Give coding agents a local code graph and project memory with cited excerpts
Graphicle maps your repo into a code graph, remembers docs, decisions and past agent sessions, and hands Claude Code, Cursor or Codex the exact files and lines. It runs locally with no API key, account or telemetry.
Source
KarLexAI on Hacker News · 2026-10-14 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-16.
What they did
Graphicle maps your repo into a code graph, remembers docs, decisions and past agent sessions, and hands Claude Code, Cursor or Codex the exact files and lines. It runs locally with no API key, account or telemetry.
Result (as claimed)
Open source (Apache-2.0); 47 points on Show HN.
Tools they used
Cost: Claude Code: free plan, paid from $17/mo; Cursor: free plan, paid from $8/mo; OpenAI Codex: free plan, paid from $8/mo. Checked 2026-10-14.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code, Cursor, OpenAI Codex. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Give coding agents a local code graph and project memory with cited excerpts What the original author did: Graphicle maps your repo into a code graph, remembers docs, decisions and past agent sessions, and hands Claude Code, Cursor or Codex the exact files and lines. It runs locally with no API key, account or telemetry. Reported result (as claimed by the author): Open source (Apache-2.0); 47 points on Show HN. Source: https://news.ycombinator.com/item?id=50088713 Tools they used: Claude Code, Cursor, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Give coding agents a local code graph and project memory with cited excerpts What the original author did: Graphicle maps your repo into a code graph, remembers docs, decisions and past agent sessions, and hands Claude Code, Cursor or Codex the exact files and lines. It runs locally with no API key, account or telemetry. Reported result (as claimed by the author): Open source (Apache-2.0); 47 points on Show HN. Source: https://news.ycombinator.com/item?id=50088713 Tools they used: Claude Code, Cursor, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Give coding agents a local code graph and project memory with cited excerpts What the original author did: Graphicle maps your repo into a code graph, remembers docs, decisions and past agent sessions, and hands Claude Code, Cursor or Codex the exact files and lines. It runs locally with no API key, account or telemetry. Reported result (as claimed by the author): Open source (Apache-2.0); 47 points on Show HN. Source: https://news.ycombinator.com/item?id=50088713 Tools they used: Claude Code, Cursor, OpenAI Codex Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Related use cases
Give coding agents a disposable Linux VM instead of your laptop
Built Clawk so coding agents run in a disposable Linux VM rather than directly on your machine.
Run coding agents side by side with shared memory, undo and phone access
Pando runs Claude Code, Codex, Grok and Cursor side by side with one shared memory, undo for any task, tests after every change and vibe coding from your phone.
Watch all your coding agents in a calm pixel room on your Mac
Shrine shows what your Claude Code, Codex, OpenCode, Cursor and Grok Bot sessions are doing on your Mac; pushes and merged PRs furnish a small pixel room.
Run up to 16 coding agents side by side
Built SwarmPane to run Claude Code, Codex, Gemini, Grok and Cursor in parallel panes with attention cues.