Merged. Fixed agent name preservation in AgentExecutor node titles after page reload in the visual builder frontend. Small fix, surfaces in the user flow every time you reopen a saved graph, so the regression was high-visibility once introduced.

Open, under review. Replaces the naive E[X²] − E[X]² variance formula in PearsonCorrelation with Welford's online algorithm plus a parallel distributed merge. Fixes catastrophic cancellation in float32 (the metric was returning 0.89 instead of 0.99 for mean=1e6 data). Numerically stable across single-process and DDP.

An open source cybersecurity language model built from scratch in PyTorch. 81M parameter decoder-only transformer (RoPE, SwiGLU, RMSNorm) trained on a 422M token multi-domain corpus across 27 sources: cybersec writeups, NVD CVEs, MITRE / CWE / OWASP, NIST SP 800, FineWeb-Edu, open-web-math, and a 105 repo open source code pull spanning 15 languages.

Ships GhostAgent (a tool-using runtime), a multi-vendor HTTP server speaking OpenAI / Anthropic / Gemini / Ollama wire formats, an MCP server, and GhostBench (a packaged eval suite with Wilson 95% CIs and McNemar paired comparisons across 14 differentiation bets). 312 tests green.

AI agent safety stack: secure-mcp, ghostguard (4-tier policy proxy with audit dashboard), CyberBench

Defensive security toolkit: ghostaudit (23 CIS Kubernetes checks), ghostforensics (memory forensics with YARA + Volatility + STIX 2.1 export), ghostsiem (Sigma-rule SIEM), securecommit (pre-commit secret scanner)

Offensive tooling: concurrent TCP port scanner, packet-level traffic analyzer, vulnerability scanner, hash-cracking framework, MAC rotator, metadata scrubber

Full-stack platforms: Complex Developers CRM (Next.js 15 + Prisma + Postgres), ChartSentinel (trading SaaS with Stripe + PostHog + Sentry), High-End CRM, ai-coding-assistant

ghostloop v1.0.3 — the agent loop, embodied. pip install ghostloop, 14 releases, live HuggingFace demo, full CI/CD with PyPI Trusted Publishing. Six simulation backends (MuJoCo / PyBullet / Gymnasium / ROS 2), 12 fail-closed policy gates, LLM + VLA policy adapters, and a bench harness with Wilson CI, McNemar, adversarial fuzzing (CMA-ES), STL temporal properties, counterfactual replay, and causal failure attribution. Production fleet dashboard with auth, rate limiting, alarms, and Prometheus. 359 tests green.

ghostloop-ui — Next.js 15 + React 19 + Tailwind 4 control plane, live at ghostloop-ui.vercel.app. Fleet view, alarm tray, episode timeline, per-counter Prometheus metrics, and a profile-aware gamepad mapper (drone / mobile base / quadruped / arm / humanoid) built for non-coders. Demo-mode fallback keeps the deploy interactive with no backend configured.

ghostloop-desktop v0.2 — Tauri 2 + Rust shell wrapping ghostloop-ui as a single-file native app for macOS / Windows / Linux. Voice control, gamepad rumble on safety events (geofence block, force-cap trip, e-stop), native OS notifications, 120 Hz gamepad polling via gilrs, system-tray integration, and a global e-stop hotkey. Per-PR CI matrix green across all three platforms.

secure-mcp — MCP server exposing security tools to AI agents with policy gates, subprocess sandboxing, and audit trails. Fail-closed by default.

CyberBench — Open, reproducible benchmark for evaluating LLMs on cybersecurity reasoning. YAML tasks, pluggable backends, ranked leaderboard.

linkdrop v0.7.1 — Cross-platform Tauri + Rust desktop app bridging iPhone to Linux for photos, files, notifications, screen mirroring. Daemon-backed pymobiledevice3 bridge, CI-built .deb / .AppImage.