claude-mem is a persistent memory system for AI coding assistants, primarily targeting Claude Code but also supporting Codex, Cursor, Windsurf, OpenClaw, and other platforms. It captures observations, summaries, and user prompts from coding sessions via lifecycle hooks (SessionStart, PostToolUse, etc.), stores them in SQLite (local) or Postgres (server), and injects relevant context into future sessions to maintain continuity across agent interactions. The system operates as a background worker daemon (Bun) or a multi-user server (Express + BullMQ + Valkey) with API key authentication, team/project scoping, and rate limiting. Architecturally, claude-mem is a hybrid of a CLI plugin and a standalone server. The CLI component integrates into IDEs via hook scripts and MCP servers, while the server component provides REST APIs for memory management, search, and cloud sync. It features a dual-storage backend (SQLite for local, Postgres for server) with vector search via ChromaDB and full-text search via SQLite FTS5. The system includes a React-based viewer for browsing memory feeds, telemetry (opt-out PostHog), and a Cloudflare Workers-based sync hub for cross-device synchronization. The codebase demonstrates strong engineering practices with well-abstracted components (search strategies, provider abstraction, atomic file operations, telemetry scrubbing) but carries some technical debt from its dual-runtime evolution (legacy worker vs. server-beta) and extensive Windows-specific workarounds. It is actively maintained with frequent releases and comprehensive test coverage.
Milvus Java SDK is a comprehensive client library for the Milvus vector database, supporting both legacy (v1) and modern (v2) APIs. It covers all core operations: collection/index/partition management, vector insert/upsert/delete/search/query, RBAC, resource groups, CDC, snapshots, and bulk import via Parquet/CSV/JSON files. The SDK uses gRPC for communication, includes connection pooling, schema caching, and iterator support for large result sets. A separate bulk writer module handles cloud storage uploads (S3, Azure, GCP) and import job orchestration. The codebase is professionally structured with a builder pattern for all request/response objects, extensive unit and integration tests, and examples demonstrating real-world usage. While dual API versions increase maintenance, the SDK is actively developed with a rapid release cadence aligned to Milvus server versions.
Onyx is a full-stack AI enterprise search and chat platform. The backend is a Python/FastAPI service with Celery workers, PostgreSQL, Redis, and a vector search engine (Vespa/OpenSearch). It ingests documents from 50+ external connectors (Google Drive, Slack, Confluence, Jira, SharePoint, etc.), runs a chunking/embedding/indexing pipeline, and serves RAG chat and search to multiple frontends: Next.js web app, React Native/Expo mobile app, Tauri desktop wrapper, Go CLI, an embeddable web widget, and a Terraform provider. It also includes an MCP server, deep research flows, sandboxed code-execution sessions (Craft), prompt caching, SSO/OAuth/SCIM multi-tenancy, rate limiting, and an admin analytics console. The repository has a hybrid character because it contains substantial data-engineering machinery (indexing pipelines, chunkers, embedding providers, evals) but the dominant identity is a production application rather than a research project.
Kronotop is a distributed database system built on FoundationDB that provides Redis-compatible (RESP2/RESP3) interfaces for multiple data models including key-value (stash), document (bucket with BSON storage and querying), and sorted sets (zmap). It features ACID transactions, secondary indexing (including vector search via HNSW), clustering, sharding, replication, and namespace isolation for multi-tenancy. The architecture is modular with clear separation between network handling (Netty), protocol processing, service layers (transaction, session, data services), and storage (volume-based segment store). Key entry points include the server entry point (KronotopInstanceStarter), CLI (kronotop-cli), and control tool (kronotop-ctl). The system relies on external dependencies such as FoundationDB, Netty, Jackson, Lettuce, Guava, JVector, and Typesafe Config. The codebase demonstrates strong engineering practices with reusable components like versionstamp utilities, retry mechanisms, and protocol handling.
Onyx is a comprehensive enterprise AI platform that provides knowledge retrieval, chat, and document indexing across 50+ third-party sources. The codebase reveals a FastAPI backend with Celery workers, PostgreSQL with Alembic migrations, OpenSearch vector search, Redis caching, and a separate model server. The frontend is a Next.js application with a custom design system (opal), alongside React Native mobile app, Go CLI, Chrome extension, and an embeddable widget. The platform supports deep research, custom agents, MCP servers, sandboxed code execution (Craft), and enterprise features like SSO, SCIM, billing, and multi-tenancy. Architecture is well-structured with clean separation of concerns, but the large codebase shows some drift: platform duplication across web/mobile/CLI, extensive Alembic migration history, and lint debt. The connector framework and design system are high-quality reusable components.
