ix-infrastructure/Ix

Understand any codebase instantly. System intelligence for codebases, built for humans and AI.

What it solves

Ix addresses the difficulty of understanding large, complex codebases. Instead of relying on simple text searches (grepping) or pasting entire files into an AI prompt, Ix creates a structured, persistent map of a repository's architecture to allow for precise querying of symbols, calls, and relationships.

How it works

Ix uses tree-sitter to parse a repository and extract symbols, calls, and imports. This data is stored as a graph in a local backend consisting of ArangoDB and a memory layer running in Docker. Users and AI agents can then query this graph via a CLI, a visualizer called Compass, or an MCP (Model Context Protocol) server that integrates with AI coding assistants like Claude Code, Cursor, and VS Code.

Who it’s for

Software engineers and AI coding agents who need to navigate, analyze, and understand the structural relationships within a codebase without losing context between sessions.

Highlights

  • Persistent System Graph: Maps the codebase once and stores it locally, preventing the need to re-derive architecture in every session.
  • Structural Querying: Provides commands to explain symbols, trace execution flows, and determine the "blast radius" (impact) of changes.
  • AI Agent Integration: Ships with an MCP server and specific "skills" to allow LLM agents to navigate the graph directly.
  • Coded-based Token Efficiency: Reduces token usage by 30-99.7% by providing bounded structural slices instead of full files.
  • Broad Language Support: Supports 27 languages, including CUDA, Rust, Go, and TypeScript.

Related

  • Project
    zzet/gortex

    A high-performance code-intelligence engine that indexes codebases into a knowledge graph to provide AI agents with precise context, reducing token usage by up to 50x.

  • Project
    CodeGraphContext/CodeGraphContext

    A toolkit and MCP server that indexes local code repositories into a graph database to provide AI agents and developers with structural context like call chains and class hierarchies.

  • Project
    DeusData/codebase-memory-mcp

    A high-performance code intelligence engine that builds a structural knowledge graph of codebases to provide AI agents with efficient, low-token access to architectural insights.

  • Project
    Lyellr88/marm-memory

    A persistent local memory server for AI agents using the Model Context Protocol (MCP), providing shared context, code graphs, and concept graphs across sessions.

  • Project
    akitaonrails/ai-memory

    ai‑memory is a Rust‑based server that records every observation a coding‑assistant makes (prompts, tool calls, session boundaries) as plain markdown files in a git‑backed wiki. The server can be run locally, in Docker/Podman, or on a homelab box and is designed to be shared across many agents (Claude Code, Codex, Cursor, Gemini CLI, etc.), machines and team members. Hooks posted by agents are consolidated into readable wiki pages at session end; the next session receives a concise handoff so it can continue exactly where the previous one stopped. Storage is human‑readable markdown plus a SQLite index (FTS5, entity and optional vector search). By default it needs no LLM or embedding keys; optional Anthropic/OpenAI integrations add LLM‑generated summaries and semantic search. Multi‑user authentication, audit logs and per‑person attribution are built in. Install via Arch AUR, Docker wrapper, or native binary, start the server, register a client and its hooks, and the system works transparently.