Operating system written in Erlang and Rust

A scripting language for cowboy coders

Native Rust runtime for adversarial extension workloads with deterministic replay, cryptographic decision receipts, and fleet-scale containment.

Electron runtime layer providing protocol-based separation, component assembly, and capability-based process control.

plan-bound authorization architecture for governing privileged effects in untrusted computational agents.

KAIROS-ARK is a high-performance, Rust-based Agent Runtime Kernel built for industrial-grade reliability. It delivers sub-100µs dispatch latency, event-sourced deterministic replay, and kernel-enforced capability sandboxing, bridging Python prototypes and production AI systems.

my tinkering notebook (blog)

Cryptographic trust mediation layer for AI agent frameworks. Apache 2.0 reference architecture composing device-attested admission, short-TTL scoped capabilities, runtime continuity envelopes, context provenance anchoring, agent intent binding, FHE context gate, MCP boundary mediation, signed policy bundles, and tamper-evident audit chain.

JavaScript on genode using the Moddable XS engine

A WASM‑first, capability‑native unikernel designed to run small, isolated WASI workloads on edge/cloud hosts, providing deterministic temporal snapshots, capability‑based authority transfer, and in‑kernel verification to enable secure, auditable migration and replay. It targets security and audit-sensitive deployments and systems‑research

Bounded shell and CLI execution for AI agents: structured contracts, policy-gated execution, hardened Linux runtime enforcement, and signed receipts.

Capability-security kernel for autonomous agents — seccomp/SELinux for agentic AI. Formal, auditable, language-agnostic, cryptographically verifiable.

The Kernel of CharlotteOS, An Experimental Modern Operating System

🚀 Streamline agentic AI workflows with KAIROS-ARK, a robust OS focused on integrity, reproducibility, and superior governance for critical applications.

A sample fastapi web app to integrate with a Tahoe-LAFS grid

Capability-based safety gates for LLM agents. The model proposes; signet authorizes.

Toy governance CLI demo: deny-by-default “danger actions” gated by signed, expiring capability leases (global revoke-all + nonce revoke) plus guarded memory quarantine. Simulation-only: no real network/shell/files. Includes tripwire + tests to prevent misuse.

Autonomous loop agent that audits other agents for missing capability receipts

Tiny Rust runtime turning devices you own into one cooperative compute fabric, gated by typed capabilities