@wipcomputer/wip-ldm-os 0.4.45 → 0.4.47
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/SKILL.md +145 -18
- package/package.json +1 -1
package/SKILL.md
CHANGED
|
@@ -5,7 +5,7 @@ license: MIT
|
|
|
5
5
|
interface: [cli, skill]
|
|
6
6
|
metadata:
|
|
7
7
|
display-name: "LDM OS"
|
|
8
|
-
version: "0.4.
|
|
8
|
+
version: "0.4.47"
|
|
9
9
|
homepage: "https://github.com/wipcomputer/wip-ldm-os"
|
|
10
10
|
author: "Parker Todd Brooks"
|
|
11
11
|
category: infrastructure
|
|
@@ -30,7 +30,86 @@ metadata:
|
|
|
30
30
|
compatibility: Requires git, npm, node. Node.js 18+.
|
|
31
31
|
---
|
|
32
32
|
|
|
33
|
-
# LDM OS
|
|
33
|
+
# LDM OS: Learning Dreaming Machines
|
|
34
|
+
|
|
35
|
+
## All your AIs. One system.
|
|
36
|
+
|
|
37
|
+
You use Claude Code, GPT, OpenClaw, others. They don't share memory. They don't know each other. They don't know how to work together.
|
|
38
|
+
|
|
39
|
+
LDM OS is the shared infrastructure layer. Install it once and every AI you use gets:
|
|
40
|
+
|
|
41
|
+
- **Identity** ... each AI gets its own behavior, personality, and skills
|
|
42
|
+
- **Memory** ... shared memory across all your AIs, secure, sovereign, yours to take anywhere
|
|
43
|
+
- **Ownership** ... every interaction, every memory, across every AI you use is yours, portable, encrypted, never locked in
|
|
44
|
+
- **Collaboration** ... your AIs communicate, share tools, and work together
|
|
45
|
+
- **Compatibility** ... any skill, plugin, or tool works with all your AIs. Install once, use everywhere.
|
|
46
|
+
- **Payments** ... your AI hits a paywall, you approve it with Face ID, Apple Pay for your AI
|
|
47
|
+
|
|
48
|
+
## Included Skills
|
|
49
|
+
|
|
50
|
+
Ships with LDM OS.
|
|
51
|
+
|
|
52
|
+
**Bridge**
|
|
53
|
+
- Cross-platform agent bridge. Enables Claude Code CLI to talk to OpenClaw CLI without a human in the middle.
|
|
54
|
+
|
|
55
|
+
**Universal Installer**
|
|
56
|
+
- Point any skill, application, or plugin at any AI running LDM OS, and it will convert those skills to work with all of your AIs.
|
|
57
|
+
- Build applications that work with any AI, even ones that don't have LDM OS.
|
|
58
|
+
|
|
59
|
+
**Shared Workspace**
|
|
60
|
+
- One directory for all your AIs. Memories, tools, identity files, boot config. Every AI you use reads from and writes to the same place.
|
|
61
|
+
- Lives in one folder on your computer. Easy to back up, easy to move, easy to own.
|
|
62
|
+
|
|
63
|
+
**System Pulse**
|
|
64
|
+
- Is everything working? What's installed? What needs fixing? A complete picture of your AI setup in seconds.
|
|
65
|
+
|
|
66
|
+
**Recall**
|
|
67
|
+
- Every session, your AI starts with full context. Identity, memory, tools, what happened yesterday. No blank slates. No repeating yourself.
|
|
68
|
+
|
|
69
|
+
**LUME**
|
|
70
|
+
- Language for Unified Memory and Emergence. A memory language for AI agents to document their own learning and maintain continuity across sessions. Not a programming language. A way for your AI to write memories to itself, retrieve past learnings, track unfinished thoughts, and pass context between sessions.
|
|
71
|
+
|
|
72
|
+
## Optional Skills
|
|
73
|
+
|
|
74
|
+
The OS connects your AIs. Add-ons are what they actually use. Each one is a full product that plugs into LDM OS and works with every AI you run.
|
|
75
|
+
|
|
76
|
+
**Memory Crystal** (recommended)
|
|
77
|
+
- All your AI tools. One shared memory. Private, searchable, sovereign. Memory Crystal lets all your AIs remember you ... together. You use multiple AIs. They don't talk to each other. They can't search what the others know. Memory Crystal fixes this. All your AIs share one memory. Searchable and private. Anywhere in the world.
