clawhip × filesystem-offloaded memory
Use this skill when you want a Claw OS-style memory system where `MEMORY.md` stays small and points into a structured `memory/` tree.
Best use case
clawhip × filesystem-offloaded memory is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use this skill when you want a Claw OS-style memory system where `MEMORY.md` stays small and points into a structured `memory/` tree.
Teams using clawhip × filesystem-offloaded memory should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/memory-offload/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How clawhip × filesystem-offloaded memory Compares
| Feature / Agent | clawhip × filesystem-offloaded memory | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use this skill when you want a Claw OS-style memory system where `MEMORY.md` stays small and points into a structured `memory/` tree.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# clawhip × filesystem-offloaded memory Use this skill when you want a Claw OS-style memory system where `MEMORY.md` stays small and points into a structured `memory/` tree. ## What you get - a clear role for `MEMORY.md` as pointer/index/current-beliefs layer - a practical read/write workflow for agents - guidance for sharding memory by time, channel, project, topic, and handoff - migration guidance away from monolithic memory files ## Read order 1. Read `MEMORY.md` first. 2. Follow the pointer to the smallest relevant shard. 3. Read subtree indexes only when needed. 4. Avoid loading the whole memory tree by default. ## Write order 1. Write detailed updates to the canonical leaf shard. 2. Update `MEMORY.md` only when the pointer map or current beliefs changed. 3. If a section grows noisy, split it into a dedicated file. 4. Archive cold history to keep the hot path small. ## Default shard map - `memory/daily/YYYY-MM-DD.md` -> chronological execution log - `memory/channels/<channel>.md` -> one lane/channel - `memory/projects/<project>.md` -> project/repo state - `memory/agents/<agent>.md` -> agent/operator profile - `memory/topics/rules.md` -> durable operating rules - `memory/topics/lessons.md` -> reusable lessons - `memory/handoffs/YYYY-MM-DD-<slug>.md` -> bounded handoffs - `memory/archive/YYYY-MM/` -> cold history ## Offload triggers Offload when: - `MEMORY.md` stops being easy to scan - one topic dominates the root file - detail is only relevant to one entity or workflow - logs or history start crowding out current beliefs ## Start here - `docs/memory-offload-architecture.md` - `docs/memory-offload-guide.md` - `docs/examples/MEMORY.example.md` - `docs/examples/memory/README.example.md`
Related Skills
clawhip × OMX (oh-my-codex)
Launch [OMX](https://github.com/Yeachan-Heo/oh-my-codex) coding sessions with clawhip monitoring.
clawhip × OMC (oh-my-claudecode)
Launch [OMC](https://github.com/Yeachan-Heo/oh-my-claudecode) coding sessions with clawhip monitoring.
clawhip
Attach/install/use clawhip as a daemon-first notification gateway runtime for OpenClaw / Clawdbot
memory-systems
Design short-term, long-term, and graph-based memory architectures. Use when building agents that must persist across sessions, needing to maintain entity consistency across conversations, or implementing reasoning over accumulated knowledge.
memory-safety-patterns
Cross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and resource management.
memory-forensics
Comprehensive techniques for acquiring, analyzing, and extracting artifacts from memory dumps for incident response and malware analysis.
hierarchical-agent-memory
Scoped CLAUDE.md memory system that reduces context token spend. Creates directory-level context files, tracks savings via dashboard, and routes agents to the right sub-context.
filesystem-context
Use for file-based context management, dynamic context discovery, and reducing context window bloat. Offload context to files for just-in-time loading.
conversation-memory
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory
filesystem
Advanced filesystem operations for listing files, searching content, batch processing, and directory analysis. Supports recursive search, file type filtering, size analysis, and batch operations like copy/move/delete. Use when you need to: list directory contents, search for files by name or content, analyze directory structures, perform batch file operations, or analyze file sizes and distribution.
Agent Memory Architecture
Complete zero-dependency memory system for AI agents — file-based architecture, daily notes, long-term curation, context management, heartbeat integration, and memory hygiene. No APIs, no databases, no external tools. Works with any agent framework.
memory-cache
High-performance temporary storage system using Redis. Supports namespaced keys (mema:*), TTL management, and session context caching. Use for: (1) Saving agent state, (2) Caching API results, (3) Sharing data between sub-agents.