shared-memory-stackComplete reference for the shared memory architecture connecting Claude Code, OpenClaw/Kimi, and LM Studio subagents through Obsidian vault + MemPalace (Chro...
Install via ClawdBot CLI:
clawdbot install nerua1/shared-memory-stackGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/nerua1/shared-memory-stackAudited Apr 17, 2026 · audit v1.0
Generated Oct 6, 2026
A development team runs Claude Code for code review, OpenClaw/Kimi for research synthesis, and LM Studio subagents for local batch analysis. The shared memory stack lets each agent deposit findings into a common Obsidian vault and retrieve relevant past context via MemPalace semantic search, ensuring no insight is lost between tool handoffs.
An indie founder uses capture-idea from CLI and Claude Code slash commands to log product ideas, customer feedback, and technical observations throughout the day. The MemPalace index enables semantic retrieval later when planning features or drafting investor updates.
Security engineers capture oauth token issues, migration risks, and vulnerability observations using the topic and tag frontmatter (e.g., bezpieczenstwo). Later, semantic search surfaces related past findings during incident response or compliance audits.
A researcher working on a long-horizon literature review uses daily notes, source clippings, and answers stored in the vault. MemPalace mines these into searchable rooms so the AI agents can recall prior readings and connect new sources to existing notes.
Power users of Claude Code and OpenClaw set up a personal shared-memory layer to avoid re-explaining context between sessions. Ideas captured from CLI, slash commands, or agent bridge calls get auto-mined into ChromaDB and surfaced during future conversations.
The memory stack is open-source (MIT) and self-hosted, but a paid tier offers cloud-hosted Obsidian vault sync, managed ChromaDB, and cross-device access for teams. Revenue comes from subscriptions per workspace or per seat.
Companies license the architecture as an internal knowledge fabric to connect multiple AI agents and enforce compliance-grade memory retention. Licensing includes setup, security review, and integration with existing SSO and audit systems.
Free tier covers local capture and search; the pro tier unlocks the openclaw-bridge, multi-agent orchestration, and advanced MemPalace mining controls. Monetization targets developers already running Claude Code or OpenClaw locally.
💬 Integration Tip
Requires macOS paths, Python 3.12 venv, ChromaDB, and the mempalace wrapper; start by verifying the vault path and running `mempalace status` before writing any capture pipeline. Use dry-run mining and test the openclaw-bridge port 18789 before wiring agents together.
Scored Oct 6, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...
AI agent for finance search agent tasks