Guardrails

Nexus-Agent is an autonomous software-engineering agent with a self-healing execution loop, AST pre-validation, persistent rollback, and terminal and web interfaces.

An open-source gateway for AI agents acting on financial data: verifies supporting evidence, evaluates a bounded policy, returns PERMIT, BLOCK, or ESCALATE, and emits a hash-chained receipt.

Okto-Nexus is a local-first MCP coordination hub for multi-agent teams, with durable messaging, atomic handoffs, governance controls, and human approval.

Okto-Pulse is a local-first SDLC workbench for AI coding teams, with structured project artifacts, governance gates, validation rules, and MCP tools.

Persistent, consensus-validated memory infrastructure for AI agents, with confidence scoring and natural memory decay.

An agent governance platform that intercepts tool calls for policy checks, human approval, and auditable traces.

SUNGLASSES is an open-source local input firewall for AI agents that scans text and files for prompt injection, credential leaks and data exfiltration, and reports both what it matched and what it could not read.

An open-source security and governance SDK for AI applications, providing deterministic policy enforcement, guardrails, cost tracking, and audit evidence.

Vetto is a daemon-less, rootless sandbox that applies kernel-enforced security policies to AI coding agents, with agent command shims and MCP tool isolation.