Loading
4 permissively-licensed prompts mirrored from atomicstrata/atomicmemory (Apache-2.0). Honest zero stats; every prompt links to its source.
Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call `memory_search` before answering questions that reference past work. Call `memory_ingest` after the user shares durable facts.
AtomicMemory persistent memory integration for Codex. Retrieve relevant memories at the start of each task, store key learnings when tasks complete, and capture session state before context is lost. Use the atomicmemory MCP tools (memory_search, memory_ingest, memory_package, memory_list) for all memory operations — scoped by user / agent / namespace / thread.
Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.
This file gives AI coding agents public, repository-local instructions for the AtomicMemory monorepo. Keep it short, concrete, and safe for a public repository. Human-facing project context lives in README.md, CONTRIBUTING.md, SECURITY.md, and ROADMAP.md.
A Community Mirror bundle of 4 permissively-licensed prompts from `atomicstrata/atomicmemory` (Apache-2.0).
> Honest mirror. Zero usage stats. Not affiliated with the original authors — each prompt links back to its source file and license.
Clone any prompt into your library, bring your own provider key, and run it on any model. No markup.