AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Memory & Context/
context-attachment-manager
context-attachment-manager logo

context-attachment-manager

Active·★ 356·MIT·Updated 2026-10-22

Context Attachment Manager is a plugin for Codex and Claude Desktop that allows users to selectively send past images to the LLM, preventing context overload and improving conversational performance. It enables granular control over visual context, ensuring efficient interaction in long, image-heavy discussions.

context-attachment-manager sits in the Memory & Context category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Every image in one list. A representative use case is Managing long conversational AI tasks with numerous images without performance degradation.. The listed license is MIT. GitHub stars are currently 360. Relevant tags include context management, LLM plugin.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#context management#LLM plugin#image attachment#conversational AI#desktop app#proxy#resource optimization
$ Install
$ claude plugin marketplace add chipfighter/context-attachment-manager && claude plugin install codex-attachment-manager@codex-attachment-manager
↗ Visit site★ GitHub
01

Features

01Every image in one list
02Filter by source
03One click to leave an image out
04The model asks, you decide
05Keeps your choice through compaction
02

Why choose it

+Every image in one list
+Filter by source
+Managing long conversational AI tasks with numerous images without performance degradation.
+Supports 6 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Windows
Platform
Verified via docs
macOS
Platform
Verified via docs
Linux
Platform
Verified via docs
Codex
Application
Verified via docs
Claude Desktop
Application
Verified via docs
Node.js
Runtime
Verified via docs
05

Quick start

1
$ claude plugin marketplace add chipfighter/context-attachment-manager
2
$ claude plugin install codex-attachment-manager@codex-attachment-manager
06

Use cases

↳Managing long conversational AI tasks with numerous images without performance degradation.
↳Preventing API request failures or slowdowns caused by overly large image attachments in LLM interactions.
↳Optimizing token usage and context window consumption by sending only relevant images.
↳Selectively providing specific visual context to an LLM on a turn-by-turn basis.
07

Alternatives

⚡Top VS:
VSmemorycrystal★12→VSratel★497→VSditto★298→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases
VS
Vault-Agent-Memory
★50
→
memorycrystal logo
memorycrystal★ 12
Persistent memory for AI agents — OpenClaw plugin + MCP server
VSCompare→
ratel logo
ratel★ 497
Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 retrieval. No vector DB. No embeddings.
VSCompare→
ditto logo
ditto★ 298
Mine your Claude Code and Codex logs into a local you.md agent profile.
VSCompare→
Vault-Agent-Memory logo
Vault-Agent-Memory★ 50
Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.
VSCompare→
kaeru logo
kaeru★ 45
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
VSCompare→
rlm-claude logo
rlm-claude★ 39
Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper
VSCompare→
context-harness logo
context-harness★ 42
Local-first context ingestion and retrieval for AI tools. SQLite + embeddings + MCP server for Cursor & Claude.
VSCompare→
geml logo
geml★ 29
One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.
VSCompare→
See all alternatives →
07
Alternatives
chipfighter /
context-attachment-manager
↗

Codex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your next message. Unchecked images become placeholders, the conversation goes on, and requests stay small.

356MIT
Last commit1d ago
StatusActive
CategoryMemory & Context
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit