least-privilege repositories
Trending repositories tagged least-privilege, ranked by trending score. Updated daily.
-
1
Attention-Span-AI/Tego
Tego limits what any AI agent can touch on Linux, and records every run. Rules for MCP servers, CI jobs, Python workers, 24/7 assistants and coding agents, enforced by the kernel.
GitHub · Go · 27 stars · 2 forks · +1 stars in 24 hours · Trending score 0.73
-
2
Permify/permify
An open-source authorization as a service inspired by Google Zanzibar, designed to build and manage fine-grained and scalable authorization systems for any application. — Permify is now part of FusionAuth 🎉
GitHub · Go · 5,974 stars · 332 forks · 0 stars in 24 hours · Trending score 0.50
-
3
jentic/jentic-one
Self-hosted execution layer for AI agents: connect any agent to real APIs, scope exactly what it can touch, and keep credentials out of the agent's hands.
GitHub · Python · 226 stars · 27 forks · 0 stars in 24 hours · Trending score 0.31
-
4
unaibamir/agent-abilities-for-mcp
Give an AI agent access to your WordPress site without handing it the keys. It only does what you allow, and it's off until you turn it on.
GitHub · PHP · 9 stars · 1 forks · 0 stars in 24 hours · Trending score 0.19
-
5
sylvesterkaczmarek/agent-boundary-check
Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.
GitHub · Python · 44 stars · 39 forks · 0 stars in 24 hours · Trending score 0.09
-
6
udondan/iam-floyd
AWS IAM policy statement generator with a fluent interface, for TypeScript, JavaScript, Python, Java, C# and Go.
GitHub · TypeScript · 570 stars · 20 forks · 0 stars in 24 hours · Trending score 0.07
-
7
Wolido/async-subagent-isolation
Fix context rot & pollution in long AI agent sessions. Subagents run in isolated processes — main agent stays read-only. Context isolation via process isolation.
GitHub · TypeScript · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.06
-
8
Sarpedon-Quality-Lab/sql-security-community-scripts
Free SQL Server security check: a read-only PowerShell script that scans SQL Server, Amazon RDS and Azure SQL Database for risky permissions, sysadmin members, xp_cmdshell, orphaned users and audit gaps, and writes a local HTML report.
GitHub · PowerShell · 21 stars · 7 forks · 0 stars in 24 hours · Trending score 0.02
-
9
pickleshell/next-level-agent
Managed multi-agent system for OpenCode with one coordinator, risk-based routing, specialized roles, model pools and failover, durable memory, controlled context compaction and recovery, independent review, and execution telemetry.
GitHub · JavaScript · 7 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00