Databend is an open-source, cloud-native distributed SQL query engine and data warehouse, built in Rust. It provides a full SQL interface for analytical workloads, supporting operations such as SELECT, INSERT, COPY INTO/OUT, MERGE INTO, and complex aggregations with window functions, subqueries, and joins. The architecture follows a storage-compute separation model: a metadata service (Meta) manages schemas, users, and catalogs via a Raft-based consensus layer, while query nodes handle SQL parsing, planning, optimization (Cascades optimizer with rule-based and cost-based passes), and distributed execution over a pipelined framework. Multiple storage engines are supported, including a native columnar Fuse engine optimized for cloud object stores (S3, MinIO, Azure Blob), as well as external formats like Iceberg, Delta Lake, Hive, Paimon, Parquet, and ORC. The system exposes access via MySQL wire protocol, HTTP API, Flight SQL, and gRPC, and includes enterprise features such as data masking, row access policies, materialized views, streams, network policies, and role-based access control.
VexDB-Lite is a vector similarity search library providing Approximate Nearest Neighbor (ANN) capabilities as extensions for PostgreSQL, DuckDB, and SQLite databases. The system implements Hierarchical Navigable Small World (HNSW) graphs for efficient similarity search, with optional Product Quantization and RaBitQ compression for memory efficiency. It features hardware-accelerated distance computation using SIMD instructions (SSE, AVX, AVX512, NEON) and provides multiple distance metrics (L2, inner product, cosine). The architecture separates core algorithms from database-specific adapters, enabling consistent functionality across different storage engines. The codebase demonstrates strong engineering practices with reusable components like the SIMD dispatch system, vector buffer manager, and product quantization implementation.
OpenCode-Mem is a plugin for OpenCode, an AI coding assistant, that provides persistent memory using vector embeddings and Turso/libSQL. It stores project-level technical memories (decisions, code facts, patterns) and learns user preferences/configs across sessions. The system uses local ONNX embeddings (or remote API) and supports multiple LLM providers (Anthropic, OpenAI, Google Gemini, MiniMax). It features auto-capture of session content, user profile learning with confidence decay, deduplication, and migration services. A full React web UI allows browsing, editing, and managing memories and user profiles. The architecture is modular: plugin entry, AI provider abstraction, Turso shard management, embedding service, web server, and shared API schemas. While primarily an application, it includes robust data pipeline patterns for vector search, ETL (migration), and user modeling.
ArcadeDB is a high-performance, multi-model database system supporting graph, document, key-value, time-series, vector, and full-text data models. It exposes multiple query languages (SQL, Cypher, Gremlin, GraphQL) and wire protocols (HTTP, Bolt, PostgreSQL, MongoDB, gRPC). The architecture is modular: a core engine (storage, indexing, query execution) with pluggable server plugins for protocols, replication (Raft-based HA), and observability. It features advanced indexing (LSM-tree, hash, vector quantization, sparse vectors, full-text BM25), time-series with PromQL and downsampling, and graph analytical views with CSR compression. Python bindings allow embedded use. The codebase demonstrates strong engineering with extensive use of interfaces, design patterns, comprehensive test coverage (including issue-specific regression tests), and automated CI/CD with performance benchmarks. It is actively maintained with low technical debt and a clean architecture.
Infinity is a high-performance AI-native vector database designed for LLM applications, offering hybrid search over dense embeddings, sparse embeddings, tensors, and full-text. Its architecture is a distributed C++ core with a modular planner/executor, multiple index types (HNSW, IVF, BMP, DiskANN, EMVB, PLAID, full-text), and a transaction system with WAL and checkpointing. The database exposes a SQL interface, a Thrift RPC API, an HTTP API, and native SDKs for Python, Go, and C++. It also includes a web GUI (Next.js) for administration. The codebase is heavily optimized with SIMD instructions, custom analyzers for multiple languages, and advanced query optimization (fast rough filters, result caching). While the repository is actively maintained with a comprehensive test suite and CI/CD pipeline, there is some technical drift from deprecated KNN implementations and disabled unit tests, and the reliance on C++20 modules may introduce compiler compatibility risks.
