enables building LLM-powered applications by providing tools for data ingestion, structuring, and advanced querying to augment large language models with private and external data.
Awesome AI Agents › Data Integration and Specialized Solutions
Scale3-Labs/langtrace
Langtrace is an open-source observability tool designed specifically for applications leveraging large language models (LLMs), vector databases, and LLM-based frameworks. It provides end-to-end tracing, real-time monitoring, debugging, and analytics capabilities to help developers capture, analyze, and optimize the performance of their LLM applications. Built on Open Telemetry (OTEL) standards, Langtrace ensures comprehensive and standardized tracing of LLM API calls, vector operations, and framework usage, enabling detailed insights into latency, costs, and usage patterns. The project supports integration with popular LLM providers such as OpenAI, Anthropic, Azure OpenAI, Cohere, and others, as well as LLM frameworks like Langchain, LlamaIndex, and more. It also supports vector databases including Pinecone, ChromaDB, QDrant, and Weaviate. Langtrace offers SDKs for both TypeScript/JavaScript and Python, making it accessible for a wide range of developers. The SDKs allow easy initialization and integration into applications, with options for both managed SaaS usage and self-hosting. Self-hosting Langtrace involves running a Next.js app along with Postgres and Clickhouse databases, with deployment facilitated through Docker and Docker Compose. The tool emphasizes privacy and security, as no telemetry data is collected when self-hosted, ensuring that all data remains on the user's infrastructure. Langtrace's architecture is designed to provide real-time observability and performance insights, helping developers debug workflows, monitor usage, and optimize costs effectively. The project is actively maintained and encourages community contributions, including feedback on developing semantic conventions for trace attributes. Overall, Langtrace is a powerful and flexible observability solution tailored for the growing ecosystem of LLM applications and related technologies.
https://github.com/Scale3-Labs/langtrace
Also in Data Integration and Specialized Solutions
pingcap/tidb
TiDB is an open-source, cloud-native, distributed SQL database offering ACID guarantees, horizontal scalability, high availability, HTAP capabilities, and MySQL compatibility.
getzep/graphiti
Graphiti is a framework for building and querying real-time, temporally-aware knowledge graphs designed to support AI agents in dynamic environments with efficient incremental updates and hybrid retrieval methods.
dolthub/dolt
Dolt is a SQL database with Git-like features, enabling full version control over data, including branching, merging, and diffing of data.
vectordotdev/vector
Vector is a high-performance, end-to-end observability data pipeline designed to collect, transform, and route logs, metrics, and traces.
cube-js/cube
Cube Core is an open-source semantic layer that enables AI, business intelligence, and embedded analytics by providing a flexible, API-driven platform supporting multiple SQL data sources and real-time analytics.
llmware-ai/llmware
llmware is a unified framework for building enterprise Retrieval-Augmented Generation (RAG) pipelines using small, specialized language models integrated with secure knowledge sources for efficient AI applications.
cocoindex-io/cocoindex
CoCoIndex is an ultra-performant data transformation framework for AI, specializing in incremental processing for data indexing and real-time semantic search with Python and Rust.