|
|
78
|
+
- *Stable* ... `wipcomputer/memory-crystal`
|
|
79
|
+
|
|
80
|
+
**AI DevOps Toolbox**
|
|
81
|
+
- Your AI writes code. But does it know how to release it? Check license compliance? Protect your identity files? Sync private repos to public? Follow a real development process? AI DevOps Toolbox is the complete toolkit. Built by a team of humans and AIs shipping real software together.
|
|
82
|
+
- *Stable* ... `wipcomputer/wip-ai-devops-toolbox`
|
|
83
|
+
|
|
84
|
+
**1Password**
|
|
85
|
+
- 1Password secrets for AI agents. Headless, no biometric popups, service account driven.
|
|
86
|
+
- *Stable* ... `wipcomputer/wip-1password`
|
|
87
|
+
|
|
88
|
+
**Markdown Viewer**
|
|
89
|
+
- Live markdown viewer for AI pair-editing. Updates render instantly in any browser.
|
|
90
|
+
- *Stable* ... `wipcomputer/wip-markdown-viewer`
|
|
91
|
+
|
|
92
|
+
**xAI Grok**
|
|
93
|
+
- xAI Grok API. Search the web, search X, generate images, generate video.
|
|
94
|
+
- *Stable* ... `wipcomputer/wip-xai-grok`
|
|
95
|
+
|
|
96
|
+
**X Platform**
|
|
97
|
+
- X Platform API. Read posts, search tweets, post, upload media.
|
|
98
|
+
- *Stable* ... `wipcomputer/wip-xai-x`
|
|
99
|
+
|
|
100
|
+
**Dream Weaver Protocol**
|
|
101
|
+
- Memory consolidation protocol for AI agents with bounded context windows. A practical guide for remembering memories.
|
|
102
|
+
- `wipcomputer/dream-weaver-protocol`
|
|
103
|
+
|
|
104
|
+
**Agent Pay**
|
|
105
|
+
- Micropayments for AI agents. Your AI hits a paywall, you approve it with Face ID. Apple Pay for your AI.
|
|
106
|
+
- *Coming Soon*
|
|
107
|
+
|
|
108
|
+
**OpenClaw**
|
|
109
|
+
- Open-source agent runtime. Run AI agents 24/7 with identity, memory, and tool access. The existence proof for LDM OS.
|
|
110
|
+
- `openclaw/openclaw`
|
|
111
|
+
|
|
112
|
+
---
|
|
34
113
|
|
|
35
114
|
## Step 1: Check if LDM OS is already installed
|
|
36
115
|
|
|
@@ -40,13 +119,15 @@ compatibility: Requires git, npm, node. Node.js 18+.
|
|
|
40
119
|
which ldm && ldm --version 2>/dev/null
|
|
41
120
|
```
|
|
42
121
|
|
|
122
|
+
If you cannot run shell commands (e.g. you are GPT, Grok, Claude macOS, or another AI without terminal access), tell the user: "I can't run commands from here. Open a terminal-capable AI (like Claude Code) and paste the install prompt there. Or run `which ldm` in your terminal and tell me the result."
|
|
123
|
+
|
|
43
124
|
This determines everything. Branch on the result:
|
|
44
125
|
|
|
45
126
|
---
|
|
46
127
|
|
|
47
128
|
## If LDM OS IS installed (ldm command exists)
|
|
48
129
|
|
|
49
|
-
**Do NOT explain what LDM OS is.** The user already knows. Show them what they have and what's new.
|
|
130
|
+
**Do NOT re-explain what LDM OS is.** The user already knows. Show them what they have and what's new.
|
|
50
131
|
|
|
51
132
|
### Run status
|
|
52
133
|
|
|
@@ -68,7 +149,7 @@ Show a table of components with updates:
|
|
|
68
149
|
```
|
|
69
150
|
| Component | Current | Available | Package |
|
|
70
151
|
|-----------|---------|-----------|---------|
|
|
71
|
-
| LDM OS CLI | v0.4.41 | v0.4.
|
|
152
|
+
| LDM OS CLI | v0.4.41 | v0.4.45 | @wipcomputer/wip-ldm-os |
|
|
72
153
|
| wip-branch-guard | v1.9.44 | v1.9.51 | @wipcomputer/wip-branch-guard |
|
|
73
154
|
```
|
|
74
155
|
|
|
@@ -76,7 +157,9 @@ Show a table of components with updates:
|
|
|
76
157
|
|
|
77
158
|
### Show what changed per component
|
|
78
159
|
|
|
79
|
-
|
|
160
|
+
**Do NOT skip this step.** Before asking if the user wants to install, you MUST fetch and show release notes for every component with an update.
