Why we built Faramesh - The Bumper Bowling for AI Agents 🎳

Hey Product Hunt! 👋 I’m the founder of Faramesh, Amjad.

We built Faramesh because we noticed a terrifying gap in the agentic stack: The Trust Gap. Right now, most developers are securing their agents with 'System Prompts.' But prompts are just polite suggestions. In a production environment, 'polite suggestions' are liabilities. If you give an agent a delete key, you shouldn't have to hope it follows instructions, you should know it can't break the rules.

Faramesh is the Deterministic Gate for AI Agents. We move security from the stochastic prompt layer to a hard execution boundary. It’s 'Bumper Bowling' for agents: no matter what the model intends, the gate physically prevents any action not defined in your YAML policy.

What we’re launching today:

• One-Line Governance: Drop a gate into LangChain, CrewAI, AutoGen, LangGraph, and LlamaIndex with a single wrapper.

• MCP Support: Govern any tool-call via the Model Context Protocol.

• Hash-Bound Provenance: Every action is canonicalized and hashed for a 100% replayable audit trail.

• Policy Packs: Ready-to-use templates for common security hurdles (SQLi, financial limits, PII protection).

We’re moving the industry from 'Model-mania' to Infrastructure-mania. We don’t need 'smarter' agents to be safe; we need better plumbing.

We’re open-source and would love for you to put our gate to the test. I’ll be here all day to talk about deterministic architecture, agentic risk, and why we think the 'Stochastic vs. Deterministic' divide is the most important fight in AI today.

Check out the repo here: Link to GitHub

Contact Email: founders@faramesh.dev

Let’s make agents safe for production. 🛠️