From d5d177ed2517aa371d865d297e242e5ffb4f3469 Mon Sep 17 00:00:00 2001 From: Haldir <0xN0rD@protonmail.com> Date: Sat, 12 Sep 2026 17:44:51 -0400 Subject: [PATCH] Update README.md More specific audience --- README.md | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index b082950..e56bf53 100644 --- a/README.md +++ b/README.md @@ -12,9 +12,15 @@ [![GitHub Stars](https://img.shields.io/github/stars/ExposureGuard/haldir?style=social)](https://github.com/ExposureGuard/haldir) [![SafeSkill 89/100](https://img.shields.io/badge/SafeSkill-89%2F100_Passes%20with%20Notes-yellow)](https://safeskill.dev/scan/exposureguard-haldir) -**The open-source governance layer for AI agents.** Identity, secrets, audit, and policy enforcement — MIT licensed, self-host or use our cloud. +**Your AI agent can call any API, spend any amount of money, and access any secret — with zero oversight. Haldir sits between your agent and its tools to enforce scoped sessions, encrypted secrets, spend caps, and a tamper-evident audit trail.** Identity, secrets, audit, and policy enforcement — MIT licensed, self-host or use our cloud. -Haldir enforces governance on every AI agent tool call: scoped sessions with spend caps, encrypted secrets the model never sees, hash-chained tamper-evident audit trail, human-in-the-loop approvals, and a proxy that intercepts every MCP call before it reaches your tools. Native SDKs for LangChain, CrewAI, AutoGen, and Vercel AI SDK. +Haldir sits between your agent and its tools to enforce: +- Scoped sessions with spend caps +- Encrypted secrets the model never sees +- Tamper-evident, hash-chained audit trail +- Human-in-the-loop approvals + +For developers and teams shipping AI agents to production.

Haldir quickstart: install, create a scoped session, check permission, log the action to the hash-chained audit trail