Search

NestJS module for interacting with web3.storage. It provides a service for uploading and retrieving data from the decentralized web using the web3.storage service. The module can be configured using the NestJS config service.

Local storage implementation

Amperstand engine — extraction, storage, search, and the HTTP server.

Fair waiting-queue + honest usage accounting for a Mac Studio shared as a small, trusted team's personal LLM compute server — a sidecar in front of a multi-backend LiteLLM gateway.

Local Falcon CLI as an importable mirage / Cloudflare-Worker command via @mirage-cli/core.

HubSpot CLI — read-only CRM (contacts, companies, deals, tickets, custom objects), marketing (forms, emails, campaigns), and CMS (blog, pages, HubDB). hs-style grammar; reuses your `hs account auth` login. Mirage-compatible command shape.

HubSpot (read-only CRM/marketing/CMS) CLI as an importable mirage / Cloudflare-Worker command via @mirage-cli/core.

Airtable (read-only bases/schema/records) CLI as an importable mirage / Cloudflare-Worker command via @mirage-cli/core.

Antimatter adapter for AG2 (AutoGen) CLI framework

Custom Triton/CUDA kernels that complement Liger Kernel for LLM post-training

Privacy-first SDK for modelstat — wrap your backend LLM calls and ship redacted usage to a local daemon or the modelstat server, without touching live-request latency.

azure openai adapter for chatluna

Shareable config for ESLint for projects that use Cypress

A single-port OpenAI- and Ollama-compatible reverse proxy that swaps the GPU between local LLM engines on demand.

Human-supervised AI code generation using Plan-Do-Check-Act methodology with TDD and refactoring. Works as Claude Code skill or standalone prompts.

Claude Code skill: YouTube URL or local video → key-points note + timestamped transcript. Zero pip deps, original-language subtitle de-dup, Whisper fallback.

🤖 AI产品经理超级工作台 | 12阶段·60+框架·20+交付物 | LLM·RAG·Agent·Prompt工程·AI评测·AI安全 | EU AI Act·深度合成新规·Token经济学 | WuKong/Claude/OpenClaw Skill

A Claude skill making the model an expert in Apple's container CLI — run Linux containers & persistent Linux machines on Apple silicon. Benchmarked: 100% vs 68% vs plain Claude.

CLMM position-lifecycle + risk skill for the Solana AI Kit — IL, range-exit probability, rebalance EV, delta-neutral hedging across Orca/Raydium/Meteora + Drift

Alexey Vorobey's experimental expert circle for Claude Code — 16 distilled mental models (Eric Seufert, Andrew Chen, Elena Verna, ...) that auto-refresh on cadence from LinkedIn, RSS, YouTube, podcasts.