[FEATURE] Allow Claude to Write/Update Project Files
Preflight Checklist
- [x] I have searched existing requests and this feature hasn't been requested yet
- [x] This is a single feature request (not multiple features)
Problem Statement
Summary
Claude can read project files but cannot write, create, or update them. This creates unnecessary friction in workflows where Claude is actively collaborating on a project. Users must manually download files Claude generates and re-upload them to the project — a tedious workaround that breaks flow and defeats the purpose of having persistent project context.
---
The Problem
Current Behavior
| Action | Supported? |
|--------|------------|
| Read project files | ✅ Yes |
| Create new project files | ❌ No |
| Update existing project files | ❌ No |
| Delete project files | ❌ No |
User Impact
When collaborating with Claude on a multi-session project:
- Session continuity is broken — Claude cannot maintain its own memory/checkpoint files in the project
- Manual file juggling required — Every file Claude generates must be downloaded and manually re-uploaded
- Context fragmentation — Project state lives partially in Claude's project files and partially in user's local/server files
- Workflow interruption — Instead of saying "update the checkpoint," users must download → save → upload → confirm
---
Proposed Solution
Proposed Solution
Allow Claude to write to project files with appropriate safeguards:
Option A: Full Write Access (Preferred)
- Claude can create, update, and delete files in the project
- Changes are immediately reflected in the project
- User can review file history/diffs if needed
Option B: Staged Write Access
- Claude proposes changes to project files
- User sees a diff/preview
- User clicks "Accept" to apply changes
- Similar to how code review works
Option C: Designated Writable Folder
- Project has a special folder (e.g.,
/claude-managed/) that Claude can write to - Other project files remain read-only
- User explicitly opts in to this folder
---
Benefits
- True project continuity — Claude can maintain state across sessions without user intervention
- Reduced friction — No more download/upload cycles for every file change
- Better collaboration model — Claude becomes a real collaborator, not just a read-only consultant
- Enables new workflows:
- Auto-updating documentation
- Progress tracking files
- Generated code that stays in project context
- Test results and logs
---
Security/Safety Considerations
Understandable concerns and mitigations:
| Concern | Mitigation |
|---------|------------|
| Claude overwrites important files | Version history / undo capability |
| Runaway file creation | Quota limits on project file count/size |
| User didn't want the change | Confirmation prompts for destructive operations |
| Accidental data loss | Soft-delete with recovery period |
---
Closing Thoughts
Claude is positioned as an AI collaborator, but the inability to write project files makes it feel more like a read-only advisor. The current limitation forces users into a clunky manual workflow that:
- Wastes time
- Breaks concentration
- Creates version confusion
- Undermines the value of project persistence
For users engaged in multi-session, complex projects — exactly the use case Projects are designed for — this limitation is a significant pain point.
Please consider adding write access to project files.
Written by a frustrated but hopeful user, with help from Claude (who also wishes it could just update the damn file).
Alternative Solutions
N/A
Priority
High - Significant impact on productivity
Feature Category
File operations
Use Case Example
Real-World Example
I'm working with Claude on a multi-day data harvesting project. We created a checkpoint_log.md to track:
- Architecture decisions
- Code changes
- Progress metrics
- Open questions
- Next steps
The ideal workflow:
Me: "Update the checkpoint with today's progress"
Claude: *updates checkpoint_log.md in project*
Done.The actual workflow:
Me: "Update the checkpoint with today's progress"
Claude: "I can't write to project files. Here's the updated content as a download."
Me: *downloads file*
Me: *opens Claude project settings*
Me: *deletes old checkpoint_log.md*
Me: *uploads new checkpoint_log.md*
Me: "Can you see it now?"
Claude: *reads file* "Yes, I can see it."This is 5 extra steps for what should be a single operation.
Additional Context
_No response_
35 Comments
I just wasted several hours on this exact issue and want to highlight the worst part: Claude doesn't know about this limitation.
I asked Claude to update files in my project. Claude used
str_replaceand fixed some encoding issues, showed me the changes, and confidently confirmed the edits were complete. When I couldn't see the updates, Claude told me to refresh my browser, blamed caching issues, and gave contradictory explanations aboutread-onlyfilesystems.All the work was lost. Encoding fixes across 30+ files, CSV updates, hours of data entry, all gone.
The failure mode isn't "Claude can't do this": it's "Claude thinks it did, tells you it did, shows you output proving it did, then silently fails."
This destroys trust. If Claude is wrong about whether it edited a file, what else is it wrong about?
+1 for this feature - this is exactly what I've been looking for!
