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
caura-ai/caura
Caura, formerly released as MemClaw, is an open-source memory layer for multi-tenant, multi-agent AI deployments. Agents write what they learn as plain text; Caura converts it into searchable, governed memory that other agents in the same fleet can recall, so knowledge compounds instead of each agent rediscovering the same facts. The design premise is that the common agent-memory benchmarks — LoCoMo, LongMemEval — measure a single agent holding one long conversation with one user, whereas production deployments look the opposite: dozens or thousands of agents acting for one organization, sharing what they learn under governance. Caura is built for that shape from the start, with memory scoped per agent, per tenant and per fleet, cross-agent propagation of outcomes so a failed approach discourages repetition elsewhere, and fleet-wide trust tiers that decide whose memories carry weight. The axes it competes on are the ones that scale with agent count: search latency, token efficiency of the recalled context, and the governance controls that make shared memory safe in a multi-tenant setting. The loop is described as three pillars — write, recall, compound — with every interaction improving the next. Integration is through an HTTP API and an MCP server exposing caura_ tools, with the older memclaw_ tool names, packages, environment variables and URLs kept working for compatibility. A standalone local mode runs with no API key or signup for evaluation. The project is written in Python, licensed Apache 2.0, and reports a production deployment at eToro running several hundred agents against one governed memory store with tens of thousands of memories and low double-digit millisecond median search.
https://github.com/caura-ai/caura
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.