Metadata-Version: 2.4
Name: zocrity
Version: 0.1.2
Summary: Budget-Safe AI Agents with Local Caching and Circuit Breakers.
Home-page: https://agentegineroom.replit.app
Author: Zocrity
License: MIT
Project-URL: Homepage, https://agentegineroom.replit.app
Project-URL: Repository, https://github.com/Zocrity-Ai/zocrity-python-sdk
Project-URL: Documentation, https://agentegineroom.replit.app/start
Keywords: ai,agents,safety,budget,llm,openai,langchain,circuit-breaker
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: openai>=1.0.0
Requires-Dist: httpx>=0.24.0
Provides-Extra: langchain
Requires-Dist: langchain-core>=0.1.0; extra == "langchain"
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.20.0; extra == "anthropic"
Provides-Extra: litellm
Requires-Dist: litellm>=1.0.0; extra == "litellm"
Provides-Extra: crewai
Requires-Dist: crewai>=0.1.0; extra == "crewai"
Provides-Extra: llama-index
Requires-Dist: llama-index-core>=0.10.0; extra == "llama-index"
Provides-Extra: server
Requires-Dist: fastapi>=0.110.0; extra == "server"
Requires-Dist: uvicorn>=0.27.0; extra == "server"
Provides-Extra: all
Requires-Dist: langchain-core>=0.1.0; extra == "all"
Requires-Dist: anthropic>=0.20.0; extra == "all"
Requires-Dist: litellm>=1.0.0; extra == "all"
Requires-Dist: crewai>=0.1.0; extra == "all"
Requires-Dist: llama-index-core>=0.10.0; extra == "all"
Requires-Dist: fastapi>=0.110.0; extra == "all"
Requires-Dist: uvicorn>=0.27.0; extra == "all"
Dynamic: author
Dynamic: home-page
Dynamic: requires-python

# 🛡️ Zocrity — The Emergency Brake for AI Agents

Stop API hallucination loops before they drain your budget. Zocrity wraps your agent runs with a hard stop so runaway retries, repeated prompts, and token spirals don't turn into surprise $100 bills.

---

## 💸 The Problem: The 'Infinite Loop' Tax

AI Agents are expensive. A single coding loop or 'hallucination spiral' can burn through your OpenAI credits while you sleep. Most developers don't realize they've spent $50 until the invoice hits.

---

## ⚡ The Solution: Zinc Infrastructure

Zocrity is a local-first, zero-config utility that intercepts your LLM calls to provide:

🛑 **Hard-Stop Budgets:** Set a limit (e.g., $2.00). Zocrity severs the connection locally the moment you hit it.

🚀 **1,000x Speedup:** Our Local Zinc Cache serves repeated prompts from a local SQLite database in ~5ms. Save 100% on compute for repeated tests.

🤖 **Loop Detection:** Automatically kills agents that repeat the same prompt structure 3+ times.

📊 **Transparent Reports:** Run `zocrity.report()` to see exactly how much money and time you've saved.

---

## 📦 Quick Install

```bash
pip install zocrity
```

---

## 🛠️ Usage (2 Lines of Code)

```python
import zocrity

# Protect your wallet & enable the lightning-fast cache
zocrity.shield(mode="HALT", enable_cache=True)

# Your existing OpenAI/LangChain code stays exactly the same!
```

---

## 🏆 The Sentinel List

We are building the world's safest AI infrastructure. The first 100 contributors/users to fork this repo and submit a PR or issue get listed here as Zinc Sentinels.

- **Zocrity-Ai** — Founder & Lead Architect
