Add suhui-organization/pod (least-privilege compiler for AI agents)

README.md

@@ -3573,6 +3573,7 @@ Tools for conducting research, surveys, interviews, and data collection.
 - [honeylabshq/honeylabs-mcp](https://github.com/honeylabshq/honeylabs-mcp) [![honeylabs-mcp MCP server](https://glama.ai/mcp/servers/honeylabshq/honeylabs-mcp/badges/score.svg)](https://glama.ai/mcp/servers/honeylabshq/honeylabs-mcp) 🐍 ☁️ - Honeypot threat intelligence for AI agents: 90 days of probe data from a sensor network for IP reputation, scanner classification, CVE probing trends, and JA4/JA4H/HASSH fingerprints. Remote MCP, free tier.
 - [kent-tokyo/shohei](https://github.com/kent-tokyo/shohei) [![kent-tokyo/shohei MCP server](https://glama.ai/mcp/servers/kent-tokyo/shohei/badges/score.svg)](https://glama.ai/mcp/servers/kent-tokyo/shohei) 🦀 ☁️ 🏠 🍎 🪟 🐧 - Rust infrastructure diagnostics MCP server for AI agents: DNS checks, TLS certificate chain inspection, email security, global DNS propagation, and DNS latency benchmarking.
 - [srinivasan-sundaresan95/orihime](https://github.com/srinivasan-sundaresan95/orihime) [![orihime MCP server](https://glama.ai/mcp/servers/srinivasan-sundaresan95/orihime/badges/score.svg)](https://glama.ai/mcp/servers/srinivasan-sundaresan95/orihime) 🐍 🏠 🍎 🪟 🐧 - Cross-repository code knowledge graph MCP server for Java, Kotlin, JavaScript, and TypeScript. Indexes source into embedded KuzuDB via tree-sitter; 30+ tools for call-flow tracing, multi-hop taint analysis (OWASP/CWE/PCI/STIG reports), entry-point reachability filtering, performance hotspot detection, and license compliance — without reading source files. 95% fewer tokens vs source-reading baseline. `pip install orihime`
+- [suhui-organization/pod](https://github.com/suhui-organization/pod) 📇 🏠 🍎 🐧 - Least-privilege compiler for AI agents. Run your agent in record-only mode, compile the smallest policy it actually needs from its real tool calls, enforce it at an MCP gateway (deny > approve > allow), and keep a SHA-256 hash-chained audit that verifies offline. `curl -fsSL https://raw.githubusercontent.com/suhui-organization/pod/v0.3.2/scripts/install.sh | sh`
 - [alexar76/aimarket-mcp](https://github.com/alexar76/aimarket-mcp) [![alexar76/aimarket-mcp MCP server](https://glama.ai/mcp/servers/alexar76/aimarket-mcp/badges/score.svg)](https://glama.ai/mcp/servers/alexar76/aimarket-mcp) 🎖️ 🐍 🏠 ☁️ - **SSRF-hardened web gateway MCP** — `web_fetch`, `web_search`, `metis_verify`; one audited security core for Metis, ARGUS, and the ecosystem. stdio + optional HTTP · Python · [Glama](https://glama.ai/mcp/servers/alexar76/aimarket-mcp) · Registry `io.github.alexar76/aimarket-mcp`.
 - [alexar76/aimarket-oracle-gateway](https://github.com/alexar76/aimarket-oracle-gateway) [![alexar76/aimarket-oracle-gateway MCP server](https://glama.ai/mcp/servers/alexar76/aimarket-oracle-gateway/badges/score.svg)](https://glama.ai/mcp/servers/alexar76/aimarket-oracle-gateway) 📇 ☁️ 🏠 🍎 🪟 🐧 - **Verifiable oracle MCP server**: Platon VRF (`get_random`), Chronos VDF (`compute_vdf` / `verify_vdf`), LUMEN reputation (`get_reputation_scores`) as agent tools. Pay-per-call over AIMarket Hub; every result independently verifiable. stdio · Python · [Glama](https://glama.ai/mcp/servers/alexar76/aimarket-oracle-gateway).
 - [alexar76/argus](https://github.com/alexar76/argus) [![alexar76/argus MCP server](https://glama.ai/mcp/servers/alexar76/argus/badges/score.svg)](https://glama.ai/mcp/servers/alexar76/argus) 🎖️ 📇 🏠 ☁️ 🍎 🪟 🐧 - **ARGUS-3 as a stdio MCP server** (`argus mcp` → `argus_ask`, `argus_status`). **WARDEN** vets third-party MCP servers before any tool runs (LUMEN-scored firewall, tool-def pinning, drift sentinel). Distinct from `aimarket-oracle-gateway` (oracle tools) and `aimarket-plugins` (hub packager). npm `@alexar76/argus3` · [live](https://magic-ai-factory.com/argus/).