Download the PHP package knobik/sql-agent without Composer
On this page you can find all versions of the php package knobik/sql-agent. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
FAQ
After the download, you have to make one include require_once('vendor/autoload.php');. After that you have to import the classes with use statements.
Example:
Example:
If you use only one package a project is not needed. But if you use more then one package, without a project it is not possible to import the classes with use statements.
In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.
In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.
Some PHP packages are not free to download and because of that hosted in private repositories.
In this case some credentials are needed to access such packages.
Please use the auth.json textarea to insert credentials, if a package is coming from a private repository.
You can look here for more information.
- Some hosting areas are not accessible by a terminal or SSH. Then it is not possible to use Composer.
- To use Composer is sometimes complicated. Especially for beginners.
- Composer needs much resources. Sometimes they are not available on a simple webspace.
- If you are using private repositories you don't need to share your credentials. You can set up everything on our site and then you provide a simple download link to your team member.
- Simplify your Composer build process. Use our own command line tool to download the vendor folder as binary. This makes your build process faster and you don't need to expose your credentials for private repositories.
Please rate this library. Is it a good library?
Informations about the package sql-agent
SQL Agent for Laravel
A self-learning text-to-SQL agent that turns natural language into accurate SQL — with context, memory, and a built-in chat UI.
Beta Release — The core API is stabilizing but may still change before v1.0.
Quick Install
Add your LLM provider to .env:
Code Example
Why This Package?
- Knowledge Base — Curated table metadata, business rules, and query patterns give the LLM the context it needs
- Self-Learning — When a query fails and the agent recovers, it saves that learning. Next time, it knows.
- Multi-Layer Context — Schema introspection, semantic search, conversation history, and accumulated learnings
- SQL Safety — Configurable guardrails prevent destructive operations
How It Works
The agent uses six context layers to ground its SQL generation:
| # | Layer | What it contains | Source |
|---|---|---|---|
| 1 | Table Usage | Schema, columns, relationships | knowledge/tables/*.json |
| 2 | Human Annotations | Metrics, definitions, business rules | knowledge/business/*.json |
| 3 | Query Patterns | SQL known to work | knowledge/queries/*.json and *.sql |
| 4 | Learnings | Error patterns and discovered fixes | save_learning tool (on-demand) |
| 5 | Runtime Context | Live schema inspection | introspect_schema tool (on-demand) |
| 6 | Institutional Knowledge | Docs, wikis, external references | Custom tools (agent.tools config) |
Layers 1–3 are loaded from the knowledge base into the system prompt. Layer 4 is built up over time as the agent learns from errors. Layers 5 and 6 are available on-demand — the LLM calls them during the tool loop when it needs live schema details or external context.
Features
- Multi-LLM Support - Any provider supported by Prism PHP (OpenAI, Anthropic, Ollama, Gemini, Mistral, xAI, and more)
- Multi-Database Support - MySQL, PostgreSQL, SQLite, and SQL Server
- Self-Learning - Automatically learns from SQL errors and improves over time
- Multiple Search Drivers - Database full-text search or pgvector semantic search
- Agentic Loop - Uses tool calling to introspect schema, run queries, and refine results
- Livewire Chat UI - Ready-to-use chat interface with conversation history
- Knowledge Base System - Define table metadata, business rules, and query patterns
- SQL Safety - Configurable statement restrictions and row limits
- Evaluation Framework - Test your agent's accuracy with automated evaluations
Requirements
- PHP 8.2 or higher
- Laravel 12.x or 13.x
- Prism PHP (installed automatically as a dependency)
- An LLM API key or local Ollama installation
- Optional: Livewire 3.x for the chat UI
- Optional: PostgreSQL with pgvector for semantic similarity search via vector embeddings
Documentation
- Configuration - All config options (database, LLM, search, safety, etc.)
- Knowledge Base - Table metadata, business rules, and query patterns
- LLM & Search Drivers - Configure LLM providers and search drivers
- Artisan Commands - All available commands and options
- Programmatic API - Facade, streaming, and dependency injection
- Web Interface - Livewire chat UI and debug mode
- Evaluation - Test accuracy with automated evaluations
- Self-Learning - Automatic learning from errors
- Events - Event hooks for custom behavior
- Agent Tools - All LLM tools with parameters and JSON schemas
- Database Support - MySQL, PostgreSQL, SQLite, SQL Server
- Troubleshooting - Common issues and solutions
Testing
When testing code that uses SqlAgent, you can mock the facade:
Contributing
Please see CONTRIBUTING.md for details.
License
SQL Agent for Laravel is open-sourced software licensed under the Apache-2.0 License.
All versions of sql-agent with dependencies
PHP Build Version
Package Version
Requires
php Version
^8.2
illuminate/support Version ^12.0|^13.0
illuminate/database Version ^12.0|^13.0
illuminate/console Version ^12.0|^13.0
prism-php/prism Version ^0.100
illuminate/support Version ^12.0|^13.0
illuminate/database Version ^12.0|^13.0
illuminate/console Version ^12.0|^13.0
prism-php/prism Version ^0.100
The package knobik/sql-agent contains the following files
Loading the files please wait ...