Agent infrastructure
OpenAPPA
archestra-ai/OpenAPPA
Deterministic guardrails for AI agents that check data sensitivity before every tool call, running in-process or as a sidecar.
Topics
Related projects
superagent6.8kAn open-source safety layer for AI agents that blocks prompt injections, redacts PII, scans repos, and red-teams production endpoints.
bifrost8.8kA high-performance open-source LLM gateway unifying 20-plus providers behind one API with failover, caching, and governance.
nono4.5kZero-setup sandbox for AI agents providing secure, multiplexed execution paths with least-privilege isolation and near-zero added latency across reusable terminals.
onecli3.6kOpen-source sandboxed agent harness for teams, providing each employee with a secured personal agent under centralized gateway credential injection and enforced access policies.
skill-scanner2.6kA security scanner for AI agent skills that detects prompt injection, exfiltration and malicious code for CI and review workflows.
landrun2.3kA lightweight Linux sandbox using Landlock to run any process with fine-grained filesystem and network isolation.