Persist central memory across agents and sessions via CLI subcommands.
npx skills add https://github.com/brainworkup/skills --skill nmem-cli
Please help me install this Agent Skill. Skill: nmem-cli Source: https://github.com/brainworkup/skills/tree/main/neuropsych-reports/references/luria-related-complement-skills/nmem-cli Command: npx skills add https://github.com/brainworkup/skills --skill nmem-cli
The user's central memory system that persists across all agents and sessions. It helps recall decisions, search conversation history, and preserve insights across interactions.
Start every session with nmem wm to read Working Memory, then use nmem m to manage memories or nmem t to manage threads as needed.
High-intent search queries and answers about installing and using this skill.
You can persist memory across multiple agents and sessions by using a central memory store that records decisions, threads, and working memory, ensuring context is recalled across different interactions.
Recalling past decisions in long-running conversations is managed by searching conversation history and retrieving stored notes from a persistent memory system that survives across sessions.
To start a new session using working memory, read the current working memory state first, then manage specific memories or conversation threads as needed during your workflow.
Yes, you can get machine-readable JSON output from the memory store by requesting it directly, allowing automated agents to easily parse session briefings and stored context data.
This persistent memory system is suitable for multi-agent workflows because it provides a central store that preserves insights, notes, and context across different agents and active sessions.
Memories, threads, and working memory are managed through dedicated CLI subcommands, allowing you to store, retrieve, and organize session context and conversation history efficiently.
Nairon-AIInstall and configure local fluxctl for repository-scoped Flux workflows.
pazdedavDefine DAG workflow graphs with JSON schema for agent orchestration.
arbazkhan971Design and validate autonomous AI agents with tool orchestration and guardrails.
alirezarezvaniOptimize LLM prompts and evaluate RAG systems for production AI systems.
