EverOS is a local-first, markdown-based memory framework for AI agents and chat applications. It ingests conversational sessions via a FastAPI REST API, extracts structured memories (episodes, atomic facts, agent cases, skills, user profiles) using LLMs, persists them as version-controllable Markdown files, and maintains derived search indexes in LanceDB (vector + BM25) and SQLite. The system provides a rich retrieval layer with keyword, vector, hybrid (RRF), and agentic (LLM-guided multi-round) search methods, plus a knowledge wiki feature. An Offline Memory Engine (OME) runs background strategies (reflection, clustering, extraction) on cron/idle/immediate triggers, and a cascade daemon watches the Markdown filesystem to reconcile indexes. The architecture is a layered monolith (entrypoints → service → memory → infrastructure) with cross-cutting components for LLM, embedding, rerank, tokenizer, and config. It ships with a CLI (Typer), a TUI demo (Textual), and extensive integration tests. While primarily an application, it includes a benchmark harness (LoCoMo, LongMemEval, EverMemBench) and evaluation fixtures, giving it a hybrid character with a strong research-oriented testing pipeline.
This repository is a curated directory/registry of 5,300+ community-built skills for OpenClaw, an AI agent platform. It is not a software application — it contains no runtime code, no API, and no executable logic. Instead, it is a structured catalog of markdown files organized into 30+ categories (DevOps, Search & Research, Coding Agents, etc.), where each entry links to a skill hosted on ClawHub (OpenClaw's public skills registry). The repo functions as a discovery and navigation layer: users browse categories to find skills, and contributors submit new skills via pull requests validated by a CI workflow. The repository also documents filtering criteria (excluding spam, duplicates, low-quality, crypto, and malicious entries), security considerations (VirusTotal scanning partnership), and contribution guidelines. While it shares some characteristics with a data_research repo (structured metadata, no application code), it is best classified as a curated content registry — the 'application' label applies only in the sense that it is not a data pipeline or research project. Key patterns include a consistent category taxonomy, a PR validation workflow, and documented quality gates. The main risks are link rot (5,300+ external links with no automated checking), quality variance across entries, and the manual effort required to maintain a list at this scale.