RBR-0001 / infrastructure
razvandimescu/numa
Portable DNS resolver in Rust — .numa local domains, ad blocking, developer overrides
Public Salvage Yard
39 verified parts. Browse by role or search what the part does.
RBR-0001 / infrastructure
Portable DNS resolver in Rust — .numa local domains, ad blocking, developer overrides
RBR-0002 / context-shaping
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
RBR-0003 / surface
Open-source, self-hostable social media management platform. Schedule, publish, and manage content across 10+ platforms from a single dashboard. Free alternative to Buffer, Sendible, and SocialPilot.
RBR-0004 / context-shaping
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
RBR-0005 / execution
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
RBR-0006 / execution
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
RBR-0007 / context-shaping
Python tool for converting files and office documents to Markdown.
RBR-0009 / context-shaping
A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
RBR-0010 / context-shaping
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 14 platforms
RBR-0012 / execution
Main development repository for TinyOS (an OS for embedded, wireless devices).
RBR-0014 / orchestration
AI agents running research on single-GPU nanochat training automatically
RBR-0015 / orchestration
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
RBR-0016 / context-shaping
An agentic skills framework & software development methodology that works.
RBR-0018 / surface
Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.
RBR-0019 / execution
control your applications using pi-coding-agent. fully invisible.
RBR-0020 / observation
See where Claude Code is burning tokens - turn raw JSONL transcripts into local cost analytics, hotspot views, and session-level usage insight.
RBR-0022 / observation
🚀 Beautiful highly customizable statusline for Claude Code CLI with powerline support, themes, and more.
RBR-0023 / execution
RBR-0024 / context-shaping
The shadcn for agent UI. A framework-agnostic design language for dense, AMOLED-black, multi-surface interfaces
RBR-0025 / orchestration
Self-improving agent runtime that learns from experience — test-verify-fix loops, correction detection, cross-project memory, multi-model orchestration.
RBR-0029 / infrastructure
An open, sub-millisecond, single-executable Firebase alternative with type-safe APIs, built-in WebAssembly runtime, realtime subscriptions, auth, and admin UI built on Rust, SQLite & Wasmtime.
RBR-0030 / memory
The open-source memory operating system for AI agents. Persistent memory, semantic search, loop detection, agent messaging, crash recovery, and real-time observability.
RBR-0032 / surface
BookLore: A self-hosted, multi-user digital library with smart shelves, auto metadata, Kobo & KOReader sync, BookDrop imports, OPDS support, and a built-in reader for EPUB, PDF, and comics.
RBR-0033 / infrastructure
Docker container for development, stuffed with modern CLI/TUI tools. Batteries included.
RBR-0034 / observation
See where your computer connects and what stands out on a live world map.
RBR-0036 / context-shaping
232+ Claude Code skills & agent plugins for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory.
RBR-0038 / infrastructure
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]