据 AlphaMoat 统计,截至 2026-09,ForesigxtMemory 累计下载 2,685 次、获 1 个星标,在全部 5,078 个 AI 技能中排名第 3,959 位,在「AI 智能体」分类(969 个)中排名第 792 位。
| 平台 | 累计安装 | 累计下载 | 星标 | 评论 |
|---|---|---|---|---|
| ClawHub ↗ | 83 | 2,611 | 1 | - |
| SkillHub ↗ | 146 | 2,685 | 1 | — |
各平台的计数口径不同,统计时间不一致。
记忆库可能包含敏感的个人、项目或关系信息;共享或语义搜索前需确认数据范围及是否会发送至外部服务。迁移和自动链接会修改 Markdown 文件,执行前先 dry-run 并备份,确保可回滚。 文档中的两种搜索命令均需 qmd;应先核对 CLI 安装来源和 vault 位置。
资料发布于 2026-10-29
以下是根据技能文档生成的示例,不代表实际运行结果。
2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。
| 月份 | 累计下载 | 环比 | 星标 |
|---|---|---|---|
| 2026-09 | 2,685 | — | 1 |
| 2026-08 | 2,491 | +4.7% | 1 |
| 2026-07 | 2,379 | +9.2% | 1 |
| 2026-06 | 2,179 | +5.4% | 1 |
| 2026-05 | 2,068 | — | 1 |
| 2026-03 | 1,718 | — | 1 |
以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。
--- name: fsxmemory version: 1.3.1 description: Structured memory system for AI agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, and local semantic search. author: Foresigxt repository: https://github.com/Foresigxt/foresigxt-cli-memory --- # 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
把开发过程中的经验、错误与纠正记录为 Markdown 文件,供后续复用并晋升为工作区记忆。
用自然语言描述需求,在本地与远程技能市场里找技能并给出推荐的技能。
给 AI agent 用的浏览器自动化命令行技能。
把用户纠正与自我复盘沉淀成分层记忆、并按使用情况升降级的技能。
在安装第三方技能之前,按清单审查来源、权限与危险模式的技能。
把 agent 的记忆与跨技能状态存成带类型和约束的知识图谱的技能。
一份为 AI 代理规划主动跟进、工作记忆与复盘流程的工作区配置指南。
指导如何创建与更新有效 Claude 技能的写作指南。
数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。