An extensible collection of agent skills for product and engineering teams that automates PRDs, planning, issue breakdowns and TDD flows, enabling modular integration of agent capabilities into repositories.

A fast local parser for text-based PDFs offering position-aware extraction, table detection and clean Markdown output — ideal for low-latency pipelines that want to avoid OCR for reports, finance and legal documents.

Prime Agent delivers a programmable, persistent RLM agent runtime for research and long‑running automation, enabling local execution of complex workflows while preserving session state.

An experimental virtual filesystem for edge and prototyping: it stores SQLite state in a Durable Object and offers execution via pluggable backends (container, Worker shell, JS runtime); suitable for research and prototypes but not production.

A layered memory system for long-horizon, multi-step agents that combines Mermaid-based symbolic short-term memory with hierarchical long-term representations to reduce context/token costs while preserving traceability and on-demand drill-down — intended for agent platforms that require persistent context management and auditability.

Superpowers provides a composable skills library and TDD-enforced agent workflow for Claude Code, enabling end-to-end automation from design and planning to subagent execution, with plugin integration and extensibility.

Agent Skills packages senior-engineer workflows into reusable agent-invokable skills to improve consistency and engineering quality across development stages.

Reasonix is a terminal AI coding agent for developers that combines configurable models, plugin tooling and prefix caching to deliver low-cost, cross-platform code assistance and automation.

AirLLM is an engineering-focused inference toolkit that optimizes VRAM and disk-loading to make large language models usable on resource-constrained single GPUs or desktops, suited for teams needing local deployment and fast experimentation.

reverse-skill delivers AI-driven task routing and on-demand toolchain bootstrap to organize repeatable reverse-engineering and pentest workflows; best suited for security researchers and teams with local tooling and compliance controls.