Codebase context builder
Turn large repositories into clean prompt context without losing structure.
CodePiler gives you a controlled workspace for importing a repository, choosing the exact files that matter, and exporting AI-ready output in the format your workflow already uses.
Prompt workspace
Import, filter, select, export
Client-side
01
Upload project folder or ZIP02
Filter by file type or sort by size03
Select files — tokens shown inline04
Save selection, export & resume laterReadable context
Structure selected files into one prompt. Token counts show inline on every file so you always know your context size.
Noise reduction
Filter by file type or sort by size. The size manager lets you bulk-deselect heavy files in seconds.
Ready to export
Switch between Text, JSON, XML, and Markdown instantly. Save your selection and reload it later without re-uploading.
Built for focused prompt prep
The product is already a usable repository-to-prompt workspace.
The strongest part of CodePiler today is the core workflow: import code, inspect structure, control the selection set, and produce clean output fast.
Selective file control
Browse the repository tree and include exactly the files the prompt needs.
Format switching
Move between plain text, JSON, XML, and Markdown without rebuilding context.
Token awareness
Estimate prompt size before you send it to ChatGPT, Claude, or another model.
Local-first handling
Repository files stay in the browser workflow instead of being pushed to a backend.
Per-file token counts
See token usage inline on every file and folder in the tree — no guesswork on what's big.
File type filtering
Filter the tree by extension in one click. Narrow to only .ts, .py, or any combination.
Size manager
View all files sorted by size or token count, then bulk-select or deselect the heavy ones.
Saved sessions
Save your repo and selection to localStorage and restore it later — no re-uploading needed.
Real impact
Less noise. Lower cost. Faster AI workflows.
Token usage directly maps to API cost and latency. Codepiler cuts both by giving you surgical control over what enters the prompt — before the LLM ever sees it.
90%
Fewer tokens sent
Precise file selection keeps prompts lean. Sending 15 targeted files instead of a full 300-file repo cuts token usage by 90%+ in typical workflows.
0
Re-upload time
Saved Sessions lets you restore any previous repository and selection instantly. No ZIP drag-and-drop, no re-filtering — the workspace opens exactly where you left it.
10×
Faster context prep
Assembling context manually takes 10–30 minutes per session. Codepiler compresses that to under 60 seconds: upload, filter, select, export.
Skip
AI read_file calls
AI coding agents (Cursor, Copilot, custom MCP tools) make repeated read_file calls to understand a codebase. Pre-pack the right files once and the agent skips those round-trips entirely.
Cost calculation
Sending a full repository vs. a curated selection
A 300-file TypeScript project typically contains ~500K tokens. At GPT-4o rates ($5 / 1M input tokens), one full-repo prompt costs ~$2.50. With Codepiler you send 20–40 relevant files (~40K tokens) — the same task costs ~$0.20. That is a 12× cost reduction per prompt, compounding across every AI session.
Full repo prompt~$2.50
Codepiler selection~$0.20
Saved per call~$2.30
Based on GPT-4o $5/1M token input pricing. Savings scale with usage frequency and model tier.
Workflow
A simple pipeline for turning source code into LLM-ready context.
The UX should feel operational, not decorative. Each step strips away manual copying and keeps the context explicit.
01
Import repository files
Upload a project folder or ZIP. Binary files, generated directories, and files over 200 KB are automatically excluded — no manual cleanup needed.
02
Filter, sort, and select
Use the file-type filter to narrow by extension, sort by token count or size to find the heavy hitters, and check exactly the files that matter. Token counts show inline on every file and folder.
03
Generate and export
Preview the assembled prompt in Text, JSON, XML, or Markdown. Verify the total token count, then copy or download. Save the selection to resume the same context later without re-uploading.
Use cases
Built for developers who need cleaner context, not just a larger prompt.
The value is not only aggregation. It is choosing the right subset of the repository and preserving structure while doing it.
1
Explain an unfamiliar codebase to an LLM in one prompt — no ad hoc copy-paste, no missed files.
2
Prepare focused debugging context by selecting only the affected modules and their direct dependencies.
3
Feed an AI agent a precise context package so it skips repeated read_file calls and starts productive immediately.
4
Save your selection for recurring workflows — re-open the same context next session without re-uploading the repository.
5
Reduce API cost by 10–90× by sending only the files that matter instead of an entire repository.
6
Package source files for documentation, onboarding prompts, or code-review summaries with a single export.
Ready to use
Open the workspace and generate structured context from your repository.
The current product already covers the core path. The next step is polishing the edges, not inventing the workflow.