Alex/true-recall
1
0
Fork 0
Code Pull Requests Activity

security: Remove private IPs and paths from repository

Browse Source 
- Replace all 10.0.0.x IPs with placeholders
- Replace absolute paths with ~/ shorthand
- Replace specific timestamps with placeholders
- No sensitive data in public repo
This commit is contained in:
root
2026-02-24 21:02:53 -06:00
parent 1739c93455
commit 2d3ed6cebb
2 changed files with 40 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
README.md
View File

@@ -2,7 +2,7 @@
**Project:** Gem extraction and memory recall system
**Status:** ✅ Active & Verified
**Location:** `/root/.openclaw/workspace/.projects/true-recall-v2/`
**Location:** `~/.openclaw/workspace/.projects/true-recall-v2/`
**Last Updated:** 2026-02-24 19:02 CST
---
@@ -30,10 +30,10 @@ openclaw status
sudo systemctl status mem-qdrant-watcher
# View recent captures
curl -s http://10.0.0.40:6333/collections/memories_tr | jq '.result.points_count'
curl -s http://<QDRANT_IP>:6333/collections/memories_tr | jq '.result.points_count'
# Check collections
curl -s http://10.0.0.40:6333/collections | jq '.result.collections[].name'
curl -s http://<QDRANT_IP>:6333/collections | jq '.result.collections[].name'
```
---
@@ -138,7 +138,7 @@ TrueRecall v2 extracts "gems" (key insights) from conversations and injects them
**File:** `skills/qdrant-memory/scripts/realtime_qdrant_watcher.py`
**What it does:**
- Watches `/root/.openclaw/agents/main/sessions/*.jsonl`
- Watches `~/.openclaw/agents/main/sessions/*.jsonl`
- Parses each turn (user + AI)
- Embeds with `snowflake-arctic-embed2`
- Stores to `memories_tr` instantly
@@ -288,8 +288,8 @@ python3 clean_memories_tr.py --execute --limit 100
| **Timer interval** | `5` minutes | How often the curator runs. `5 min` = fast backlog clearing. `30 min` = balanced. `60 min` = minimal overhead. |
| **Batch size** | `100` | Max memories sent to curator per run. Higher = fewer API calls but more memory usage. |
| **Max gems per run** | *(unlimited)* | Hard limit on gems extracted per batch. Not set by default — extracts all found gems. |
| **Qdrant URL** | `http://10.0.0.40:6333` | Vector database endpoint. Change if Qdrant runs on different host/port. |
| **Ollama URL** | `http://10.0.0.10:11434` | LLM endpoint for gem extraction. Change if Ollama runs elsewhere. |
| **Qdrant URL** | `http://<QDRANT_IP>:6333` | Vector database endpoint. Change if Qdrant runs on different host/port. |
| **Ollama URL** | `http://<OLLAMA_IP>:11434` | LLM endpoint for gem extraction. Change if Ollama runs elsewhere. |
| **Curator LLM** | `qwen3:30b-a3b-instruct` | Model for extracting gems. `30b` = best quality (~3s). `4b` = faster but needs JSON fallback. |
| **User ID** | `rob` | Owner identifier for memories. Used for filtering and multi-user setups. |
| **Source collection** | `memories_tr` | Qdrant collection for raw captured memories. |
@@ -324,7 +324,7 @@ python3 clean_memories_tr.py --execute --limit 100
### 6. memory-qdrant Plugin
**Location:** `/root/.openclaw/extensions/memory-qdrant/`
**Location:** `~/.openclaw/extensions/memory-qdrant/`
**Config (openclaw.json):**
```json
@@ -347,7 +347,7 @@ python3 clean_memories_tr.py --execute --limit 100
### Core Project
```
/root/.openclaw/workspace/.projects/true-recall-v2/
~/.openclaw/workspace/.projects/true-recall-v2/
├── README.md # This file
├── session.md # Detailed notes
├── curator-prompt.md # Extraction prompt
@@ -377,8 +377,8 @@ python3 clean_memories_tr.py --execute --limit 100
| File | Purpose |
|------|---------|
| `/root/.openclaw/extensions/memory-qdrant/` | Plugin code |
| `/root/.openclaw/openclaw.json` | Configuration |
| `~/.openclaw/extensions/memory-qdrant/` | Plugin code |
| `~/.openclaw/openclaw.json` | Configuration |
| `/etc/systemd/system/mem-qdrant-watcher.service` | Service file |
---
@@ -387,7 +387,7 @@ python3 clean_memories_tr.py --execute --limit 100
### memory-qdrant Plugin
**File:** `/root/.openclaw/openclaw.json`
**File:** `~/.openclaw/openclaw.json`
```json
{
@@ -400,8 +400,8 @@ python3 clean_memories_tr.py --execute --limit 100
"embeddingModel": "snowflake-arctic-embed2",
"maxRecallResults": 2,
"minRecallScore": 0.7,
"ollamaUrl": "http://10.0.0.10:11434",
"qdrantUrl": "http://10.0.0.40:6333"
"ollamaUrl": "http://<OLLAMA_IP>:11434",
"qdrantUrl": "http://<QDRANT_IP>:6333"
},
"enabled": true
}
@@ -430,11 +430,11 @@ python3 clean_memories_tr.py --execute --limit 100
```bash
# Count points
curl -s http://10.0.0.40:6333/collections/memories_tr | jq '.result.points_count'
curl -s http://10.0.0.40:6333/collections/gems_tr | jq '.result.points_count'
curl -s http://<QDRANT_IP>:6333/collections/memories_tr | jq '.result.points_count'
curl -s http://<QDRANT_IP>:6333/collections/gems_tr | jq '.result.points_count'
# View recent captures
curl -s -X POST http://10.0.0.40:6333/collections/memories_tr/points/scroll \
curl -s -X POST http://<QDRANT_IP>:6333/collections/memories_tr/points/scroll \
-H "Content-Type: application/json" \
-d '{"limit": 3, "with_payload": true}' | jq '.result.points[].payload.content'
```
@@ -456,7 +456,7 @@ openclaw gateway status
Send a message, then check:
```bash
# Should increase by 1-2 points
curl -s http://10.0.0.40:6333/collections/memories_tr | jq '.result.points_count'
curl -s http://<QDRANT_IP>:6333/collections/memories_tr | jq '.result.points_count'
```
---
@@ -470,8 +470,8 @@ curl -s http://10.0.0.40:6333/collections/memories_tr | jq '.result.points_count
sudo journalctl -u mem-qdrant-watcher -f
# Verify dependencies
curl http://10.0.0.40:6333/ # Qdrant
curl http://10.0.0.10:11434/api/tags # Ollama
curl http://<QDRANT_IP>:6333/ # Qdrant
curl http://<OLLAMA_IP>:11434/api/tags # Ollama
```
### Plugin Not Loading