Guide · Go
Understand a large Go codebase — fast
Go keeps files small and packages flat, which is great to write and disorienting to read — a service can be forty tiny packages whose relationships live only in import statements. Reading files top to bottom doesn't scale; what scales is a map: every file, symbol, import, and call, ranked by what actually matters, navigable instead of imagined.
Map the repository in seconds
Paste the GitHub URL into the OpenVisio web app and the repository is fetched and indexed entirely in your browser — nothing uploaded, no account for your first map. For private work, the CLI (npm install -g openvisio) indexes any local folder the same way.
Indexing is deterministic — tree-sitter parses the repository into files, symbols, imports, and calls, and PageRank ranks what matters. No LLM ever sees your code during indexing, nothing is uploaded, and the whole thing runs on your machine.
What the map shows in a Go project
The city view turns those forty packages into districts you can see at a glance, import arcs show how they layer, and PageRank surfaces the handful of packages everything else routes through.
Four views on one graph: a 3D city (folders are districts, files are buildings sized by lines of code and colored by hotness), an atlas constellation of symbols, and architecture and folder dependency views. Filter by language, folder, or recently changed.
Ask, and get cited answers
The narrator explains the architecture and traces any flow in plain words, and every claim carries a path:line citation — touch it and the file lights up on the map. It is grounded in the deterministic graph, not free-form generation.
Give your AI agent the same map
The graph you explore is the same one served to coding agents over MCP — Claude Code, Cursor, Codex. Once connected, the agent has six structured queries instead of blind file reads: resolve_context (a task-ranked skeleton plus the relevant neighborhoods, every line with a path:line anchor), find_symbol, get_dependents, get_neighborhood, get_hotspots, and get_repo_skeleton. Discovery stops being a token sink and becomes a lookup.
Frequently asked questions
Does OpenVisio support Go?
Yes — Go is parsed natively via its tree-sitter grammar, alongside 40+ other languages, so polyglot repositories map as one graph.
Do I need to install anything to try it?
No. Paste a public GitHub URL into the web app and the map builds in your browser. The CLI install is only needed for private local repos and the MCP server.
How is this different from an IDE's "find usages"?
Find-usages answers one symbol at a time. The map answers repository-scale questions — where the complexity lives, what is load-bearing, how the top-level pieces depend on each other — and ranks it all with PageRank so the important files stand out.
Watch it map gin — right now
One click — the map builds in your browser in seconds. No install, no account, nothing uploaded.
Map ginor npm install -g openvisio for the MCP server