joshuaswarren/remnic — Local-first memory plugin for AI agents including OpenClaw, Hermes, Codex, Claude Code and more.

Description and use

A local‑first memory plugin that equips AI agents—such as OpenClaw, Hermes, Codex, Claude Code, and others—with persistent, long‑term recall across conversations. It uses LLM‑driven extraction to convert interactions into plain‑markdown notes, stores them locally, and provides hybrid search through QMD for fast, context‑aware retrieval. The project enables seamless orchestration of memory for agents without relying on external services.

Problem

joshuaswarren/remnic helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Early or unclear: treat as research material until maintenance, releases, docs, and issue activity are verified.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

Local-first memory plugin for AI agents including OpenClaw, Hermes, Codex, Claude Code and more. LLM-powered extraction, plain markdown storage, hybrid search via QMD. Gives agents persistent long-term memory across conversations.

Source