Train LLMs locally with zero setup

In today’s newsletter:

• Unsloth Docker Image: Train LLMs Locally with Zero Setup

• Mem0: Build AI Agents with scalable long-term memory

• ROMA: Open Source Meta-Agent Framework

Reading time: 3 minutes.

Train LLMs Locally with Zero Setup

Unsloth AI, released a Docker image that lets you train LLMs locally with zero setup.

Local training is often complex due to dependency issues or broken environments.

With this Docker image, you can bypass those problems entirely. Just pull, run, and start training.

Key Features:

• Pre-installed Unsloth environment - No need to install packages in notebooks, just import unsloth and run

• Ready-to-use notebooks - The unsloth-notebooks/ folder contains example fine-tuning notebooks

• Dual access modes - Both Jupyter Lab and SSH access available

• Non-root user setup - Runs with unsloth user for enhanced security

• GPU-optimized - Built for NVIDIA GPUs including latest Blackwell GPUs

It’s 100% Open Source.

🔗 Check out the Docker hub

Build AI agents with scalable long-term memory

Mem0 is a fully open-source memory layer that gives AI agents persistent, contextual memory across sessions.

Without memory, agents reset after every interaction, losing context and continuity, which limits their usefulness in real-world applications.

Mem0 solves this by storing and managing long-term context efficiently, ensuring agents can learn and evolve with every conversation.

Here’s how it works:

• Memory extraction – Uses LLMs to identify and store key facts from conversations while preserving full context

• Memory filtering & decay – Prevents memory bloat by removing or aging irrelevant data over time

• Hybrid storage – Combines vector search for semantic lookup with graph-based relationships for structured context

• Smart retrieval – Prioritizes memories based on relevance, recency, and importance

• Efficient context handling – Reduces token usage by sending only the most relevant memory snippets back to the model

It’s 100% Open Source.

🔗 Check out the Github Repo

ROMA: Meta-Agent Framework

Meta-agent framework for building high-performance multi-agent systems!

ROMA is an open-source meta-agent framework for building agents with hierarchical task execution.

It adopts a recursive hierarchical architecture where tasks are decomposed into subtasks, agents handle the subtasks, and results are aggregated upward.

The goal is to simplify the development of complex agent workflows by making task decomposition, coordination, and tracing more manageable.

Key components:

• Atomizer: Determines whether a task is “atomic” (directly executable) or requires planning.

• Planner: Breaks down non-atomic tasks into subtasks.

• Executor: Executes atomic tasks using LLMs, APIs, or even other agents.

• Aggregator: Collects results from subtasks and merges them into a parent output.

• The recursion loop follows: solve(task) → decompose → solve(subtasks) → aggregate results.

🔗 Check out the Github repo

That’s a Wrap

That’s all for today. Thank you for reading today’s edition. See you in the next issue with more AI Engineering insights.

PS: We curate this AI Engineering content for free, and your support means everything. If you find value in what you read, consider sharing it with a friend or two.

Your feedback is valuable: If there’s a topic you’re stuck on or curious about, reply to this email. We’re building this for you, and your feedback helps shape what we send.

WORK WITH US

Looking to promote your company, product, or service to 150K+ AI developers? Get in touch today by replying to this email.