Enables AI coding agents to query a locally indexed codebase graph for symbol definitions, immediate callers and callees, and multi-hop downstream dependency impact analysis through MCP tools.

Enables Claude Code and Codex to write, update, and retrieve durable long-term memories that survive session boundaries and context compaction. All recall runs locally against a single SQLite file using hybrid BM25, embedding, and recency ranking cut to an explicit token budget, with no cloud dependency.

Enables AI agents to query a Python codebase as a knowledge graph over MCP, exposing symbol search plus callers, callees, and module dependency tools.

Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.