Acontext is an LLM orchestration backend and agent memory framework designed to manage session state and knowledge for AI agents. It functions as a context manager and orchestration layer that integrates model providers with a secure code sandbox and a zero-knowledge data store. The project is distinguished by its approach to knowledge distillation, capturing agent learnings as reusable Markdown skills and structured memory files. It provides a secure execution environment where shell commands and scripts run in isolated containers with the ability to mount these persistent skill files direct
OpenViking is a multi-tenant context server and knowledge base administration system designed to provide AI agents with persistent long-term memory. It enables the indexing of diverse documents and codebases to support retrieval-augmented generation, allowing agents to recall past interactions, user preferences, and learned experiences across sessions. The project is distinguished by its use of a URI-based virtual filesystem to organize memories, resources, and skills. It implements a tiered context loading system that balances retrieval precision with token budgets by structuring data into a
sql.js-httpvfs is a virtual file system and loader designed to execute SQL queries against read-only SQLite databases hosted on remote static file servers. It enables the retrieval of database files over HTTP without requiring the entire file to be downloaded to the client. The project distinguishes itself by using byte-range HTTP fetching to simulate local random-access reads. It includes a chunking tool that splits large databases into smaller pieces via a JSON configuration, which helps bypass file size limits and optimizes caching. The system covers a range of capabilities including remo
This project serves as a comprehensive technical reference for the architecture and design of data-intensive applications. It provides a structured analysis of the fundamental principles required to build reliable, scalable, and maintainable software systems, covering the core trade-offs inherent in modern data infrastructure. The repository explores the mechanics of distributed data management, including strategies for replication, partitioning, and achieving consensus across multiple nodes. It details the design of storage engines, indexing techniques, and transaction management models, whi
pifs este un sistem de fișiere cu constante matematice și un simulator de stocare fără date. Acesta emulează un sistem de fișiere virtual prin maparea datelor fișierelor la secvențe de cifre din cadrul unor constante matematice infinite, pentru a elimina nevoia de stocare fizică pe disc.
Principalele funcționalități ale philipl/pifs sunt: Constant-Based Data Mapping, Data Storage Architectures, Virtual Filesystems, Data-Free Storages, File Storage and Metadata Management, File System Simulators, Mathematical Storage Simulators, Position and Length Indexing.
Alternativele open-source pentru philipl/pifs includ: memodb-io/acontext — Acontext is an LLM orchestration backend and agent memory framework designed to manage session state and knowledge for… phiresky/sql.js-httpvfs — sql.js-httpvfs is a virtual file system and loader designed to execute SQL queries against read-only SQLite databases… volcengine/openviking — OpenViking is a multi-tenant context server and knowledge base administration system designed to provide AI agents… vonng/ddia — This project serves as a comprehensive technical reference for the architecture and design of data-intensive… apache/gravitino — Gravitino is a federated metadata lake and unified data catalog designed to manage tables, files, and AI models across… ellanjiang/gameframework.