Skip to content

SponsioLabs/Sponsio](https:

AI Agents & Assistants

A runtime guardrail that enforces deterministic contracts for LLM agents, blocking unsafe actions in sub‑millisecond time with zero LLM cost.

Python Latest v0.1.1 · 2mo ago Security brief →

Features

  • Enforces agent contracts via formal methods checks before each action
  • Blocks malicious or unintended behavior (e.g., destructive SQL) deterministically under 0.01 ms
  • Works across multiple frameworks: LangChain, Claude Agent, OpenAI Agents, Google ADL, CrewAI, Vercel AI, MCP, etc.
  • Provides audit‑trail logs and configurable outcomes (Pass / Block · Warn · Escalate / Redirect)
  • Supports both Python and TypeScript projects

Recent releases

View all 2 releases →
Upgrade now
v0.1.1 Bugfix
Breaking upgrade

Fixes pyyaml crash

Upgrade now
v0.1.0 Bug fix
Breaking upgrade Auth RBAC

Restored missing modules

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

About

Stars
466
Forks
28
Languages
Python TypeScript JavaScript
Downloads/week
1 ↑58%
NPM Maintainers
1
Contributors
6
TypeScript
Types included ✓

Install & Platforms

Install via
pip npm

Community & Support

Beta — feedback welcome: [email protected]