Run full AI agents on any machine, model, and runtime — steer them all from one nest.
Open tools for agent fleets — plus the odd neural renderer and translation model.
Run full AI agents on any machine, model, and runtime — steer them all from one nest.
Open tools for agent fleets — plus the odd neural renderer and translation model.
Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.
The ultimate free AI integration for Unreal Engine 5 — 158 tools via Model Context Protocol
Shared memory for AI agent swarms. Knowledge graphs, semantic search, LLM extraction, real-time channels — all Raft-replicated
Rust 6
Google Stitch plugin for Claude Code — design UIs, capture screenshots, pull designs as components
Post-quantum stateless Sphinx mixnet. Hybrid X25519+ML-KEM-768 per-hop KEM, fixed-size 32KB packets, Loopix Poisson mixing, SURB replies, blind-token guard auth, TCP transport. Research prototype.
Zero-trust multi-hop onion VPN with blind token authentication. 1.4MB relay binary, ~5MB RAM. Random N-hop circuits, onion encryption, Noise transport.
Round-trip PII redaction proxy for Claude Code. Replaces names/emails/secrets with deterministic tokens before the API sees them; restores real values in the response. ~12ms/string.
Shared memory for AI agent swarms. Knowledge graphs, semantic search, LLM extraction, real-time channels — all Raft-replicated
Drop-in AI gateway. Route any coding agent through any LLM provider. Auto-failover, Anthropic<->OpenAI format conversion, 15 PII guardrails, multi-tenancy, multiple subscription support.
Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.
Multi-persona phone OS for Pixel 9/10 - hardware-isolated Android personas via pKVM, with a Cuttlefish-based dev loop
Loading…
Loading…