I want to strongly support this request. The ability for Claude to edit and create files within the Projects workspace would be transformative for my workflow, and I believe the current architecture already provides the perfect security model for implementing this safely.
Why This Makes Sense from a Security Perspective
The key insight is that Projects already operates as an isolated sandbox. When we upload files to a Project:
The original files remain untouched on our local systems or cloud storage (Google Drive, Dropbox, etc.)
Claude only has access to the copies we've explicitly uploaded to the Project workspace
Any modifications Claude makes would be contained within that workspace
We maintain complete control over what gets synced back to our original files
This is actually a safer model than many other AI integrations that request direct access to cloud storage or local filesystems. The Projects workspace acts as a security boundary - Claude can work freely within it, but the "blast radius" of any mistakes or unwanted changes is completely contained.
My Use Case
I frequently work with documents and files that need iterative refinement. Right now, my workflow looks like:
Upload file to Project
Ask Claude to make specific edits
Copy Claude's suggested changes from the chat
Manually apply them to my local file
Re-upload if I need further iteration
This creates significant friction and breaks the collaborative flow. If Claude could edit files directly in the Project workspace, I could:
Iterate quickly on documents without constant copy-paste
Review Claude's changes and download the modified version when satisfied
Keep my original files safe while experimenting with different approaches
Maintain version history within the Project for comparison
The Staged Approach is Perfect
I especially like the "staged write access" idea mentioned in the original post. Having Claude propose changes that I can review and approve before they're finalized would give me confidence while still dramatically reducing friction compared to the current manual process.
Additional Thought: External Sync Tools
As a future enhancement, this architecture would also enable third-party sync tools to integrate with Projects via API. Users could build automated workflows to sync approved changes back to Google Drive or other storage, while still maintaining the security boundary and explicit approval steps.
Bottom Line
This feature leverages the existing Projects infrastructure and actually enhances security by keeping everything in a controlled workspace. It would make Claude significantly more useful for file-based work without introducing the risks associated with direct filesystem or cloud storage access.
Really hoping to see this implemented - it feels like a natural evolution of what Projects already does so well.
Agree totally.
Ability to download the Project files should be an option as well.
Came here looking for this. Yes, please!
omg yes please, it's terrible experience here
I would love to know if this is even being considered, as it is a major friction point. I have ongoing project files and this would allow me to have the project library version be the master version. Easily referenced in a chat with semantic search capability, accessible across desktop and mobile use, and also accessible to Cowork.
I can accomplish this other by other means, but this would be by far the easiest and most direct way possible.
It also encourages me to stay with a Claude-only workflow, so would be an advantage for Anthropic to offer.
I really wish for this feature too. I haven’t been using Claude for long, but having to do changes one at a time, download changed file, delete old file from project, upload new file breaks workflow.
I’ve noticed it more due to writing in python script (new coder, still learning so Claude has been great at explaining things). But it would be nice to have some sort of feature for Claude to update existing files in the project folder. Claude already has a feature to roll back any changes they’ve made if you decide you don’t want them so it wouldn’t be difficult or painful to have this feature.
Was trying to put together a rather large plan. Thought it would be able to keep a single source of truth doc or .md file in the Project, and continuously edit/make changes. Instantly gave up once I realized it can't update the files on its own.
One big issue here is that Claude doesn't appear to even have full read-only access to the actual _files_ in the project libraries, only embeddings- which is generally fine but can itself be limiting.
If full read/write access could be added, that would really be the best of all worlds. I'm guessing their recommendation is to just use desktop app file system tools, though that rules out mobile or web clients.
+1 on this. The core ask is pretty clear: writable project files so Claude can update persistent context across sessions without workarounds. It's a reasonable request given how Projects are positioned as long-running workspaces.
+1 please
+1 on this.
+1
+1 this is honestly a bizarre and insane limitation. So counterintuitive I could not at first believe it was in fact a limitation
+1
+1
+1 on this request.
I want to maintain project summaries during co-design session (NB these are Chat, not Code). We often go backwards and forwards, both proposing alternatives, discounting some, then adding other options. I want to maintain a current summary of our agreed position. But Claude create new file -> delete old file -> Add new to project is awkward and risks error. If you forget to delete the old file, you get two different versions with the same name - so you need delete both and start again.
Saving an updated file is the type of task a regular application can do any day of the week. Imagine Word if it only had "Save as" and you had to manually go to File Explorer to delete the old file and rename the new. That's what working with Claude is like.
+1
Found this while searching for a solution to this maddening issue.
