Initial scaffold: GyanDoot v2.0 in Rust

Full Cargo workspace with 11 crates:
- gyandoot-core: Shared types, config, error types
- gyandoot-agent: Agent loop, tool execution, context compression
- gyandoot-providers: LLM provider abstraction (OpenAI, Anthropic, Ollama)
- gyandoot-memory: MemPalace persistent memory system
- gyandoot-platform: Platform adapters (Telegram, Discord, Webhook, CLI)
- gyandoot-security: Credential vault, sanitizer, threat detector
- gyandoot-kanban: Task decomposition, swarm orchestration, diagnostics
- gyandoot-subagents: Sub-agent spawning and orchestration
- gyandoot-skills: Skills discovery, loading, preprocessing, bundles
- gyandoot-profile: Multi-agent profile manager
- gyandoot-gateway: Gateway sessions, routing, access control

Plus: CLI entry point with clap, cross-platform installer script,
KANBAN.md, .gnpl/AGENTS.md

Workspace compiles clean: cargo check passes with 0 errors.

crates/gyandoot-agent/src/lib.rs

@@ -0,0 +1,13 @@
+//! GyanDoot Agent — Core agent loop, tool execution, context compression.
+//!
+//! This crate implements the main agent inference loop: receiving messages,
+//! invoking LLM providers, executing tool calls, compressing context when
+//! needed, and interacting with memory.
+
+pub mod agent_loop;
+pub mod tools;
+pub mod context;
+
+pub use agent_loop::AgentLoop;
+pub use tools::ToolExecutor;
+pub use context::ContextCompressor;