SLM Database Migrator
Analyzes legacy database schemas and generates zero-downtime, CPU-optimized migrations and modern ORM model definitions offline.
01 / Overview & Capabilities
Analyzes legacy database schemas and generates zero-downtime, CPU-optimized migrations and modern ORM model definitions offline.
Key Features
- Direct SQL table schema analysis and dependency mapping
- Automatic compatibility matching for migrations
- Generates modern SQLAlchemy and Django ORM models
- Suggests structural indexing plans for performance improvement
02 / Standalone OS Harness Installers, CLI & Python SDK
In SLMAgents 2.0, SLM Database Migrator executes inside the 10-Plane Pure-CPU Agent Harness (slm_harness). Download a self-extracting Individual Agent + Harness OS Installer for macOS, Windows, or Linux (bundling slm_db_migration + slm_harness + the ./slm CLI), install the full 26-agent desktop suite, or install via Python pip:
1. Individual SLM Database Migrator + 10-Plane Harness Installers (All OSes)
slm_db_migration + slm_harness + ./slm CLIslm_db_migration + slm_harnessslm_db_migration + slm_harness + ./slm CLI2. Full 26-Agent Studio & Desktop OS Installers
3. 10-Plane Harness CLI (./slm) & Python pip Installation
# Option A: Install via PyPI or editable source with the 10-Plane Harness $ pip install slm-db-migration $ pip install -e ./slm_harness -e ./slm_db_migration # Option B: Run directly through the Unified 10-Plane Pure-CPU Harness CLI (./slm) $ ./slm ask "Migrate this MySQL CREATE TABLE schema to PostgreSQL with safe UP/DOWN migration scripts" $ ./slm chat # Interactive Rich TUI with 18 slash commands (/trace, /models, /arena, /undo) $ ./slm serve # 100% Offline Web AI Studio + OpenAI /v1 API at http://127.0.0.1:7860
03 / 10-Plane Pure-CPU Harness Integration (slm_harness)
Rather than executing as an isolated prompt wrapper, SLM Database Migrator is natively orchestrated by the SLMAgents 2.0 10-Plane Pure-CPU Harness (via slm_harness.runtime.legacy_bridge and CascadeRouter). Every call benefits from hybrid llama.cpp GGUF (Q4_K_M) + Quantized INT4/INT8 CPU execution, watermarked LRU memory governance, grammar-constrained decoding, and deterministic verification at $0 API cost:
| Harness Plane | Subsystem | How It Powers SLM Database Migrator on Pure CPU |
|---|---|---|
| Plane 6 | CascadeRouter (<35ms) |
Stage 2 (DDL Dialect / ALTER TABLE / Migration Signature) & Stage 3 (Embedding Margin) |
| Plane 2 & 5 | MemoryArena & Hybrid CPU Runtime |
Specialist Role: sql (Prem-1B-SQL GGUF Q4_K_M) + coding (Qwen2.5-Coder-1.5B INT4). Managed inside Watermark LRU MemoryArena (lite 2.6 GB / balanced 4.7 GB / power 8.2 GB) with zero-copy session sharing and automatic OOM tier step-down (8B -> 4B -> 3B -> 0.8B). |
| Plane 7 & 8 | Deterministic Verifier & Governance | Plane 7 SQLite/PostgreSQL DDL AST Validator & Rollback Safety Verifier |
| Plane 1, 3 & 4 | Kernel, Artifact Scratchpad & 4-Tier Memory | SQLite WAL CheckpointStore (/fork, /rewind, /undo), content-addressed artifact://<sha12> handles to prevent prompt bloat, and hybrid SQLite FTS5 BM25 + HNSW vector memory. |
04 / Source Checkout (Git Sparse-Checkout)
Clone this agent alongside the 10-Plane Pure-CPU Harness (slm_harness) from the monorepo using Git sparse-checkout — no need to download all 26 agents:
Option 1 — Sparse Checkout with 10-Plane Harness (Recommended)
# 1. Create and enter a new directory $ mkdir slm_db_migration_workspace && cd slm_db_migration_workspace # 2. Initialise empty git repo and add remote $ git init $ git remote add origin https://github.com/t00114218-stack/SLMAgents.git # 3. Enable sparse-checkout for both slm_harness and slm_db_migration $ git sparse-checkout init --cone $ git sparse-checkout set slm_harness slm_db_migration # 4. Pull the 10-Plane Harness and agent source $ git pull origin main
Option 2 — Full Repository Clone
$ git clone https://github.com/t00114218-stack/SLMAgents.git $ cd SLMAgents $ ./slm doctor
Note: After checkout, install the harness and agent in editable mode with pip install -e ./slm_harness -e ./slm_db_migration or download the pre-packaged OS Harness Installer above.
05 / Configuration & API Reference
Constructor Parameters
Instantiate SLMDBMigrator with performance options:
| Parameter | Type / Default | Description |
|---|---|---|
| model_path | str | None | Explicit path to GGUF (Q4_K_M) or quantized ONNX model weights. If omitted, managed automatically by the 10-Plane Harness MemoryArena. |
| cache_dir | str | None | Directory to store model weights offline. Defaults to ~/.cache/slm-db-migration/. Also settable via SLM_DATABASE_MIGRATOR_CACHE_DIR. |
| n_threads | int | 4 | CPU thread count for 10-Plane Harness inference (auto-tuned to physical P-cores). Optimize for CPU core count. Also settable via SLM_DATABASE_MIGRATOR_N_THREADS. |
Methods
| Method Signature | Return Type | Description |
|---|---|---|
generate_migration(from_schema, to_schema, system_prompt=None, user_input=None) | str | Compares two SQL schemas and outputs ALTER TABLE SQL migration commands. |
Method Parameters (Execution Customization)
All main execution methods accept optional system routing parameters:
| Parameter | Type / Default | Description |
|---|---|---|
| system_prompt | str | None | Optional custom system prompt instruction to override the default system template response parameters. |
| user_input | str | None | Optional additional user-supplied target text variables or contextual keys. |
Quick Start
from slm_db_migration import SLMDBMigrator
migrator = SLMDBMigrator()
migration_sql = migrator.generate_migration(
from_schema=from_schema,
to_schema=to_schema,
system_prompt="Strict zero-downtime rules",
user_input="Postgres compatibility"
)
print(migration_sql)
Environment Variables
Configure agent parameters globally using environment values:
| Environment Variable | Default | Purpose |
|---|---|---|
| SLM_DATABASE_MIGRATOR_N_THREADS | 4 | Sets CPU inference execution threads. |
| SLM_DATABASE_MIGRATOR_CACHE_DIR | ~/.cache/slm-db-migration/ | Default directory to store local GGUF (Q4_K_M) and quantized INT4/INT8 model weights (shared with ~/.slm_harness/models). |
CPU Performance Tuning
To run the SLMDBMigrator engine efficiently on CPU under 1.5 GB memory footprint:
- Match Threads to Core Count: Set
n_threadsorSLM_DATABASE_MIGRATOR_N_THREADSto match the physical CPU core count. - Sequential Processing: Avoid concurrent processing when batch files are large.
- Garbage Collection: Clear variables and run
gc.collect()to release model RAM blocks after execution.
Verified Input & Output Logs
Diagnostic execution console response running locally on CPU:
→ INPUT (To-Schema):
CREATE TABLE users (id INT PRIMARY KEY, name TEXT, email TEXT);
← OUTPUT:
{
'migration_sql': 'ALTER TABLE users ADD COLUMN email TEXT;',
'sandbox_result': 'Migration verified successfully in SQLite sandbox.'
}