intertwine

Observational Memory — Documentation skill for Claude Code

Documentation community

Local-first shared memory for Claude Code, Codex, OpenCode, Kimi, Grok, Cowork, and Hermes, with bounded observation and searchable Markdown context.

How to install Observational Memory

This entry records only its repository, not the path inside it, so there is no exact command to give. Open intertwine/observational-memory and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Observational Memory does

Local-first shared memory for Claude Code, Codex, OpenCode, Kimi, Grok, Cowork, and Hermes, with bounded observation and searchable Markdown context.

Alternatives in Documentation

会话管理（Session Manager）需求文档（PRD / Markdown） — 目标：对 Codex / Claude Code 的本地会话记录进行可视化管理，并提供“一键复制 / 一键终端恢复”能力 31.7k ★
Notion Knowledge Capture — Convert conversations into structured, searchable Notion wiki entries 14.6k ★
Hyperresearch — Agent-driven research knowledge base 2.4k ★

README

Observational Memory

![Observational Memory header showing local agent memory shared across Claude Code, Codex, Grok, Claude Cowork, and Hermes, with reviewed export to hosted agents.](assets/observational-memory-header.png)

[![PyPI version](https://img.shields.io/pypi/v/observational-memory.svg)](https://pypi.org/project/observational-memory/) [![Latest release](https://img.shields.io/github/v/release/intertwine/observational-memory?label=release)](https://github.com/intertwine/observational-memory/releases/latest) [![Python versions](https://img.shields.io/pypi/pyversions/observational-memory.svg)](https://pypi.org/project/observational-memory/) [![PyPI downloads](https://img.shields.io/pypi/dm/observational-memory.svg)](https://pypi.org/project/observational-memory/) [![CI](https://github.com/intertwine/observational-memory/actions/workflows/ci.yml/badge.svg)](https://github.com/intertwine/observational-memory/actions/workflows/ci.yml) [![GitHub stars](https://img.shields.io/github/stars/intertwine/observational-memory?style=social)](https://github.com/intertwine/observational-memory/stargazers)

**Shared, local memory for AI coding agents — now with a native Claude Code and Codex bridge that needs no transcript capture or an LLM.**

Observational Memory, or `om`, helps agents carry useful context from one session and tool to the next. In v0.10.0, its native-memory bridge reads the small memory summaries that Claude Code and Codex already maintain, indexes an approved set in a private local keyword-search index (BM25), and makes that shared context available through OM retrieval.

The bridge is available on macOS in v0.10.0. It reads native memory sources without changing them. It does **not** ingest raw transcripts, call an LLM, run reflection, or silently upload memory.