Faramesh

Establishing the Standard for Agentic Execution Control

2 followers

Establishing the Standard for Agentic Execution Control

2 followers

The first deterministic governance and control system for AI agent actions, providing policy-based access control, approval workflows, and comprehensive observability.

Free

Launch tags:SaaS•Artificial Intelligence•GitHub

Launch Team

Render: Get up to $100K in startup creditsCloud infrastructure for founders who want to move fast and NOT break things

Promoted

Maker

📌

We spent most of 2025 watching teams try to 'prompt' their way out of agentic hallucinations. It doesn't work. If you give an LLM-based agent access to a production database or a shell, you are always one 'ignore previous instructions' jailbreak away from a catastrophic incident. We believe Faramesh is the first project to treat the 'Agent-to-System' bridge as a distributed systems problem rather than a prompting problem. The hardest part to get right was the Deterministic Canonicalization. LLMs are inherently messy, one model might send {"power": 100.0} while another sends {"power": 100} for the same tool call. To build a reliable Action Authorization Boundary (AAB), we had to ensure that the semantic intent produces a stable, cryptographic hash every single time. Without this, you cannot have reliable RBAC, audit trails, or 'fail-closed' security for autonomous agents. We’ve open-sourced the core logic today and would love for the community to tear apart our approach in canonicalization.py. We’re specifically interested in whether people think this architecture could eventually be standardized into a formal 'Agentic Firewall' protocol.

Report

9mo ago

Forum Threads

p/faramesh

•

9mo ago

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.

p/faramesh

•

9mo ago

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

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

View all