Install
$ agentstack add mcp-akashkobal-contextmemory ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
ContextMemory 🧠
Persistent AI coding context memory for developers and teams. Git tracks your code history. ContextMemory tracks your intent history. Never re-explain your architecture, decisions, or progress to AI assistants again.
You're deep in a Cursor session refactoring a payment service. You've explained the architecture, tried 3 approaches, finally found the right one. Session dies. Next morning — or worse, your teammate picks it up — and the AI has zero memory. You spend 15 min re-explaining everything. Every. Single. Time.
This is broken across every AI coding tool: Cursor, Claude Code, Copilot, Windsurf — none of them persist context across sessions, editors, or team members.
🚀 Installation
Install globally from npm:
npm install -g @akashkobal/contextmemory
Verify installation:
contextmemory --help
⚡ Quick Start
Initialize inside your project:
contextmemory init
Save your working context:
contextmemory save
Quick save:
contextmemory save "Implemented multi-model execution"
Resume your context:
contextmemory resume
This copies a formatted prompt to your clipboard. Paste it into ChatGPT, Cursor, Claude, or any AI coding tool.
🧠 How It Works
ContextMemory creates:
.contextmemory/
├── context.json
├── history/
│ ├── entry-1.json
│ ├── entry-2.json
Each entry captures:
- Task
- Goal
- Approaches
- Decisions
- Current State
- Next Steps
📦 Commands
Core
contextmemory init
contextmemory save
contextmemory resume
contextmemory log
contextmemory diff
Automation
contextmemory watch
contextmemory hook install
contextmemory handoff @username
🔌 MCP Integration (Optional)
Add to your MCP configuration:
{
"mcpServers": {
"contextmemory": {
"command": "npx",
"args": ["-y", "@akashkobal/contextmemory", "mcp"]
}
}
}
🏗 Works With
- Spring Boot
- React
- Node.js
- Python
- Microservices
- Monorepos
AI Tools:
- ChatGPT
- Cursor
- Claude
- Copilot
- Windsurf
📄 License
MIT
👨💻 Author
Akash Kobal GitHub: https://github.com/AkashKobal
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AkashKobal
- Source: AkashKobal/contextmemory
- License: MIT
- Homepage: https://www.npmjs.com/package/@akashkobal/contextmemory
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.