AI SRE tools for RCA, Incident Response, Cost-Saving, Infra management, DevOps and more
Your machine's AI brain. One 20MB binary gives every tool, script, and cron job shared AI memory + 136 API endpoints. Desktop app, CLI, Telegram — all connected. Rust-powered.
Deploy OpenClaw locally with one click. Configure the latest Claude models. Supports Telegram & Feishu.
Interactive visualization and exploration of large language model (LLM) systems, infrastructure, and inference workflows
reShapr website
《AI Infra》:面向平台建设方的中文 AI 基础设施书稿——31 章 + 附录 + 结构化数据与证据体系
The complete AI stack, bottom-up from sand to a served token — a source-backed Obsidian vault. 15 domains, 110 topics, beginner to expert: semiconductor physics, fabs, GPUs, datacenters, power, cooling, training, and inference.
🩺 RAG Doctor — Open-source diagnostic tool for Retrieval-Augmented Generation (RAG) systems. Analyzes codebases to detect architectural issues in LLM pipelines such as missing retrieval, bad chunking, embedding mismatches, and vector database misuse.
Exercise: Integrate Model Context Protocol with GitHub Copilot
Model-independent agent harness with persistent memory, MCP orchestration, skills, tools and local-first governance.
Safety-first AutoDL plugin for Codex with 26 typed MCP tools and documentation-aware skills
Surgical middleware for LLMs. Reduces token waste by 40-60% using Triple-Tier Memory (Anchor + Fact Sheet + Buffer) and Semantic Caching. Built for production-grade branding & cost-recovery.
CLI and browser lab for pruning LLM agent context under a token budget
Community catalog of LLM model specs — pricing, context windows, capabilities, and AI-CLI compatibility. Auto-synced from LiteLLM with objective corrections.
Enable persistent memory for Claude that works across crashes and restarts in both Claude Code and Claude Cowork environments.
Deterministic prompt optimization middleware for LLM workflows.
Deterministic execution loop core for AI builders — turn tasks into reproducible runs, explicit decisions, and retryable improvements.
GarageAI is an ambitious endeavor to construct Europe's AI backbone from the ground up, beginning in unconventional spaces. We deploy high-performance, single-tenant LLM inference nodes directly on customer premises or within our distributed network of dedicated, solar-powered garages across Europe. This innovative approach enables the sustainab...
A data-driven registry and operator-based specification for normalizing AI models. Decouple providers from your code with a unified, versioned manifest.
Desktop operator surface for an evidence-backed AI organism: tools, memory, autonomy, receipts, and transparent model execution.
To associate your repository with the ai-infrastructure topic, visit your repo's landing page and select "manage topics."