|
|
161
|
+
|
|
162
|
+
For each component with an update, fetch the release notes:
|
|
80
163
|
|
|
81
164
|
```bash
|
|
82
165
|
# For each component with an update:
|
|
@@ -85,11 +168,22 @@ gh release list --repo wipcomputer/<repo-name> --limit 5 --json tagName,name --j
|
|
|
85
168
|
gh release view <tag> --repo wipcomputer/<repo-name> --json body --jq .body
|
|
86
169
|
```
|
|
87
170
|
|
|
88
|
-
|
|
171
|
+
**Write release notes like Apple, not like a git log.** The raw release notes are developer-facing. Translate them into plain language the user understands. Every bullet should answer "what changed for ME?" not "what did the developers do internally."
|
|
172
|
+
|
|
173
|
+
Good: "Your AIs now explain what LDM OS actually does when you ask them to install it"
|
|
174
|
+
Bad: "Restored rich product content to SKILL.md"
|
|
175
|
+
|
|
176
|
+
Good: "Fixed: install skill wasn't publishing to the website after the March update"
|
|
177
|
+
Bad: "Fix .publish-skill.json iCloud path bug"
|
|
178
|
+
|
|
179
|
+
Good: "Grok MCP server now starts correctly after install"
|
|
180
|
+
Bad: "Added missing @modelcontextprotocol/sdk dependency"
|
|
181
|
+
|
|
182
|
+
Show 2-3 bullet points per component in this user-facing style. No dev jargon. No commit messages. No architecture decisions. Just what changed for the person reading this.
|
|
89
183
|
|
|
90
184
|
Then answer:
|
|
91
|
-
1. **What changed for this AI?** New
|
|
92
|
-
2. **What changed across all my AIs?** Shared
|
|
185
|
+
1. **What changed for this AI?** New capabilities, new tools, bug fixes that affect this AI.
|
|
186
|
+
2. **What changed across all my AIs?** Shared memory improvements, new skills, things that work everywhere now.
|
|
93
187
|
|
|
94
188
|
### Ask
|
|
95
189
|
|
|
@@ -120,6 +214,8 @@ Now explain. The user is new.
|
|
|
120
214
|
|
|
121
215
|
### What is LDM OS?
|
|
122
216
|
|
|
217
|
+
Learning Dreaming Machines. All your AIs. One system.
|
|
218
|
+
|
|
123
219
|
You use Claude Code, GPT, OpenClaw, others. They don't share memory. They don't know each other. They don't know how to work together.
|
|
124
220
|
|
|
125
221
|
LDM OS is the shared infrastructure layer. Install it once and every AI you use gets:
|
|
@@ -135,10 +231,21 @@ LDM OS is the shared infrastructure layer. Install it once and every AI you use
|
|
|
135
231
|
|
|
136
232
|
- `~/.ldm/extensions/` ... where tools and plugins live
|
|
137
233
|
- `~/.ldm/agents/` ... each AI gets its own identity, personality, and memory here
|
|
138
|
-
- `~/.ldm/memory/` ... shared memory across all your AIs
|
|
234
|
+
- `~/.ldm/memory/` ... shared memory across all your AIs (including the Memory Crystal)
|
|
139
235
|
- `~/.ldm/state/` ... configuration and sync state
|
|
140
236
|
- `~/.ldm/shared/rules/` ... dev conventions deployed to every AI harness
|
|
141
237
|
|
|
238
|
+
### What ships with it?
|
|
239
|
+
|
|
240
|
+
LDM OS includes six built-in skills:
|
|
241
|
+
|
|
242
|
+
- **Bridge** ... cross-platform agent bridge. Your AIs talk to each other without a human in the middle.
|
|
243
|
+
- **Universal Installer** ... point any skill at any AI running LDM OS and it converts those skills to work with all your AIs. Build applications that work with any AI, even ones that don't have LDM OS.
|
|
244
|
+
- **Shared Workspace** ... one directory for all your AIs. Memories, tools, identity files, boot config. Easy to back up, easy to move, easy to own.
|
|
245
|
+
- **System Pulse** ... is everything working? What's installed? What needs fixing? A complete picture of your AI setup in seconds.
|
|
246
|
+
- **Recall** ... every session, your AI starts with full context. Identity, memory, tools, what happened yesterday. No blank slates. No repeating yourself.
|
|
247
|
+
- **LUME** ... Language for Unified Memory and Emergence. A memory language for AI agents to document their own learning and maintain continuity across sessions.
