NeuroSploit v3.3.0 — Autonomous MD-Agent Engine

Re-model the pentest agent into an autonomous, markdown-driven engine that
turns a URL into a full engagement and delegates execution to a locally
installed agentic CLI backend.

Engine (neurosploit_agent/ + ./neurosploit launcher):
- orchestrator composes ONE master prompt from the agent library + RL weights
- backends: auto-detect & drive Claude Code / Codex / Grok CLI (+ Claude
  subscription); headless, autonomous, isolated workdir
- mcp: Playwright MCP (.mcp.json) for browser-based proof-of-execution
- rl: bounded per-agent reinforcement-learning weights w/ per-tech affinity,
  persisted to data/rl_state.json
- models: latest registry incl. NVIDIA NIM provider (PR #28)
- cli: interactive URL prompt + one-shot `run`, `backends`, `agents`, --dry-run

Agent library (agents_md/, 213 total):
- 196 vuln specialists incl. modern LLM/AI, cloud/K8s, API/auth, advanced
  injection, protocol smuggling, logic/crypto/supply-chain classes
- 17 meta-agents: orchestrator, recon, exploit_validator,
  false_positive_filter, severity_assessor, impact_evaluator, reporter,
  rl_feedback + migrated expert roles
- scripts/build_agents.py data-driven builder; REGISTRY.md index

Docs: rewritten README.md, v3.3.0 RELEASE.md, .env.example (NVIDIA NIM, xAI,
engine vars).

Retire legacy Python orchestration (neurosploit.py + agent classes) to legacy/.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.env.example

@@ -20,6 +20,13 @@ GEMINI_API_KEY=
 # OpenRouter (multi-model): https://openrouter.ai/keys
 OPENROUTER_API_KEY=
 
+# xAI Grok: https://console.x.ai/  (used by the Grok CLI backend)
+XAI_API_KEY=
+
+# NVIDIA NIM (PR #28): https://build.nvidia.com/  — keys look like `nvapi-...`
+# OpenAI-compatible endpoint at https://integrate.api.nvidia.com/v1
+NVIDIA_NIM_API_KEY=
+
 # Together AI: https://api.together.xyz/settings/api-keys
 TOGETHER_API_KEY=
 
@@ -155,3 +162,21 @@ DATABASE_URL=sqlite+aiosqlite:///./data/neurosploit.db
 HOST=0.0.0.0
 PORT=8000
 DEBUG=false
+
+# =============================================================================
+# NeuroSploit v3.3.0 — Autonomous MD-Agent Engine
+# =============================================================================
+# The engine delegates execution to a locally-installed agentic CLI backend.
+# Default backend (claude | codex | grok). First installed is used if unset.
+NEUROSPLOIT_BACKEND=claude
+# Default provider/model (see neurosploit_agent/models.py)
+NEUROSPLOIT_PROVIDER=anthropic
+NEUROSPLOIT_MODEL=claude-opus-4-8
+# OOB collaborator host for blind/SSRF/XXE proof (optional)
+NEUROSPLOIT_COLLABORATOR=
+# Reinforcement-learning loop (1=on). State persists to data/rl_state.json
+NEUROSPLOIT_RL=1
+# Playwright MCP for browser-based proof of execution (1=on; needs npx)
+NEUROSPLOIT_MCP=1
+# OpenAI-compatible base URL override (set automatically per provider)
+#OPENAI_BASE_URL=