fsxmemory
Structured memory system for AI agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, and local semantic search.
Best use case
fsxmemory is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Structured memory system for AI agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, and local semantic search.
Teams using fsxmemory 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/fsxmemory/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How fsxmemory Compares
| Feature / Agent | fsxmemory | 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?
Structured memory system for AI agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, and local semantic search.
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.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Foresigxt Memory Structured memory system for AI agents. ## Install ```bash npm install -g @foresigxt/foresigxt-cli-memory ``` ## Setup ### Option 1: Initialize New Vault ```bash # Initialize vault (creates folder structure + templates) fsxmemory init ~/memory ``` ### Option 2: Use Existing Vault **For isolated workspace memory** (each workspace has its own vault): ```bash # Create .env in workspace root echo 'FSXMEMORY_PATH=/path/to/workspace/memory' > .env # All agents in THIS workspace use this isolated vault fsxmemory stats # Works automatically! ``` **For shared memory across all workspaces**: ```bash # Set global environment variable (in ~/.bashrc or ~/.zshrc) export FSXMEMORY_PATH=/path/to/shared/memory # All agents in ALL workspaces share the same vault ``` **Or**: Use `--vault` flag for one-time override: ```bash fsxmemory stats --vault /path/to/other/vault ``` ## Core Commands ### Store memories by type ```bash # Types: fact, feeling, decision, lesson, commitment, preference, relationship, project, procedural, semantic, episodic fsxmemory remember decision "Use Postgres over SQLite" --content "Need concurrent writes for multi-agent setup" fsxmemory remember lesson "Context death is survivable" --content "Checkpoint before heavy work" fsxmemory remember relationship "Justin Dukes" --content "Client contact at Hale Pet Door" fsxmemory remember procedural "Deploy to Production" --content "1. Run tests 2. Build 3. Deploy" fsxmemory remember semantic "Event Loop Concept" --content "JavaScript's concurrency model..." fsxmemory remember episodic "First Production Deploy" --content "Deployed v2.0 today, team was nervous but it went well" ``` ### Quick capture to inbox ```bash fsxmemory capture "TODO: Review PR tomorrow" ``` ### Search (requires qmd installed) ```bash # Keyword search (fast) fsxmemory search "client contacts" # Semantic search (slower, more accurate) fsxmemory vsearch "what did we decide about the database" ``` ## Context Death Resilience ### Checkpoint (save state frequently) ```bash fsxmemory checkpoint --working-on "PR review" --focus "type guards" --blocked "waiting for CI" ``` ### Recover (check on wake) ```bash fsxmemory recover --clear # Shows: death time, last checkpoint, recent handoff ``` ### Handoff (before session end) ```bash fsxmemory handoff \ --working-on "Foresigxt Memory improvements" \ --blocked "npm token" \ --next "publish to npm, create skill" \ --feeling "productive" ``` ### Recap (bootstrap new session) ```bash fsxmemory recap # Shows: recent handoffs, active projects, pending commitments, lessons ``` ## Migration from Other Formats Migrate existing vaults from OpenClaw, Obsidian, or other markdown-based systems: ### Analyze First (Dry Run) ```bash # See what would be changed without modifying files fsxmemory migrate --from openclaw --vault /path/to/vault --dry-run ``` ### Migrate with Backup ```bash # Recommended: Creates automatic backup before migration fsxmemory migrate --from openclaw --vault /path/to/vault --backup # The migration: # ✅ Adds YAML frontmatter to all markdown files # ✅ Renames directories (procedural→procedures, semantic→knowledge, episodic→episodes) # ✅ Creates .fsxmemory.json config file # ✅ Preserves all content and custom categories # ✅ Creates timestamped backup for rollback ``` ### Rollback if Needed ```bash # Restore from backup if something went wrong fsxmemory migrate --rollback --vault /path/to/vault ``` ### Migration Options ```bash # Available source formats --from openclaw # OpenClaw vault format --from obsidian # Obsidian vault format --from generic # Generic markdown vault # Migration flags --dry-run # Preview changes without modifying files --backup # Create backup before migration (recommended) --force # Skip confirmation prompts --verbose # Show detailed progress --rollback # Restore from last backup ``` ### Example: Migrate OpenClaw Vault ```bash # 1. Analyze first fsxmemory migrate --from openclaw --vault ~/.openclaw/workspace/memory --dry-run # 2. Run migration with backup fsxmemory migrate --from openclaw --vault ~/.openclaw/workspace/memory --backup --verbose # 3. Verify migration worked fsxmemory stats --vault ~/.openclaw/workspace/memory fsxmemory doctor --vault ~/.openclaw/workspace/memory ``` **Migration Speed**: ~53 files in 0.07 seconds ⚡ ## Auto-linking Wiki-link entity mentions in markdown files: ```bash # Link all files fsxmemory link --all # Link single file fsxmemory link