Cognee is an open-source AI memory platform that enables agents and applications to build, store, and query persistent knowledge graphs from documents, code, and conversations. The system provides a Python SDK, a FastAPI REST API, a CLI, a Next.js frontend, and an MCP server for agent integration. Core operations include ingesting data (remember), extracting entities and relationships via LLMs or GLiNER (cognify), retrieving context (recall), and self-improvement loops (improve). The architecture is modular with adapter/registry patterns for graph databases (Ladybug, Neo4j, Turso), vector stores (LanceDB, PGVector), LLM providers (LiteLLM, OpenAI, Anthropic, Ollama), and integrations (Slack, GitHub, Google Drive). The frontend provides a dashboard for dataset management, knowledge graph visualization, and business analytics. The project also includes an evaluation framework for benchmarking retrieval strategies against standard datasets like HotpotQA and BEAM. While production-grade in many areas, some components are marked as demo-quality or have cloud-only stubs.
53AIHub is an open-source enterprise AI knowledge management and agent orchestration platform. The codebase reveals a multi-tenant SaaS/self-hosted system that allows organizations to build, deploy, and operate AI agents across multiple backends (OpenAI, Coze, Dify, Gemini, etc.), manage knowledge bases with full RAG pipelines (document parsing, chunking, embedding, graph extraction, wiki generation), record and transcribe meetings with insight extraction, and provide a unified search and chat interface. The architecture is a Go monolith backend using Gin and GORM, with a monorepo frontend comprising three React apps (admin console, end-user portal, and embeddable agent plugin) sharing a common business logic and component library. Data flows center on document ingestion pipelines, real-time agent relay with tool execution, and recording/speech processing. The system integrates with vector stores (Qdrant), Elasticsearch, Redis, and various LLM providers. While primarily an application, it contains substantial data processing pipelines characteristic of a data_research project, particularly the RAG and recording insight modules.
This repository is the deployment system for Internet-in-a-Box (IIAB): an offline-first learning server for schools and communities without reliable Internet. It is an Ansible configuration-management application that installs and configures a complete local network stack — nginx reverse proxy, PHP-FPM, MySQL/PostgreSQL, hostapd WiFi access point, dnsmasq DNS/DHCP, Squid proxy, captive portal, Samba, CUPS — alongside a catalog of educational services such as Kiwix (offline Wikipedia/ZIM), Kolibri, WordPress, MediaWiki, Nextcloud, Gitea, JupyterHub, Moodle, Calibre-Web, and an offline OpenStreetMap/vector-tile mapping system with geocoding. Python, PHP, and Jinja2 templates generate systemd units, nginx virtual hosts, and app configs for every deployed service. Architecture is a staged Ansible pipeline: eleven role groups (0-init through 9-local-addons, then network) are driven from top-level playbooks (iiab-stages.yml, iiab-from-cmdline.yml) invoked by shell entry points (iiab-install, iiab-configure, iiab-network). Every role follows consistent conventions: defaults in defaults/main.yml, an install.yml and enable-or-disable.yml, boolean *_install/*_enabled flags validated up front with Ansible assert tasks, install state recorded in /etc/iiab/iiab_state.yml, and disk usage audited into iiab.ini. A custom Ansible module (get_curl) performs resumable/atomic downloads used across roles. Content provisioning is data-driven: maps and ZIM catalogs are generated (roles/maps/generate-catalog.py) and fetched at install time; offline search and geometry utilities (FQR, static_search.js) are bundled into the served front end. The project is actively developed (Ubuntu 24.04 and Raspberry Pi OS CI matrices, expected-state integration tests) but carries heavy legacy baggage: a large 0-DEPRECATED-ROLES tree, numerous .unused files, Python 2 support scripts, hardcoded versions/vendor URLs, plaintext default secrets, and fragile per-distro workarounds. The reusable gems — the custom download module, the tested geographic FQR geometry utility, the client-side static geocoder, the Ansible facts script, and the pdsm proot service manager — are isolated enough to extract into new projects. Overall it is a solid, professional infrastructure-as-code project with a few genuinely reusable components, tempered by significant accumulated technical debt.
proselint is a linter for English prose that checks style, usage, and common writing errors based on authoritative references like Garner's Modern American Usage. It operates as a Python library with a command-line interface (CLI) and a FastAPI web service. The architecture is a monolith: text input is tokenized and matched against a registry of checks (existence, preferred forms, consistency, etc.) using a pluggable regex engine (RE2 or Python re). Results are output as structured JSON or formatted text. The project also includes editor plugins (Sublime Text, CodeMirror), a pre-commit hook, and a Jekyll-based documentation site. While the core linting logic is well-architected with a clean check type system and configurable thresholds, the repository carries significant technical debt from vendored third-party code (an old CodeMirror distribution) and several unmaintained editor plugins. The codebase is actively maintained with CI/CD across platforms and Python versions, but the outdated dependencies and legacy components introduce medium technical drift.
This repository is a curated list of command-line tools, designed to help users discover and evaluate CLI utilities for various tasks. It does not contain any executable code or application logic; instead, it serves as a static reference document hosted on GitHub. The main content resides in `readme.md`, which organizes tools into categories such as CSV, File System, Git, Networking, and Programming Languages, each with links to the tools' source repositories and concise descriptions. Contribution guidelines are provided in `contributing.md` to maintain the list's quality and consistency. The repository uses shields.io badges to display metadata like the license and links to related curated lists. Although the repository lacks reusable software components or architectural patterns due to its static nature, it is well-maintained with recent commits and active issue tracking. It exhibits low technical drift as it has no code dependencies to become outdated. As a reference resource, it effectively fulfills its goal of aggregating CLI tools, though it does not demonstrate notable software engineering craftsmanship.
This repository is not a software application or data pipeline. It is a curated index of backend coding challenges sourced from real job postings by various companies. The only substantive content is a single README.md file containing a table of company names, countries, required stacks, and hyperlinks to external challenge repositories. The sole automated component is a GitHub Actions workflow that periodically checks the validity of those links and creates issues for broken ones. There is no source code, no application architecture, no data transformations, and no reusable software components. The repository serves as a reference directory for developers seeking practice challenges, but it provides no functional tooling or infrastructure.