shieldcortex 2.4.5 → 2.4.6
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/README.md +38 -5
- package/package.json +7 -3
package/README.md
CHANGED
|
@@ -209,14 +209,47 @@ curl -X POST http://localhost:3001/api/v1/quarantine/1/reject
|
|
|
209
209
|
|
|
210
210
|
## OpenClaw Integration
|
|
211
211
|
|
|
212
|
+
**One command. Persistent memory for every OpenClaw session.**
|
|
213
|
+
|
|
214
|
+
```bash
|
|
215
|
+
sudo npx shieldcortex openclaw install
|
|
216
|
+
```
|
|
217
|
+
|
|
218
|
+
This installs the **cortex-memory** hook directly into OpenClaw's bundled hooks directory. No configuration needed.
|
|
219
|
+
|
|
220
|
+
### What It Does
|
|
221
|
+
|
|
222
|
+
```
|
|
223
|
+
Session Start During Session Session End (/new)
|
|
224
|
+
│ │ │
|
|
225
|
+
▼ ▼ ▼
|
|
226
|
+
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
|
|
227
|
+
│ Inject past │ │ "remember │ │ Auto-extract│
|
|
228
|
+
│ context │ │ this: ..." │ │ decisions, │
|
|
229
|
+
│ into agent │ │ → save │ │ fixes, etc. │
|
|
230
|
+
└─────────────┘ └─────────────┘ └─────────────┘
|
|
231
|
+
```
|
|
232
|
+
|
|
233
|
+
| Feature | What Happens |
|
|
234
|
+
|---------|--------------|
|
|
235
|
+
| **Context Injection** | On session start, relevant past memories are injected into the agent's bootstrap context |
|
|
236
|
+
| **Keyword Triggers** | Say "remember this:" or "don't forget:" followed by content to save it with critical importance |
|
|
237
|
+
| **Auto-Extraction** | On `/new`, the hook extracts architecture decisions, bug fixes, and learnings from the ending session |
|
|
238
|
+
| **Security** | All content passes through the 5-layer defence pipeline before storage |
|
|
239
|
+
|
|
240
|
+
### Shared Memory
|
|
241
|
+
|
|
242
|
+
The database (`~/.shieldcortex/memories.db`) is shared with Claude Code. Memories created in OpenClaw appear instantly in Claude Code sessions, and vice versa.
|
|
243
|
+
|
|
244
|
+
### Commands
|
|
245
|
+
|
|
212
246
|
```bash
|
|
213
|
-
npx shieldcortex openclaw install
|
|
247
|
+
sudo npx shieldcortex openclaw install # Install hook
|
|
248
|
+
sudo npx shieldcortex openclaw uninstall # Remove hook
|
|
249
|
+
npx shieldcortex openclaw status # Check status
|
|
214
250
|
```
|
|
215
251
|
|
|
216
|
-
|
|
217
|
-
- Auto-save on `/new` command
|
|
218
|
-
- Context injection on bootstrap
|
|
219
|
-
- Keyword triggers ("remember this...")
|
|
252
|
+
[Full documentation](docs/openclaw-integration.md)
|
|
220
253
|
|
|
221
254
|
---
|
|
222
255
|
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "shieldcortex",
|
|
3
|
-
"version": "2.4.
|
|
4
|
-
"description": "Complete memory system + security layer for AI agents. Persistent storage, semantic search, prompt injection firewall, credential protection, and audit trail. One package, full solution.",
|
|
3
|
+
"version": "2.4.6",
|
|
4
|
+
"description": "Complete memory system + security layer for AI agents. Native OpenClaw integration. Persistent storage, semantic search, prompt injection firewall, credential protection, and audit trail. One package, full solution.",
|
|
5
5
|
"main": "dist/index.js",
|
|
6
6
|
"types": "dist/index.d.ts",
|
|
7
7
|
"exports": {
|
|
@@ -57,7 +57,11 @@
|
|
|
57
57
|
"ai-memory",
|
|
58
58
|
"credential-protection",
|
|
59
59
|
"audit-trail",
|
|
60
|
-
"trust-scoring"
|
|
60
|
+
"trust-scoring",
|
|
61
|
+
"openclaw",
|
|
62
|
+
"moltbot",
|
|
63
|
+
"clawdbot",
|
|
64
|
+
"coding-assistant"
|
|
61
65
|
],
|
|
62
66
|
"author": "Michael Kyriacou",
|
|
63
67
|
"license": "MIT",
|