memory/2024-01-15.md ``` ## Templates Reference Foresigxt Memory includes structured templates for consistent documentation. Location: `templates/` directory. ### Available Templates | Template | Type | Use For | Sections | |----------|------|---------|----------| | `decision.md` | decision | Key choices, architecture decisions | Context, Options, Decision, Outcome | | `procedure.md` | procedural | How-to guides, workflows, SOPs | Purpose, Prerequisites, Steps, Pitfalls, Verification | | `knowledge.md` | semantic | Concepts, definitions, mental models | Definition, Key Concepts, Examples, Why It Matters | | `episode.md` | episodic | Events, experiences, meetings | What Happened, Context, Key Moments, Reflection | | `person.md` | person | Contacts, relationships | Contact, Role, Working With, Interactions | | `project.md` | project | Active work, initiatives | Goal, Status, Next Actions, Blockers | | `lesson.md` | lesson | Insights, patterns learned | Situation, Lesson, Application | | `handoff.md` | handoff | Session continuity | Working On, Context, Next Steps, Blockers | | `daily.md` | daily | Daily notes, journal | Focus, Done, Notes | ### Template Usage Templates are automatically selected by memory type: ```bash fsxmemory remember decision "Title" --content "..." # → templates/decision.md fsxmemory remember procedural "Title" --content "..." # → templates/procedure.md fsxmemory remember semantic "Title" --content "..." # → templates/knowledge.md fsxmemory remember episodic "Title" --content "..." # → templates/episode.md fsxmemory remember relationship "Name" --content "..." # → templates/person.md fsxmemory remember lesson "Title" --content "..." # → templates/lesson.md ``` **To view template structure**: Read the template file in `templates/` directory before creating a memory document. **Template features**: - YAML frontmatter with metadata (title, date, type, status) - Structured sections with placeholder guidance - Wiki-link suggestions for connections - Auto-generated tags ## Folder Structure ``` vault/ ├── .fsxmemory/ # Internal state │ ├── last-checkpoint.json │ └── dirty-death.flag ├── decisions/ # Key choices with reasoning ├── lessons/ # Insights and patterns ├── people/ # One file per person ├── projects/ # Active work tracking ├── procedures/ # How-to guides and workflows ├── knowledge/ # Concepts and definitions ├── episodes/ # Personal experiences ├── handoffs/ # Session continuity ├── inbox/ # Quick captures └── templates/ # Document templates (9 types) ``` ## Best Practices 1. **Checkpoint every 10-15 min** during heavy work 2. **Handoff before session end** — future you will thank you 3. **Recover on wake** — check if last session died 4. **Use types** — knowing WHAT you're storing helps WHERE to put it 5. **Wiki-link liberally** — `[[person-name]]` builds your knowledge graph ## Integration with qmd Foresigxt Memory uses [qmd](https://github.com/tobi/qmd) for search: ```bash # Install qmd bun install -g github:tobi/qmd # Add vault as collection qmd collection add /path/to/vault --name my-memory --mask "**/*.md" # Update index qmd update && qmd embed ``` ## Configuration Foresigxt Memory supports three ways to set the vault path (in order of precedence): ### 1. Command-line flag (highest priority) ```bash fsxmemory stats --vault /path/to/vault ``` ### 2. Environment variable ```bash export FSXMEMORY_PATH=/path/to/memory fsxmemory stats ``` ### 3. .env file (for workspace-isolated memory) ```bash # Create .env in workspace root cat > .env << 'EOF' FSXMEMORY_PATH=/home/user/.openclaw/workspace/memory EOF # All fsxmemory commands in this workspace use this isolated vault fsxmemory stats fsxmemory checkpoint --working-on "task" ``` **Use .env when:** - ✅ **Isolating workspace memory** — Each project has its own separate vault - ✅ **Per-project configuration** — Different agents in different workspaces use different vaults - ✅ **Portable** — Workspace agents automatically use the right vault - ✅ **Git-safe** — Add `.env` to `.gitignore` to protect paths **Use global export when:** - ✅ **Sharing memory across workspaces** — All agents everywhere use one vault - ✅ **Centralized knowledge** — One source of truth for all projects **Environment Variables:** - `FSXMEMORY_PATH` — Vault path (can be set in shell or `.env` file) ## Publishing Skill Package To create a distributable skill package (includes SKILL.md and templates/): ```bash # Package the skill npm run package-skill # Output: dist-skill/fsxmemory-skill.zip (~8KB) ``` **Package contents:** - `SKILL.md` - Complete documentation and reference - `templates/` - All 9 memory templates - `.env.example` - Configuration template - `INSTALL.md` - Quick setup guide **Distribution:** Share the `fsxmemory-skill.zip` file with other agents/teams. They can extract it to get: - Complete skill documentation - Ready-to-use templates - Configuration examples **For OpenClaw/ClaudeHub:** The packaged skill is ready for upload to skill repositories. ## Links - npm: https://www.npmjs.com/package/@foresigxt/foresigxt-cli-memory - GitHub: https://github.com/Foresigxt/foresigxt-cli-memory - Issues: https://github.com/Foresigxt/foresigxt-cli-memory/issues
Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述