Claude Code skill that makes Claude respond like a caveman while maintaining full technical capability
MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens.
Caveman Code — a terminal coding agent
OpenCode plugin — injects caveman compression rules every turn, survives /compact, supports live mode switching
Why use many token when few do trick. Caveman mode for pi — cuts ~75% output tokens while keeping full technical accuracy.
Skillflag producer CLI reference implementation.
The open agent skills ecosystem
The Gateway provider for the [AI SDK](https://ai-sdk.dev/docs) allows the use of a wide variety of AI models and providers.
Caveman token-compression plugin for OpenCode
AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.
A fully-featured caching GraphQL client.
The **[Anthropic provider](https://ai-sdk.dev/providers/ai-sdk-providers/anthropic)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Anthropic Messages API](https://docs.anthropic.com/claude/reference/messages_post).
Tlon/Urbit skill for OpenClaw agents
The **[OpenAI provider](https://ai-sdk.dev/providers/ai-sdk-providers/openai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the OpenAI chat and completion APIs and embedding model support for the OpenAI embeddings API.
The **[Google Generative AI provider](https://ai-sdk.dev/providers/ai-sdk-providers/google-generative-ai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Google Generative AI](https://ai.google/discover/generativeai/)
Native Pi caveman communication mode with session persistence, slash command control, status badge, and settings-manager integration.
Caveman communication mode plugin for opencode
Cross-agent persistent memory with compressed storage. Plug-and-play memory for Claude Code, Gemini CLI, OpenCode, Codex, and Cursor.
This package provides a foundation for implementing providers that expose an OpenAI-compatible API.
Various graph generators for graphology.
General-purpose agent with transport abstraction, state management, and attachment support
This package provides building blocks to create framework-level integration of Apollo Client with React's streaming SSR. See the [@apollo/client-integration-nextjs](https://github.com/apollographql/apollo-client-integrations/tree/main/packages/nextjs) pac
The **[xAI Grok provider](https://ai-sdk.dev/providers/ai-sdk-providers/xai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the xAI chat and completion APIs.
Token compression plugin for OpenCode AI — multi-layer filtering, semantic compression, and dynamic context pruning.