Search

No description available

Validate LLM outputs against schemas with automatic retry and JSON extraction.

Test prompt variants across LLM providers with LLM-as-judge evaluation

Cloud-agnostic rate limit mitigation for LLM APIs

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.

No description available

A safety+observability layer for LLM calls: policy guardrails, secret scanning, sanitization, schema validation, retries, budgets, and logs.

LLM Sandbox is a lightweight and portable sandbox environment designed to run large language model (LLM) generated code in a safe and isolated mode.

This is a python sdk for llm

Smart memory management for LLM conversations - topic-aware compression that just works

Directly Connecting Python to LLMs - Dataclasses & Interfaces <-> LLMs

simple llm based tools to access from cli

Tiny wrapper exposing Prompture helpers to convert LLM output into JSON.

Tokenizer utilities for LLM inference

llm-toolbox is now LMtoolbox

Tiny wrapper exposing Prompture helpers to convert LLM output into TOON.

Meta-package for LLM Tracekit - OpenTelemetry instrumentations for LLM providers.

No description available

A plugin for LLM that enables proper plugin management when installed via uv tool.

LLM plugin to access models available via the Venice API