Search

Tandem is an MCP bridge that lets a chatbot (Claude.ai or ChatGPT) spin up and drive, interactive Claude Code sessions on your own machine. Runs 2 sessions in a lead/worker loop that works autonomously. Also makes claude code respond to the initial Chatbot through the browser so it can respond back.

📚 给中国律师/法务的一站式开源 AI 工具地图｜184 个 gh 核验开源仓·按工作场景分类·能否商用标注｜awesome list

Maximum Claude output with minimum tokens. 50+ compression patterns, 10 system prompts, benchmarked results. Star to unlock usage.

AI Skills. A self-contained "brain" distilled from The Book of Elon — 72 mental models + the full book corpus, answering in his voice.

Claude skills to run ads: advertising & marketing strategy, campaign structure, targeting, creative, and budgets for Google Ads, Meta Ads, TikTok & more.

Simplified LLM API calls and prompt construction for GPT, Claude, Gemini and more

CLI tool for simplifying LLM post-training workflows (SFT, DPO, RLHF) via LLaMA-Factory

Filesystem Storage Backup

Allows to use server environment with fs storage attachment

Allows to use server environment with fs storage attachment S3

Allows to use server environment with fs storage attachment

Swiss AI Hub Pipeline SDK: Dagster-based document ingestion, parsing, embedding, and vector storage for RAG.

Allows to use server environment with fs storage

CLI installer for claude-vault-scaffold — sets up Obsidian + Claude Code vault integration

Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.)

One-line installer for Vertical AI skill distribution

Core domain logic for @nexus-cross/connect-kit — types, ports, utilities

Zero-dependency TypeScript stream orchestration for LLM pipelines — race, fallback, merge, and tee over any AsyncIterable or ReadableStream, generic over T.

Install the llm-model-metadata SKILL.md skill with npx

Grawkus — terminal coding agents with a mind for the whole repo. Speaks any OpenAI-compatible API with repo-aware context, benchmark tracing, MemPalace memory, and terminal-first agent workflows.