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
CodeAbra/iai-personal-memory-engine
iai-pme is a personal memory engine that gives AI coding assistants persistent recall across sessions, running entirely on the user's machine. It connects to anything that speaks MCP over stdio — Claude Code, Claude Desktop, Cursor, Codex CLI, Gemini CLI, Cline, Continue.dev, Zed, Goose, Aider, Hermes, OpenClaw and others — so the same memory follows a developer between tools instead of being locked into one assistant. The retrieval philosophy is stated as verbatim over paraphrase: it stores what was actually said, favours precise cues over summarization, and keeps rare events rare so an unusual instruction is not smoothed away by frequency. Rather than having the agent search a project repeatedly, iai-pme injects a compact memory pack into context; the project reports that this costs roughly an order of magnitude fewer tokens than the agent-driven search it replaces, and it ships the benchmark harness behind each claim so results can be reproduced. Reported figures include high recall on LongMemEval and a rescue metric for surfacing memories that a first pass missed. The engine core is written in Rust with a Python package on PyPI, targets Python 3.11 and 3.12, runs on macOS and Linux with Windows in beta, and stores data locally encrypted with AES-256-GCM and no telemetry. A dashboard visualizes the memory as it is used, showing search, pinning, fading of stale entries, rescue of forgotten ones, and teaching the engine a specific file. It is MIT licensed and aimed at developers who want their assistant to remember decisions and context without sending any of it to a service.
https://github.com/CodeAbra/iai-personal-memory-engine
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.