Who it is forA developer using Claude Code, Codex or Cursor on a repository who wants the agent to find code and decisions without searching blindly.
The problemA coding agent has to search the repository from scratch each time, and project docs and past decisions are scattered across files and sessions.
The outcomeThe agent calls Graphicle's tools and gets relevant code, docs and decisions as excerpts with file names and line numbers.
What you need first
- A local Git repository with the code you want to index
- Homebrew, or the install script from the Graphicle README, to install the program
- A terminal on macOS or Linux, or the Windows preview build for x86-64
- A coding agent that supports MCP, such as Claude Code, Codex or Cursor (optional, for agent use)
Steps
- Run
brew install graphicle-ai/tap/graphicle(or use the install script from the README if you do not use Homebrew). - Open a terminal in your repository and run
cd your-repo. - Run
graphicle setupand read the list of files it changed; it backs each one up first. - Ask your agent: "use Graphicle to find where failed requests are retried".
- Run
graphicle doctorif the agent does not see the Graphicle tools.
Prompt for your agent
In the Graphicle-AI/graphicle repository's setup, run `graphicle setup --yes` in <repo-path>, then list every file it changed. Expected output: a list of changed files and a confirmation that the Graphicle MCP server is connected. Verify by asking the agent to use graphicle to find <topic> and checking that the answer cites file names and line ranges.
Caveat. Setup edits agent configuration files and Git hooks, so review the list of changed files it prints, and remember that `graphicle disconnect` undoes what it added.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page