Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

General-purpose agent with transport abstraction, state management, and attachment support

Pi extension that exposes Firecrawl web scraping and crawling tools.

To get the docs for the LLM, check out [this index](./llm/index.md).

To get the docs for the LLM, check out [this index](./llm/index.md).

TypeScript bridge for recursive-llm: Recursive Language Models for unbounded context processing with structured outputs

Тонкий шар роботи з LLM (локальні omlx + хмарні провайдери) поверх pi: model tiers, one-shot, agentic-раннери, write-guard, trace, telemetry, prompt-budget

OpenTelemetry Exporter Prometheus provides a metrics endpoint for Prometheus

Streaming colorization for Shiki, useful for highlighting LLM outputs and other text streams

A better EventSource API

Local SQLite memory engine for Oh My Pi agents

Information on LLM models, context window token limit, output token limit, pricing and more

WebLLM provider for Vercel AI SDK v5+ (High-performance in-browser LLM inference)

Shared modules of the Spacecat Services - Scrape Client

Bright Data service for scraping purposes in n8n

FireCrawl nodes for n8n

To get the docs for the LLM, check out [this index](./llm/index.md).

To get the docs for the LLM, check out [this index](./llm/index.md).

To get the docs for the LLM, check out [this index](./llm/index.md).

To get the docs for the LLM, check out [this index](./llm/index.md).