Zero-config persistent memory for Claude with automatic cost savings. Use when you need to remember project context, reduce API token costs, track learned patterns, manage memories across sessions, or curate/clean up memories. Automatically compresses context 6x and saves 84% on API costs.
Persistent memory for Claude with proven 84.3% cost savings through context compression and intelligent memory management.
MemoryLane provides persistent memory across sessions with automatic cost optimization:
Activate MemoryLane when the user:
Start by checking what MemoryLane knows about the project:
```bash
python3 src/cli.py status
```
This shows memory statistics, category breakdown, and cost savings.
Search memories by keyword:
```bash
python3 src/cli.py recall "<query>"
```
Example:
```bash
python3 src/cli.py recall "authentication"
python3 src/cli.py recall "database"
```
Display high-value learned patterns:
```bash
python3 src/cli.py insights
```
Show detailed token savings and cost reduction:
```bash
python3 src/cli.py costs
```
For new projects or initial setup:
```bash
python3 src/learner.py initial
```
This performs initial learning from git history (last 20 commits) and workspace structure.
**Proactive Quality Check**: When MemoryLane context is injected in system messages, scan for poor quality memories:
Signs of poor quality memories:
If you detect 2+ poor quality memories, proactively ask:
> "I notice some of the injected memories appear to be low quality (status summaries, debug notes). Would you like me to clean these up?"
**Curation Process**:
1. List all memories for review:
```bash
python3 src/cli.py curate --list
```
2. Evaluate each memory for usefulness, duplication, quality, and relevance.
3. Apply curation decisions:
```bash
python3 src/cli.py curate --apply '<JSON>'
```
JSON format:
```json
{
"decisions": [
{"id": "patt-001", "action": "KEEP"},
{"id": "lear-002", "action": "DELETE", "reason": "off-topic"},
{"id": "insi-003", "action": "REWRITE", "new_content": "Improved content"}
]
}
```
**DELETE these types**:
**KEEP these types**:
Get a specific memory:
```bash
python3 src/cli.py memory get <id>
```
Update a memory:
```bash
python3 src/cli.py memory update <id> --content "New content"
```
Delete a memory:
```bash
python3 src/cli.py memory delete <id>
```
**IMPORTANT**: Always use these commands instead of editing memories.json directly.
View or modify settings:
```bash
python3 src/cli.py config list
python3 src/cli.py config get memory.max_context_tokens
python3 src/cli.py config set memory.max_context_tokens 3000
```
Key settings:
Export memories as markdown:
```bash
python3 src/cli.py export-markdown --category patterns --output context.md
```
Create backup:
```bash
python3 src/cli.py backup --output backup.json
```
Restore from backup:
```bash
python3 src/cli.py restore backup.json
```
Start background server for low-latency operations:
```bash
python3 src/server.py start
```
Check server status:
```bash
python3 src/server.py status
```
Stop server:
```bash
python3 src/server.py stop
```
**Example 1: Remembering Important Information**
User: "Remember that this project uses PostgreSQL with SSL mode required"
You:
```bash
python3 -c "
import sys; sys.path.insert(0, 'src')
from memory_store import MemoryStore
store = MemoryStore('.memorylane/memories.json')
store.add_memory('context', 'Project uses PostgreSQL with SSL mode required', 'manual', 0.9)
print('✓ Remembered')
"
```
**Example 2: Project Onboarding**
```bash
python3 src/learner.py initial
python3 src/cli.py insights
python3 src/cli.py export-markdown --output project-context.md
```
**Example 3: Daily Development**
```bash
python3 src/cli.py status
python3 src/cli.py insights
python3 src/cli.py costs
```
Validated through comprehensive testing:
Leave a review
No reviews yet. Be the first to review this skill!
# Download SKILL.md from killerskills.ai/api/skills/memorylane-dbcagw/raw