Current use case--Claude Project "AI Binder," creating documentation and reference sources for myself (including to upload as Claude chat refs) on using multiple different AI tools. Creating any one document takes its own chat (at least one), and multiple sessions, so I end sessions with the chat generating a basic log, including next steps, and further details if it's handing off to a new or existing chat. There's no way to keep a single [X] Chat Session Log file that's updated after each work session, let alone a larger Project Log keeping track of progress across [X], [Y], and [Z] chats.
Compounded--working with an institutional Workspace account, chats can only access docs and sheets if I've made them public and editable to anyone with the link, and even then weirdness crops up, so I'm copying from a doc to give the chat content, then copying from the chat to upload the doc, and trying to track versions of the files I'm editing as I go.
Time sink, and major source of AI Brain Fry.
Even just being able to optionally allow edits or creates would improve this feature, every edit I have to re-add the document to the project files and remove the old one.
+1. Project files aren't and should not be static entities. As you work through the project, and the knowledge evolves, that extra context needs to be added to the project files. Otherwise, the project files will become stale very quickly. A project is a dynamic entity that evolves as the work progresses. Treating it, and forcing users to treat it as frozen entity stuck in limbo from the beginning of time defeats the purpose of using projects in the first place. The lack of this feature is fueling the use of obsidian+claude workflows these days. It should tell the anthropic about the how much in demand this feature is.
+1. Without the ability to edit the files in a project. What is the point of a project? I ask this with genuine sincerity. Every time I think to start a project, I realize there is no point because I can't easily change any of the underlining documentation or context. Feels like a big miss and I would love to some priority on this. Even if its not allowing Claude to edit, but at least allowing the user to edit to start.
What @jpwallace22 said - what is the point of a project, which is supposed to be self-contained, if Claude cannot edit the project files? Or, asked differently, what is the purpose of project files, if Claude cannot edit them?
Deleting and uploading a new version each time something changes is a huge pain and using external solutions (file system, notion connector or similar) proves to be extremely unreliable...
If security is the main concern - make it a setting that is turned off by default, or, as others suggested, prompt the user to agree to a change with a diff.
Without this feature projects feel incomplete.
So, I do agree with everyone here, but it also seems that this could help some of you guys:
<img width="280" height="266" alt="Image" src="https://github.com/user-attachments/assets/4ed6f8ce-0181-4da8-9e5d-167f7998b62e" />
+1 - Please implement this or a variation of it. At least when the file is generated, add a dropdown option to update file already in project.
Current workaround I've been using is to keep living files on Drive, but I assume the constant tool use eats up tokens like crazy. Ideally it would just work on the platform itself.
+10000000
Please do this feature, it's basically a shared memory file across all chats in the project, it's a must have feature
When claude told me it was unable to do this I thought it was hallucinating...
Ive just spent an hour migrating all my project instructions and knowledge files from a Claude Chat project into a Claude Cowork project, which does have the ability to write to files, and opens up the use of agents and sub-agents to use connectors too - game changer! Checkout the below Youtube links for more information on how to do this, and setting up a memory file. Hope this helps!
https://www.youtube.com/watch?v=pl90LATQlHI
https://www.youtube.com/watch?v=ib74sLgjIBM
@mike-hill-certus while cowork does have the ability to do this (which is very good), it is not portable. The feature request here still remains completely valid for workflows involving users who move between Claude desktop and Claude on their phone frequently. And yes, I realise the dispatch feature does allow you to send off tasks to the cowork project from your phone, but this is really clunky workflow compared to a simple cloud-based project in Claude chat with persistent, mutable files.
+1 for the original feature still being implemented.
I completely agree @tony-cox I wanted to share my expereince so that it might help some folks in their use case. Theres defnitely a need for this feature still, 100% :)
I have spent at least 20 hours doing tests to understand the way the container filesystem works a d designing work arounds for this in claude chat - systems of tracking version numbers in files and detecting collisions and merging of edits by multiple sessions on same file.
YEs, please. It is madness from a user point of view, that this cannot be done. Use-case, a friend is trying to track their food intake, seems like with a photo and some description Claude can aprox. figure out the values for a meal quite well. So I thought: I give them 1 week, they create a project on the phone app, then everytime they eat something, they send a picture with brief text to that project, Claude has instructions to add its evaluation of the meal to a table in an md in the project folder, and that's all. AFter the week they have a good estimate of their habits and what can be changed. But Claude cannot do this, as it cannot edit project files omg, only create new ones that they should then upload to project via contextual menu as a lowest friction point. They can install cowork and do it locally, but then they need a way to send the images from their phone to cowork, because there is no web link, etc. Any workaround is a drag that makes this much more annoying for them on a daily basis. Probably won't invite them.
You can do that, Claude can edit his own work files, then link it to you.