Llm Ops Python Packages

openllm

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

autorag

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

openllm-core

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

friendli-client

Friendli Suite Client

openllm-client

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

agent-policy-layer

The standard protocol for defining runtime guardrails for your enterprise agents with a mission of trustworthy and reliable agentic systems 🛡️

ultracontext

Open Source Context infrastructure for AI agents. Auto-capture and share your agents' context everywhere.

aiconfig-extension-hugging-face

AIConfig is a config-based framework to build generative AI applications.

moralstack

MoralStack is a governance and safety layer for LLM applications. It analyzes user requests before generation, evaluates risk and intent, and decides whether the AI should answer normally, answer safely, or refuse. The goal is to make AI systems more auditable, controllable, and reliable in sensitive or regulated contexts.

python-aiconfig

AIConfig is a config-based framework to build generative AI applications.

lintlang

lintlang is a static linter for AI agent configs, tool descriptions, and system prompts that runs zero-LLM quality gating in CI. Catches language-level failures (vague tool descriptions, missing stop conditions, schema gaps) before they reach runtime, with deterministic regex + structural detectors and no model calls.

openshard

Receipts for AI coding agents. Route work across models, gate risky actions, verify results, and keep an execution record.

agentcontract

Behavioral contracts for AI agents — Python reference implementation

wildedge-sdk

ML inference monitoring for Python: on-device and remote models

aigovkit

Vigil AI Governance SDK — one-line LLM call logging plus evals (LLM-as-judge, RAG metrics, drift)

aiconfig-extension-llama-guard

An extension for using LLama Guard with aiconfig

replayd

Turn failed AI agent runs into replayable regression tests

ai-sdlc-framework

Python SDK for the AI-SDLC Framework

lm-debug-eval-ui

AIConfig is a config-based framework to build generative AI applications.

aiconfig-extension-gemini

An extension for using Gemini with aiconfig

periflow-client

Client of PeriFlow, the fastest generative AI serving available.

aiconfig-extension-llama

Model Parser extension for Llama

liteswarm

Lightweight Agent Framework for building AI apps with any LLM

claude-code-langfuse-hook

Drop-in Claude Code Stop hook that ships per-user, per-project usage traces to Langfuse.