lumayapartners/memini
by Various
Never the same mistake twice — mistake-prevention guardrails and persistent project memory for AI coding agents (Claude Code, Cursor, Windsurf)
MCP
lumayapartners/memini
Added 3 Sept 2026
Overview
Memini adds persistent project memory and mistake-prevention guardrails to AI coding agents like Claude Code, Cursor, and Windsurf. It tracks past errors and project context so agents avoid repeating the same mistakes. Written in TypeScript, it is available as an open-source GitHub project.
Best for
Best for
Developers using AI coding agents who want to avoid repeating the same mistakes across sessions
Use cases
- Prevent an AI agent from repeating a known bug or failed approach
- Maintain project-specific context across coding sessions
- Enforce project-specific rules and guardrails during code generation
Notes
Memini adds persistent project memory and mistake-prevention guardrails to AI coding agents like Claude Code, Cursor, and Windsurf. It tracks past errors and project context so agents avoid repeating the same mistakes. Written in TypeScript, it is available as an open-source GitHub project.
0 stars on GitHub. Last updated 2026-07-22. Licensed MIT.
Use cases
- Prevent an AI agent from repeating a known bug or failed approach
- Maintain project-specific context across coding sessions
- Enforce project-specific rules and guardrails during code generation
Pros
- Open source and free to use
- Works across multiple popular AI coding agents
- Persistent memory reduces repeated errors
Cons
- Zero stars suggests limited community adoption or validation
- Requires setup and maintenance of memory files
- Effectiveness depends on the agent’s ability to use the provided context
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Open source and free to use
- Works across multiple popular AI coding agents
- Persistent memory reduces repeated errors
Cons
- Zero stars suggests limited community adoption or validation
- Requires setup and maintenance of memory files
- Effectiveness depends on the agent's ability to use the provided context
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
