#llm

The Complete AI Development Toolkit for Claude Code — 114 skills, 37 agents, 212 hooks. Production-ready patterns for full-stack development.

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond

Declarative language for composable Al workflows. Devtool for agents and mere humans.

Hundreds of models & providers. One command to find what runs on your hardware.

Braintrust tracing plugin for pi

One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

BioMCP: Biomedical Model Context Protocol

The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it, with all the best practices already in place.

Statistical Machine Intelligence & Learning Engine

📝 Markdown and HTML renderer for Svelte 5 — built for streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, token caching, TypeScript types.

A unified interface for various AI model providers

A modern, blazing-fast SQL IDE for the cloud era. Query PostgreSQL, MySQL, SQLite & MongoDB from anywhere your browser is your new database studio.

TokenSpeed is a speed-of-light LLM inference engine.

🥨 Lobe Icons - Brings AI/LLM brand logos to your React & React Native apps — static SVG/PNG/WebP, no dependencies.

TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

Pragmatic AI Labs MCP SDK

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

A set of pi-extensions, including pi-continuous-learning that continually improves you pi coding agent experience

One endpoint in front of unlimited MCP servers and REST APIs. The agent sees a fixed ~15-tool surface however many you connect, so tool-list token cost stays flat (about 89% less on a 100-tool stack) and the savings climb as you add more. Single Rust binary.

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

AI integration layer for Jido agents with LLM orchestration and reasoning strategies.

LLM model metadata catalog with fast, capability-aware lookups

LiteLLM proxy provider extension for Pi

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

DocLang spec and reference toolkit

Effortlessly request recommended movies, TV shows and anime to Jellyseer/Overseer based on your recently watched content on Jellyfin, Plex or Emby—let SuggestArr handle it all automatically, keeping your library fresh with new and exciting content!

Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.