Zero-config persistent memory for Claude with automatic cost savings. Remembers project context, reduces API costs by 84%, tracks patterns, and manages memories across sessions. Use for remembering, recalling, context compression, cost tracking, or memory curation.
MemoryLane provides persistent memory for Claude with proven 84.3% cost savings through intelligent context compression. It remembers information across sessions in 4 categories (patterns, insights, learnings, context), compresses context 6.4x on average, tracks API cost savings in real-time, learns passively from git commits and file changes, and works out of the box with zero configuration.
Activate MemoryLane when the user:
Start by checking MemoryLane status to see memory statistics, category breakdown, and cost savings:
```bash
python3 src/cli.py status
```
Search memories by keyword when the user asks what you know or remember:
```bash
python3 src/cli.py recall "<query>"
```
Example:
```bash
python3 src/cli.py recall "authentication"
```
Display learned project insights (high-value patterns):
```bash
python3 src/cli.py insights
```
Show detailed breakdown of token savings and cost reduction:
```bash
python3 src/cli.py costs
```
When starting work on a project, perform initial learning from git history and workspace:
```bash
python3 src/learner.py initial
python3 src/cli.py insights
```
When you see MemoryLane context injected via `# Project Context (from MemoryLane)` 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?"
When user requests curation or confirms after detection:
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 (DELETE/KEEP/REWRITE):
```bash
python3 src/cli.py curate --apply '<JSON decisions>'
```
**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:**
Manage individual memories instead of editing memories.json directly:
```bash
python3 src/cli.py memory get <id>
python3 src/cli.py memory delete <id>
python3 src/cli.py memory update <id> --content "New content"
```
Export memories as markdown or create backups:
```bash
python3 src/cli.py export-markdown --category patterns --output context.md
python3 src/cli.py backup --output backup.json
python3 src/cli.py restore backup.json
```
Start sidecar server for low-latency memory operations:
```bash
python3 src/server.py start
python3 src/server.py status
python3 src/server.py stop
```
Key settings in `.memorylane/config.json`:
Configure settings via CLI:
```bash
python3 src/cli.py config get memory.max_context_tokens
python3 src/cli.py config set memory.max_context_tokens 3000
python3 src/cli.py config list
```
1. **Privacy**: All data stored locally in `.memorylane/` directory
2. **No Dependencies**: Pure Python 3.8+ (no external packages for production)
3. **Automatic Exclusions**: Respects `.env`, `secrets/`, and other sensitive patterns
4. **Backup Before Reset**: Always creates backup before destructive operations
5. **Server Optional**: CLI works standalone; server adds performance for frequent operations
**User**: "What do you know about our database setup?"
**Response**: Let me recall what I know about the database.
```bash
python3 src/cli.py recall "database"
```
**User**: "How much money has MemoryLane saved me?"
**Response**: Let me check the cost savings.
```bash
python3 src/cli.py costs
```
Leave a review
No reviews yet. Be the first to review this skill!
# Download SKILL.md from killerskills.ai/api/skills/memorylane-persistent-memory-and-cost-savings/raw