context-attachment-manager
A local plugin for image-heavy chats in Codex, Claude Code and other agents: earlier images stop going out with every message, and the model fetches the one it needs by its ID, also after compaction.
Manage image-heavy chats with AI by keeping only necessary images and searching for them using descriptions.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeA local plugin for image-heavy chats in Codex, Claude Code and other agents: earlier images stop going out with every message, and the model fetches the one it needs by its ID, also after compaction.
context-attachment-manager has 789 stars on GitHub. It has been forked 68 times. context-attachment-manager is written mainly in TypeScript. It has been in active development since 2026. context-attachment-manager is available under the MIT license. Its main topics are ai-agents, claude-code, claude-code-plugin, codex.
What is context-attachment-manager?
A local plugin for image-heavy chats in Codex, Claude Code and other agents: earlier images stop going out with every message, and the model fetches the one it needs by its ID, also after compaction.
Is context-attachment-manager open source?
context-attachment-manager is an open-source project. It is released under the MIT license.
Is context-attachment-manager free?
Yes. context-attachment-manager is free and open source — you can use, modify and self-host it.
What license does context-attachment-manager use?
context-attachment-manager is available under the MIT license.
What language is context-attachment-manager written in?
context-attachment-manager is written mainly in TypeScript.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/chipfighter-context-attachment-manager.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.