This is a production-grade long-term memory plugin for the OpenClaw AI agent platform, built as a TypeScript/ESM module. It provides a complete memory lifecycle: LLM-powered extraction from conversation transcripts (6-category classification with L0/L1/L2 layering), hybrid vector+BM25 retrieval with cross-encoder reranking, Weibull decay-based importance scoring, tier management (core/working/peripheral), and multi-scope isolation (global, agent, user, project). The plugin integrates deeply into OpenClaw via lifecycle hooks, agent tools, CLI commands, and a dreaming engine for periodic consolidation. It stores all data in LanceDB and supports multiple embedding providers, LLM backends, and OAuth flows. The codebase is large and complex, with extensive test coverage (100+ tests) and many edge-case handlers, but exhibits significant technical debt in a single massive index.ts file and multiple fallback/legacy migration paths. It is not a research project; it is a highly functional, actively maintained plugin with a clear engineering focus on correctness, resilience, and performance.
This repository is a collection of deployable templates and educational cookbooks for building real-time LLM applications using the Pathway framework. It provides ready-to-deploy RAG (Retrieval-Augmented Generation) solutions with live data synchronization from various sources (files, Google Drive, SharePoint, etc.), built-in vector and hybrid search, and integration with LangGraph for agentic workflows. The templates are production-oriented with Docker support, while the cookbooks demonstrate advanced patterns like Self-RAG with self-reflection and query rewriting. The codebase is well-structured but exhibits some duplication across templates, and the core logic relies heavily on the external Pathway library.
GraphRAG is a Microsoft Research project that implements a graph-based retrieval-augmented generation (RAG) system. It extracts structured knowledge (entities, relationships, claims) from unstructured text using LLMs, builds a hierarchical knowledge graph via Leiden community detection, generates community summaries, and supports multiple query strategies: local search (entity-centric), global search (map-reduce over community reports), DRIFT search (iterative multi-hop), and basic vector search. The system is designed as a Python library with a CLI (Typer) and a public API, plus a Streamlit demo app for comparing search modes. It provides extensive configuration via YAML/JSON with environment variable substitution, and supports multiple backends for storage (file, Azure Blob, CosmosDB), caching (SQLite, JSON, memory), vector stores (LanceDB, Azure AI Search, CosmosDB), and LLM providers (OpenAI, Azure OpenAI, LiteLLM). The codebase is organized as a monorepo with eight sub-packages (graphrag, graphrag-llm, graphrag-storage, graphrag-vectors, graphrag-cache, graphrag-input, graphrag-chunking, graphrag-common), each with its own pyproject.toml and versioning. The project is explicitly in maintenance mode, accepting only bug fixes and dependency updates, with no new features planned. Despite this, the architecture is well-structured with clean abstractions, factory patterns, middleware pipelines, and a composable design that makes many components reusable in other projects.
OS1 (nokodo) is a full-stack AI-powered collaborative platform combining autonomous agents, deep research, real-time collaboration, and extensible tooling in a self-hostable workspace. The system features a modular architecture with FastAPI/Python backend, Svelte 5 frontend, and separate admin console, communicating via REST API, WebSocket, and Redis pub/sub. Core capabilities include AI agent construction with tool integration (web search, code execution, file operations), persistent memory system with vector search, real-time document editing, and comprehensive resource management (threads, notes, files, projects, calendars, reminders). The platform emphasizes extensibility through plugin systems for tools, filters, and hooks, with production-ready deployment via Docker Compose.
ReadAny is a full-featured, cross-platform e-book reader application with deep AI integration. It supports reading EPUB, PDF, MOBI, FB2, and other formats via the modified foliate-js engine, and provides text-to-speech, annotations, reading statistics, and cross-device sync (WebDAV, S3, LAN). The AI subsystem offers chat with RAG (semantic search over book content), context-aware tools, and execution of user-defined skills. The application follows a local-first architecture with robust offline capabilities and optional cloud sync. The codebase is structured as a pnpm monorepo with four main packages: 'core' (shared business logic, types, stores, AI, RAG, sync, stats, TTS), 'app' (Tauri desktop client with React+shadcn UI), 'app-expo' (Expo/React Native mobile client), and 'cli' (agent integration via MCP and managed shims). The application exhibits high craftsmanship in its platform abstraction layer, persistent store pattern, and hybrid search engine. However, there is significant platform-driven code duplication (desktop vs. mobile UI components) and a complex dependency graph with multiple patched packages, indicating some architectural debt.
