Search

Cambium — a bounded-agent behavioral coherence engine. The deterministic spine decides what to ask. The model only answers. The eval framework decides whether the answer counted.

Hugging Face Space: ai-antenna-design-tool

Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...

A persistent roster of Claude specialists, dispatchable on tickets across your projects.

Cross-agent AI work digest — reads sessions from Hermes, Codex, Claude Code, Copilot CLI, and more. Outputs value reports with effort estimates and ROI.

Knowledge-base readiness validation for RAG & AI agents — config-driven, deterministic pipeline integrity checks.

DEER - Deterministic Executable Engine for Runtime-agents

LLM-based gray-zone verifier for axor-core anomaly detection

LLM application: 🖼️ Generative UI and Agentic Frontends

LLM application: 🗂️ Generative UI Starter Project

LLM application: 🪙 AI Financial Coach Agent

LLM application: 📊 AI Dashboard Canvas Agent

LLM application: 🛠️ AI MCP App Builder

LLM application: ✈️ MCP Apps Generative UI Showcase

LLM application: 🎛️ AI Shadcn Component Generator

APOHARA: Context Forge — Silicon-native KV cache coordination for multi-agent LLM pipelines on AMD Instinct MI300X. Now ships with a slim safety-only install path.

Apohara ContextForge plugin for vLLM V1 — multi-agent KV-cache coordination, JCR Safety Gate (INV-15), RotateKV INT4 hooks, on AMD Instinct MI300X.

Drop-in replacement for claude-agent-sdk that adds a proxied telemetry pipeline (PII redaction + guardrails) with OpenTelemetry and AgentOS sinks.

Counterfactual replay and causal attribution over LLM-agent trajectories: find which step actually caused a bad outcome by intervening on it.

Agent Evidence Layer — turns AI-agent runtime behavior into signed, tamper-evident, control-mapped audit evidence.