Reusable AI skills and capabilities for agent workflows
Benedikt Hiepler
LLM plugin providing access to Grok models using the xAI API
Michael Bianco
CLI tool for managing LLM IDE prompts and rules
Sondre 'Ooki' Glimsdal <[email protected]>
Async OpenAI Responses API client with typed tool calling, lazy output parsing, and Azure/Databricks backends
Greg Crabtree
Robust JSON parsing for LLM outputs with automatic repair and field extraction
Yossi Ovadia <[email protected]>
LLM Katan - Lightweight LLM Server for Testing - Real tiny models with FastAPI and HuggingFace
Erin Clemmer <[email protected]>
A tool for loading and computing on parts of LLM models.
Production-ready LLM client with audit trail, deterministic caching, and provenance tracking
Renato Freitas <[email protected]>
AI-powered log analyzer for CI environments using LLMs
Johannes Hötter
Turn Python functions into typed LLM calls using docstrings as prompts
Faizan Batra
Intelligent multi-LLM request router for cost optimization
Ljubomir Buturovic
A CLI tool to list available LLM models from various providers
Hamza Ferrahoglu <[email protected]>
Advanced system information tool for local LLM usage
Paul Eger
Use an LLM to run inference, for NER (named entity recognition) and/or NEL (named entity linking). Build a knowledge graph. Evaluate results.
...moreSergey Alexandrov
LLM plugin providing access to models running on an Ollama server
Simon Willison
LLM plugin for models hosted by OpenRouter
Ujjwal Prakash Bajpayee <[email protected]>
Validate LLM outputs against schemas with automatic retry and JSON extraction.
Prashant Dudami
Cloud-agnostic rate limit mitigation for LLM APIs
LLM Redact Contributors
Privacy-first text redaction using local LLM models with rule generation capabilities
Yaman Ahlawat <[email protected]>
A centralized registry for discovering and managing LLM model capabilities. Track model features, costs, and limitations across providers like OpenAI and Anthropic. Supports both verified model definitions and user-managed entries with local storage.
...moreYour Name
A safety+observability layer for LLM calls: policy guardrails, secret scanning, sanitization, schema validation, retries, budgets, and logs.
...moreKen Furudate
Dynamic feature distillation framework for robust zero-shot LLM annotation.
Sharan
Smart memory management for LLM conversations - topic-aware compression that just works
Andreas Kirsch, Daedalus Lab Ltd
Directly Connecting Python to LLMs - Dataclasses & Interfaces <-> LLMs