✨ Why agentic-stack?
Most "AI skills" are a single clever prompt. These are full multi-agent pipelines with the engineering that separates a demo from a tool:
- 🧪 Evidence in, judgment out. Research runs split evidence-gathering (parallel sub-agents) from judgment (a deterministic Python scoring engine for product decisions, an adversarial red-team for research). The conclusion is grounded — not vibes, not a hallucinated ranking.
- 🔁 They get smarter.
ultradeep writes a transferable lesson back into its own program.md after every run. Your tooling compounds.
- 🗂️ They compound into a knowledge base. Reports file themselves into an optional Obsidian wiki, cross-linked and searchable next time.
- 🛡️ Privacy-first by design. Ships the engine, never your data. No secrets, no personal content — your wiki/memory start as empty scaffolds.
- ⚡ Zero-to-running in one command. An interactive installer wires the free MCP servers and asks what you want. Required pieces are free and key-less.
Built by @justsima — the agentic research workflow behind real deep-research, buying decisions, and high-stakes calls, packaged so you can run it too.
How it compares
| Single-prompt "skill" | Vanilla Claude Code | agentic-stack |
|---|
| Multi-agent fan-out | ❌ | ⚠️ manual | ✅ |
| Adversarial red-team verification | ❌ | ❌ | ✅ |
| Deterministic scoring — no hallucinated rankings | ❌ | ❌ | ✅ |
| Self-learning across runs | ❌ | ❌ | ✅ |
| Files into a knowledge base | ❌ | ❌ | ✅ |
| One-command install + MCP wiring | — | — | ✅ |
| Privacy-first — ships the engine, not your data | — | — | ✅ |
🧩 The plugins
