Build Powerful AI Agents
with Small Language Models
Production-ready framework optimized for Small Language Models. 5-10x faster with vLLM, automatic task decomposition, and multi-agent orchestration.
from effgen import Agent, load_model
# Load any Hugging Face model with vLLM
model = load_model(
"Qwen/Qwen2.5-7B-Instruct",
engine="vllm",
tensor_parallel_size=2
)
# Create agent with built-in tools
agent = Agent(
model=model,
tools=["web_search", "code_executor", "calculator"],
enable_memory=True,
enable_decomposition=True
)
# Execute complex multi-step tasks
result = agent.run("""
Research the latest AI papers from 2024,
calculate average citations for top 5,
and generate a summary report.
""")
print(result) # ✨ Magic happens!Everything You Need to Build
Production-Ready AI Agents
Optimized for Small Language Models with enterprise-grade features
Intelligent Task Decomposition
Automatically breaks down complex tasks with multi-dimensional complexity analysis and spawns specialized sub-agents.
- Automatic complexity scoring
- Sub-agent routing
- Parallel execution
Universal Tool Integration
15+ built-in tools with full MCP, A2A, and ACP protocol support. Create custom tools in minutes.
- Web search & Wikipedia
- Code execution sandbox
- MCP client/server
SLM-Optimized Prompts
Advanced prompt engineering specifically designed for smaller models with Jinja2 templates and few-shot learning.
- Template management
- Context compression
- Chain orchestration
Multi-Agent Orchestration
Coordinate multiple specialized agents with lifecycle management and agent-to-agent communication.
- Task routing
- Shared memory
- A2A protocol
Ultra-Fast vLLM Integration
Native vLLM support delivers 5-10x faster inference compared to standard Transformers. Automatic multi-GPU tensor parallelism and PagedAttention for optimal performance.
- 5-10x faster inference
- 60% memory reduction
- Auto multi-GPU support
Production Infrastructure
Docker sandboxed execution, comprehensive logging, state persistence, and enterprise security.
- YAML configuration
- Monitoring & metrics
- Secret management
Up and Running in 60 Seconds
Three simple steps to your first AI agent
Install✨
Get started with pip or choose your preferred installation method
pip install effgen[vllm]Create Agent✨
Initialize your agent with a model and tools
from effgen import Agent, load_model
model = load_model("Qwen/Qwen2.5-7B-Instruct")
agent = Agent(model=model, tools=["all"])Execute Tasks✨
Run complex multi-step tasks with a single command
result = agent.run(
"Analyze the latest tech trends and "
"create a comprehensive report"
)See effGen in Action
Real-world examples showcasing the power and versatility
Code Assistant
Generate, execute, and debug code with DeepSeek Coder. Automatic testing and validation built-in.
Research Agent
Conduct comprehensive research, summarize findings, and generate detailed reports with citations.
Data Analysis Pipeline
Load, clean, analyze data, create visualizations, and generate insights automatically.
Multi-Agent System
Coordinate specialized agents for complex workflows with A2A communication.
Join Our Growing Developer Community
Connect with thousands of developers building the future of AI agents
GitHub
Star the repo, contribute code, report issues, and stay updated with the latest releases.
Discord
Join our active community, get help, share projects, and discuss the future of AI agents.
Twitter/X
Follow us for the latest updates, announcements, tips, and community highlights.
Want to learn more about our community?
Visit our dedicated community page for resources, events, and contribution guidelines.
Explore CommunityReady to Build the Future of AI?
Join thousands of developers building next-gen agents with effGen