How they fit together
ChatGPT Projects holds your context. Riflet builds the file you put in it. The Project handles persistence and organization. The slow part is collecting scattered sources and deciding what actually belongs, and that is what Riflet is for.
These are not competing tools. ChatGPT Projects is built by OpenAI and is where your context lives. Riflet is a local-first desktop app that assembles that context from mixed sources and exports it as one portable file. You use both.
Who does what
| Task | Riflet | ChatGPT Projects |
|---|---|---|
| Collecting sources from repos, sites, vaults, and folders | Connects to each source type and pulls the files together in one workspace. | Not part of what it does. It receives files you already have. |
| Choosing what the AI should and should not see | Visual file tree, preview, ignore patterns, and saved filter presets. | You decide at upload time, one file at a time. |
| Reading PDFs, DOCX, XLSX, and PPTX into clean text | Parses them locally into Markdown and fenced code blocks. | Handles common documents directly once uploaded. |
| Knowing the size of the context before you use it | Live token count against the selected model window, before export. | You find out once the files are in place. |
| Keeping context available across chats | Not its job. Riflet produces the file and stops there. | This is exactly what Project files are for. |
| Using the same context in Claude or Gemini too | The exported file is plain text, so it uploads anywhere. | Project files stay inside ChatGPT. |
What ChatGPT Projects does well
- Project files persist across every chat in the project, so context survives past a single conversation.
- Chats stay grouped by project, which keeps long-running work from getting lost in your history.
- Project instructions apply to every conversation inside the project.
- It is the right home for your context if ChatGPT is where you do the work.
What it leaves to you
- It does not gather sources. A repository, a documentation site, an Obsidian vault, or a Notion export has to become files before it can be uploaded.
- Uploads and updates are manual. When the underlying sources move on, you replace the files yourself.
- There is no view of what your context costs in tokens before it is in place.
- Project files stay in ChatGPT. Using the same context in Claude or Gemini means preparing it again.
Building the file in Riflet
Add your sources in Riflet
Local folders, a public or private GitHub repository, a web page or full sitemap, an Obsidian vault, or a Notion export can all sit in the same workspace.
Select exactly what belongs in the project
Browse the file tree, preview files, and apply ignore patterns or an imported .gitignore so build output and dependencies never reach the upload.
Check the token count before you export
The live token count tells you how large the bundle is against your model's context window while you can still trim it down.
Export one file and add it to Project files
Export a single .txt or .md, open your ChatGPT Project, and upload it. One structured file is easier to keep current than a dozen separate ones.
Build your Project files file with Riflet
Combine files, folders, repos, websites, PDFs, Office docs, and notes into one context file, then upload it where you already work.
Download Riflet freeFrequently asked questions
Do I still need ChatGPT Projects if I use Riflet?
Yes. Riflet assembles and trims the context file. The Project is where that file lives so every chat in it starts with the same background. Riflet has no chat interface and does not talk to a model.
Does Riflet sync automatically into ChatGPT Projects?
No. Riflet creates the export and you upload it. When your sources change, you re-export and replace the file. A saved workspace makes the re-export a one-click step, but the upload is still yours to do.
Is one big file better than uploading many small ones?
Usually yes, for upkeep. One structured export with clear file path separators is a single thing to replace when sources change, instead of tracking which of a dozen uploads is now out of date.
Can I upload the same file to Claude or Gemini?
Yes. The export is plain text, so the same bundle works in Claude Projects, Gemini Gems, Perplexity, and local models without being rebuilt for each platform.