Agents Towards Production

Active
GitHub Jupyter Notebook NOASSERTION

Description

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

Key Features

  • 28 production-grade tutorials — Covering stateful workflows, vector memory, web search APIs and more
  • End-to-end coverage — From Docker deployment, FastAPI endpoints to security guardrails and GPU scaling
  • Multi-agent coordination — Teaching multi-Agent collaboration architecture design and implementation
  • Observability & evaluation — Including logging, monitoring, testing and evaluation for production
  • Browser automation — Tutorials cover agent browser automation operations
  • Code-first — All tutorials as Jupyter Notebooks, ready to run

Use Cases

💡 Learning how to advance AI agents from prototype to production
💡 Mastering best practices for RAG systems and vector database integration
💡 Building production-grade agent applications with security guardrails
💡 Learning Docker and GPU deployment methods for agents
💡 Understanding multi-agent coordination and observability approaches

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (21.4k stars)
  • Responsive to issues, low backlog

⚠️ Limitations

  • No clear open-source license

Quick Start

```bash
# Clone the repository
git clone https://github.com/NirDiamant/agents-towards-production.git
cd agents-towards-production

# Follow tutorials in order:
# 1. LangGraph basics
# 2. Agent memory systems
# 3. RAG integration
# 4. Security guardrails
# 5. Deployment & monitoring
# Each tutorial is an independent Jupyter Notebook
```

Related Projects

12 Factor Agents

25.7k · TypeScript
Stale B

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

agentframeworkevaluation +2
  • · 12 core principles framework — systematic best practices from NL-to-tool-calls to stateless reducer pattern
  • · Own your context window (Factor 3) — build and manage LLM context yourself, not via framework black box
  • · Tools as structured outputs (Factor 4) — treat tool calls as structured outputs, simplify agent interaction

OpenShell

8.5k · Rust
Active A

OpenShell is the safe, private runtime for autonomous AI agents, developed by NVIDIA. Provides controlled execution environments and resource management.

rustagentframework +2
  • · Sandboxed execution environments protecting data, credentials, and infrastructure with declarative YAML policies
  • · Four defense-in-depth layers: filesystem, network, process, and inference policy enforcement
  • · Hot-reloadable network and inference policies via `openshell policy set` without restarting sandboxes

SwanLab

4.2k · Python
Active A+

An open-source, modern-design AI training tracking and visualization tool. Supports PyTorch, Transformers and more. Monitor and evaluate AI agent training processes.

pythonobservabilityevaluation +2
  • · Seamless integration with 50+ mainstream frameworks: native support for PyTorch, Transformers, HuggingFace Accelerate, PaddleNLP, NVIDIA NeMo RL and more, with two lines of code to connect training pipelines
  • · Rich visualization system: supports line charts, scalar plots, PR curves, ROC curves, confusion matrices, 3D point clouds, molecular structures, ECharts custom charts and 20+ chart types
  • · Multi-dimensional hardware monitoring: real-time monitoring of GPU (NVIDIA/AMD ROCm/Hygon DCU/Cambricon MLU/Moore Threads/Muxi/Iluvatar/Kunlun), disk utilization, network traffic and other hardware metrics

AgentBench

3.7k · Python
Stale C

A comprehensive benchmark to evaluate LLMs as agents (ICLR 2024), covering operating systems, databases, knowledge graphs, digital card games and more.

evaluationpythonagent +1
  • · First comprehensive benchmark evaluating LLMs as autonomous agents across 8 diverse environments
  • · Covers OS interaction, database operations, knowledge graphs, digital card games, and lateral thinking puzzles
  • · AgentBench FC integrates function-calling style prompts with AgentRL reinforcement learning framework