BookWith is a next-generation e-reader application that enhances traditional book reading with AI capabilities. The system allows users to upload and read EPUB books, annotate text, interact with an AI chatbot for contextual questions about the content, and generate AI-powered podcasts from book material. The architecture follows a client-server model with a Next.js/React frontend and a FastAPI/Python backend, employing domain-driven design principles. Key features include a multi-layer memory system for maintaining conversation context, semantic search via Weaviate vector database, and integration with external AI services like Gemini and Google Cloud Text-to-Speech. The frontend uses modern React patterns with Zustand/Jotai for state management, Tailwind CSS for styling, and shadcn/ui-inspired components. The backend utilizes PostgreSQL for relational data, implements clean architecture with separate domain/application/infrastructure layers, and provides a well-structured API with automatic OpenAPI schema generation.
ObjectBox Java is an open-source, embedded NoSQL database library for Java and Kotlin, targeting Android, JVM, and desktop platforms. It provides a high-performance, native-backed object persistence engine with type-safe querying, reactive data observation, object relations (ToMany/ToOne), vector search via HNSW indexes, and optional client-server or mesh peer-to-peer synchronization. The code is organized into multiple Gradle modules including a core `objectbox-java` module with JNI bindings, an annotation API (`objectbox-java-api`), Kotlin extensions, RxJava 2/3 adapters, Android-specific integrations (LiveData, Admin web UI, Paging DataSource), and a mesh sync module using Google Nearby Connections. The architecture is library-centric with a clear separation between Java-facing API, internal serialization (vendored FlatBuffers), and native runtime. Extensive unit and integration tests cover core CRUD, transactions, queries, relations, sync, and error handling. The repository is actively maintained with a version 6.0.0-beta, publishes to Maven Central, and uses multi-platform CI (GitLab, Jenkins). While the codebase includes some legacy APIs and generated FlatBuffers code, the core abstractions exhibit solid software engineering practices with reusable patterns for reactive subscriptions, property converters, and cross-platform native library loading.
This repository provides a server application for interacting with COMSOL Multiphysics models via a programmable interface. It features a modular architecture separating concerns into COMSOL model manipulation tools (geometry, mesh, physics, etc.), a knowledge base built from COMSOL documentation PDFs for retrieval-augmented generation, and utility functions for versioning and async handling. The system enables users to load, modify, and simulate COMSOL models through a server interface (likely MCP - Model Context Protocol), while leveraging a vector database of processed PDF documentation to provide contextual assistance. Key entry points include src/server.py and various domain-specific scripts in comsol_models/ directories for building and simulating specific models (e.g., solenoids, micromixers).
SuperCoder is a local-first, open-source AI coding agent with a desktop application (Tauri + Rust + React) and a suite of backend services. The core agent (Rust crate) provides an LLM-driven loop with tool execution (file editing, bash, git, code search), subagent spawning, and an 'Auto' mode where an orchestrator LLM generates plans executed by worker agents. The desktop app offers a rich UI for agent interaction, diff review, file exploration, and permission management. A separate Go-based 'Context Engine' service indexes codebases into vector (Qdrant), graph (FalkorDB), and text stores, enabling semantic code search, dependency analysis, and automated PR review with risk scoring. The repository also includes a legacy v1 backend (Go) with workflow executors for Django/Flask/Next.js code generation and a workspace service for managing isolated development environments. While primarily an application, the context engine introduces data/research elements through its indexing pipelines, retrieval strategies, and code review analytics.
monkeSearch is a macOS-native file search tool that uses a local LLM to parse natural language queries into structured search parameters, then executes Spotlight searches via PyObjC. The system breaks queries into file type indicators (with specificity detection), temporal expressions, and residual keywords, converting them to NSPredicates using UTIs for file type matching and date comparisons for temporal filtering. It features a clean separation between LLM-based query parsing (query_gen.py) and Spotlight execution (parser.py), with the former being particularly well-engineered for reuse. The tool is designed for offline, agentic use with no cloud dependencies, targeting low-resource environments.