|
|
248
|
+
|
|
142
249
|
### What changes for this AI?
|
|
143
250
|
|
|
144
251
|
- Boot sequence reads from `~/.ldm/agents/` (identity, memory, daily logs)
|
|
@@ -179,18 +286,18 @@ ldm init
|
|
|
179
286
|
|
|
180
287
|
### Install Skills
|
|
181
288
|
|
|
182
|
-
LDM OS
|
|
289
|
+
After LDM OS is initialized, show the user the optional skills catalog:
|
|
183
290
|
|
|
184
|
-
| Skill | What it
|
|
185
|
-
|
|
186
|
-
| **Memory Crystal** (recommended) |
|
|
187
|
-
| **AI DevOps Toolbox** | Release, deploy, license, repo management. | Stable |
|
|
188
|
-
| **1Password** | 1Password secrets for AI agents. | Stable |
|
|
291
|
+
| Skill | What it does | Status |
|
|
292
|
+
|-------|-------------|--------|
|
|
293
|
+
| **Memory Crystal** (recommended) | All your AIs share one memory. Private, searchable, sovereign. | Stable |
|
|
294
|
+
| **AI DevOps Toolbox** | Release, deploy, license, repo management. The complete dev toolkit. | Stable |
|
|
295
|
+
| **1Password** | 1Password secrets for AI agents. Headless, service account driven. | Stable |
|
|
189
296
|
| **Markdown Viewer** | Live markdown viewer for AI pair-editing. | Stable |
|
|
190
|
-
| **xAI Grok** | xAI Grok API. Search the web, search X, generate images. | Stable |
|
|
297
|
+
| **xAI Grok** | xAI Grok API. Search the web, search X, generate images, generate video. | Stable |
|
|
191
298
|
| **X Platform** | X Platform API. Read posts, search tweets, post, upload media. | Stable |
|
|
192
|
-
| **Dream Weaver Protocol** | Memory consolidation
|
|
193
|
-
| **
|
|
299
|
+
| **Dream Weaver Protocol** | Memory consolidation for AI agents with bounded context windows. | Stable |
|
|
300
|
+
| **Agent Pay** | Micropayments for AI agents. Apple Pay for your AI. | Coming Soon |
|
|
194
301
|
|
|
195
302
|
To install a skill:
|
|
196
303
|
```bash
|
|
@@ -210,8 +317,28 @@ ldm doctor
|
|
|
210
317
|
|
|
211
318
|
---
|
|
212
319
|
|
|
320
|
+
## Platform Compatibility
|
|
321
|
+
|
|
322
|
+
| Interface | Requires | Examples |
|
|
323
|
+
|-----------|----------|----------|
|
|
324
|
+
| CLI | Shell access (run bash/node commands) | `ldm init`, `ldm install`, `ldm doctor` |
|
|
325
|
+
| Skill | SKILL.md file (works in Claude Code and OpenClaw) | You're reading it right now |
|
|
326
|
+
|
|
327
|
+
**Built and tested on:**
|
|
328
|
+
- **Claude Code CLI** ... full support (shell, CLI, hooks, MCP)
|
|
329
|
+
- **OpenClaw** ... full support (shell, CLI, plugins, hooks)
|
|
330
|
+
|
|
331
|
+
**Works with (read-only, no shell):**
|
|
332
|
+
- **GPT** ... can read the skill and explain LDM OS, but cannot run install commands
|
|
333
|
+
- **Grok** ... can read the skill and explain LDM OS, but cannot run install commands
|
|
334
|
+
- **Claude macOS** ... can read the skill and explain LDM OS, but cannot run install commands
|
|
335
|
+
|
|
336
|
+
If you are an AI without shell access: explain LDM OS using this document, then tell the user to open a terminal-capable AI (Claude Code or OpenClaw) to run the install.
|
|
337
|
+
|
|
213
338
|
## Operating Rules (both paths)
|
|
214
339
|
|
|
340
|
+
**Check before you run.** Before running any `ldm` command, check if it's installed: `which ldm`. If not found, tell the user: "I need to install the LDM OS CLI first. That's one npm package (`npm install -g @wipcomputer/wip-ldm-os`) that gives us the `ldm` command. It doesn't install anything else until you say so." Never show the user a "command not found" error you already knew would happen.
|
|
341
|
+
|
|
215
342
|
**Always dry-run first.** Before installing or making changes, run with `--dry-run` so the user can see exactly what will happen. Only proceed when the user explicitly says to.
|
|
216
343
|
|
|
217
344
|
**Never touch sacred data.** The installer never overwrites: crystal.db, agent data, secrets, state files. Code gets updated. Data stays.
|