HN Showcase
Back to browse
GitHub Repository

The "Cloudflare for AI Agents". 7-layer security interceptor, real-time observability dashboard, and automated reliability testing for MCP and AI tool chains. Prevent hallucinations, prompt injection, and destructive tool calls.

14 starsPython

ToolGuard – Pytest for AI agent tool calls

by Heer_J·Mar 17, 2026·1 point·2 comments
Visit ProjectView on HN

AI Analysis

●●●BangerSolve My ProblemZero to One

Finally, pytest for AI tool calls when evals only test intelligence.

Strengths
  • •Reads type hints to generate Pydantic schemas for deterministic fuzzing.
  • •No LLM needed to run tests, making it viable for CI/CD pipelines.
  • •Clear separation: tests execution reliability, not AI reasoning quality.
Weaknesses
  • •Python-only, no support for TypeScript or other agent frameworks.
  • •Early project with only 16 commits and 1 star.
Category
AI/ML
Target Audience

Developers building AI agent tool chains

Similar To

LangSmith · Arize Phoenix · Pytest

Post Description

I got tired of my AI agents crashing because the LLM hallucinated a JSON key or passed a string instead of an int. So I built ToolGuard — it fuzzes your Python tool functions with edge-cases (nulls, missing fields, type mismatches, 10MB payloads) and gives you a reliability score out of 100%.

No LLM needed to run tests. It reads your type hints, generates a Pydantic schema, and deterministically breaks things.

pip install py-toolguard

GitHub: https://github.com/Harshit-J004/toolguard

If you are building complex tool chains, I would be incredibly honored if you checked out the repo. Brutal feedback on the architecture is highly encouraged!

Similar Projects

Developer Tools●●●Banger

ToolGuard – Pytest for AI agent tool calls

Layer 2 execution testing without LLMs when eval frameworks only test intelligence.

Ship ItSolve My ProblemBig Brain
Heer_J
103mo ago
Developer Tools●●Solid

PolyMCP – Run MCP Python Tools in WASM via Pyodide

PolyMCP turns Python functions into a single Pyodide WASM bundle so agents can call tools directly in the browser or at the edge — neat and practical. It keeps MCP niceties like input validation, error handling, and orchestration inside the bundle and ships runnable demo HTML to prove the flow. Be realistic about Pyodide trade-offs: bundle size and no native-extension support make this best for lightweight, interactive tools and demos rather than heavy backend workloads.

WizardryNiche Gem
justvugg
204mo ago