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
Arvo-AI/aurora
Aurora automates the investigation phase of on-call incident response. Alerts arrive from PagerDuty, Datadog, Grafana, New Relic, OpsGenie, incident.io or AWS CloudWatch webhooks, and each one triggers a background investigation instead of an immediate page. LangGraph-based agents choose dynamically from more than thirty tools, running kubectl, aws, az and gcloud inside sandboxed Kubernetes pods, querying logs, checking recent deployments and correlating signals in parallel until they can state a root cause. The output is a structured analysis rather than raw command transcripts: postmortems are generated with a timeline, impact assessment and remediation steps and can be exported to Confluence, Notion or SharePoint, and the agent can go further and open a pull request containing a suggested code fix. Artifacts are documents the agent maintains and keeps updating as an investigation progresses, while Actions run automated workflows once an analysis completes, such as writing the postmortem, opening the fix pull request or posting to Slack. Connectors cover the major clouds, Kubernetes clusters connected by uploading a kubeconfig for on-premise setups, Fly.io and CloudBees, and models can be served through AWS Bedrock as well as direct providers. Extensibility hooks let an operator gate LLM calls, enforce seat limits or otherwise alter behaviour at defined lifecycle points, and an incident dashboard shows the queue and each investigation''s reasoning, so knowledge that used to live with individual engineers is captured. Aurora is written in Python with a Next.js interface, released under Apache 2.0, and can be self-hosted or tried on the vendor''s hosted instance. It targets SRE, platform and DevOps teams that repeat the same manual triage on every alert.
https://github.com/Arvo-AI/aurora
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.