kleosr/cursorkleosr

Make AI Development Feel Natural in Cursor

What it solves

It solves the problem of "agent amnesia" in AI coding assistants, where the agent forgets the project's current state, goals, and progress between sessions or requires the user to manually provide context every time.

How it works

The project uses a combination of a permanent Cursor rule (.cursor/rules/workflow-memory.mdc) set to alwaysApply: true and root-level Markdown files. This forces the AI agent to automatically follow a specific loop: read the project configuration and current state, perform the work, and then write the updated state back to the files. It organizes work into a structured pipeline: ANALYZE $\rightarrow$ PREPARE $\rightarrow$ IMPLEMENT $\rightarrow$ VALIDATE.

Who it’s for

Developers using the Cursor editor who want a persistent, automated memory system for their AI agents without needing external databases or complex setups.

Highlights

  • Always-on Memory: Uses Cursor rules to ensure the agent reads state before thinking, eliminating the need for manual context pasting.
  • Zero Dependencies: Relies entirely on plain Markdown files, making the state diffable, greppable, and editor-agnostic.
  • Structured Workflow: Implements a formal state machine for task progression (Analyze, Prepare, Implement, Validate).
  • Canonical Handbook: Centralizes agent rules, skills, and workflows in a single AGENTS.md file.

Related

  • Project
    OthmanAdi/planning-with-files

    A persistent file-based planning system for AI coding agents that stores task plans, findings, and progress on disk to prevent state loss during context resets.

  • Project
    JamesShi96/project-butler

    A persistent memory system for AI coding assistants that uses a structured Markdown-based memory stack to maintain project context, rules, and progress across sessions.

  • Project
    mindmuxai/brain.md

    A persistent, file-based memory layer for coding agents that stores project decisions and constraints as plain Markdown in the repository.

  • Project
    rohitg00/agentmemory

    A persistent memory layer for AI coding agents that captures and compresses session data to eliminate the need for re-explaining project context across sessions and tools.

  • Project
    akitaonrails/ai-memory

    ai‑memory is a Rust‑based, self‑contained service that gives AI coding assistants a shared, long‑term, markdown‑backed memory. It automatically captures prompts and tool calls via hooks, stores them as git‑versioned markdown pages, and lets any supported agent (Claude Code, Codex, Cursor, Gemini CLI, etc.) retrieve a concise hand‑off on a different machine or after a teammate’s session. By default it works offline with zero LLM calls; optional LLM‑driven “dream” consolidation, vector search, and aging policies are configurable. The project provides native packages, Docker images, and a macOS menu‑bar app, and includes built‑in multi‑user auth, audit logs, and per‑project sharing.