Open-source context retrieval layer for AI agents

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Semantica 🧠 — A framework for building semantic layers, context graphs, and decision intelligence systems with explainability and provenance.

Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.

Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It auto injects relevant memories across developers and future sessions to save tokens and time spent on tasks.

Distributed data mesh for real-time access, migration, and replication across diverse databases — built for AI, security, and scale.

A Rust runtime that unifies relational tables, graph relationships, and vector embeddings in a single tensor-based storage layer with distributed consensus and semantic search

Stop paying for AI APIs during development. LocalCloud runs everything locally - GPT-level models, databases, all free.

NPU powered On-device AI Mobile applications using Melange

A curated list of awesome tools, frameworks, platforms, and resources for building scalable and efficient AI infrastructure, including distributed training, model serving, MLOps, and deployment.

Predictive memory layer for AI agents. MongoDB + Qdrant + Neo4j with multi-tier caching, custom schema support & GraphQL. 91% Stanford STARK accuracy, <100ms on-device retrieval

TME: Structured memory engine for LLM agents to plan, rollback, and reason across multi-step tasks.

GPU-aware inference mesh for large-scale AI serving

CX Linux — AI-powered Linux OS. Natural language system administration for Ubuntu & Debian. The AI layer for Linux infrastructure.

Production-ready AI infrastructure: RAG with smart reindexing, persistent memory, browser automation, and MCP integration. Stop rebuilding tools for every AI project.

UniRobot is an embodied intelligent software framework that integrates the robot brain (data, models, model training) with the robot body (perception, model inference, control).

ARF is an agentic reliability intelligence platform that separates decision intelligence (OSS) from governed execution (Enterprise), enabling autonomous operations with deterministic safety guarantees.

AI Infrastructure Engineer Learning Track - Production ML infrastructure curriculum (2-4 years experience)

A production-grade LLM gateway that abstracts multiple model providers, implements intelligent routing, caching, retries, and observability to deliver reliable, cost-aware LLM access.

The memory layer for software teams. Search everything your engineering org knows—code, PRs, docs, decisions—with answers that cite their sources.