pathwaycom/llm-app
Ready-to-run cloud templates for building real-time RAG, AI pipelines, and enterprise search applications that synchronize with various live data sources.
Awesome Infra for AI › Vector Databases & Retrieval Infrastructure
matrixarkai/TemporalStore
TemporalStore is open-source temporal infrastructure for LLM memory. It replaces the usual stack behind a grounded agent, where a vector database, a feature store, a Redis-style counter tier, a stream pipeline and a bespoke memory service are operated side by side, with a single time-aware engine. Applications bring their own data models and business logic; the engine handles real-time ingest, entity and summary extraction, retrieval, serving-time aggregates and control state from one temporal index. The central retrieval primitive is the ContextPack: a ranked, token-budgeted slice of memory assembled on demand and injected into the prompt, so a session does not replay its whole history each turn. The store deliberately uses no vector database. Alongside memory it serves exact count, sum, min, max and average aggregates over high-cardinality keys computed on read rather than pre-aggregated in a stream job, and O(1) atomic control state for frequency caps, quotas, pacing and suppression at serving time. The implementation is Rust with an append-structured page store, no garbage-collection pauses and crash-safe reload from its own persistence. It exposes a RESP surface, so existing Redis clients can talk to it, plus an HTTP execute endpoint. A single node runs from one docker compose file, and the same build scales out to a replicated shared-storage cluster with a metaserver and datanodes. For agent use it installs as a memory layer with automatic ingest and injection per turn plus recall and remember tools: a Claude Code marketplace plugin wires the lifecycle hooks, and Codex integrates over MCP with the same tool surface. The project publishes benchmark methodology and numbers on LoCoMo and LongMemEval, reporting large reductions in replayed prompt tokens at comparable answer quality. It is Apache-2.0 licensed and self-hostable.
https://github.com/matrixarkai/TemporalStore
Also in Vector Databases & Retrieval Infrastructure
run-llama/llama_index
LlamaIndex is an open-source data framework for building LLM applications by connecting custom data sources to large language models, focusing on data ingestion, indexing, and retrieval augmented g...
milvus-io/milvus
Milvus is a high-performance, cloud-native vector database designed for scalable vector Approximate Nearest Neighbor (ANN) search, efficiently organizing and searching vast amounts of unstructured ...
VectifyAI/PageIndex
PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes from documents and uses LLMs to reason over them for context-aware retrieval.
qdrant/qdrant
Qdrant is an open-source, high-performance vector similarity search engine and vector database designed specifically for AI applications, enabling fast storage, search, and management of vectors wi...
Tencent/WeKnora
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval, and autonomous reasoning, featuring RAG, ReAct agents, and an auto-maintaining ...
topoteretes/cognee
Cognee is an open-source AI memory platform that provides AI agents with persistent long-term memory through a self-hosted knowledge graph, combining vector embeddings and graph reasoning.
RyanCodrai/turbovec
TurboVec is a Rust-based approximate nearest neighbor (ANN) vector index with Python bindings, built on Google Research's TurboQuant algorithm for efficient, memory-optimized vector similarity search.