Blog
Deep-dives on agentic systems, generative computing, and the ideas behind Mellea.
Why Mellea?
Agents are just programs, patterns of control flow around generative AI. So why the 80–90% failure rate? Because they're built out of prompts, not code. Mellea is a different approach.
→Granite Switch in Mellea: one checkpoint, every adapter function
With Granite Switch, adding validation to a Mellea program — checking that an answer is grounded, that a requirement is met, that nothing in the response was hallucinated — is a single function call against the backend you're already using. One checkpoint, a dozen drop-in validations, no second pipeline to stand up.
→The Loop Needs a Gate
The industry just spent a fortnight agreeing you should write loops, not prompts. Everyone also agrees on the catch: a loop is only as good as the gate that can fail its work.
→From Linting to Tests: Doubling Functional Correctness in Qiskit IVR
Wiring functional tests into Mellea's Instruct-Validate-Repair loop nearly doubled functional correctness on the Qiskit Human Eval benchmark, on top of what static validation already provided.
→Using MCP Server Tools in Mellea
Mellea now supports MCP server tools. Discover any MCP server's tools and call them directly from a Mellea agent.
→Making Small Models Rock with Mellea
Small open-weight models can handle production-shaped work when the harness decomposes the task, validates outputs, and routes each step to the right local model.
→What Mellea Brings to DSPy: Structured Validation for Reliable AI Programs
Add semantic validation and quality guarantees to DSPy programs with Mellea's integration for structured prompting and runtime verification.
→Validate Every CrewAI Agent Output: Automatic Retry with Mellea
Mellea brings structured validation and automatic repair to CrewAI multi-agent systems through the instruct-validate-repair pattern.
→Cut LLM Costs Without Sacrificing Quality: The SOFAI Pattern in Mellea
Route most requests to a small model and escalate only hard cases to a larger one — Mellea's SOFAISamplingStrategy makes the dual-model pattern a one-line strategy swap.
→What Mellea Brings to LangChain: Structured Generative Programming for Reliable AI Applications
Learn how Mellea's generative programming patterns add structured validation, automatic retry, and inference-time scaling to LangChain applications.
→Getting Started with Mellea in Five Minutes
Install uv, pull a local model with Ollama, and build your first Mellea pipeline from scratch — no API key, no cloud, fully private.
→Mellea Meets AI Frameworks: Structured Validation for LangChain, CrewAI, and DSPy
How Mellea brings structured validation and automatic retry to LangChain, CrewAI, and DSPy
→Your LLM Provider is Down. Now What?
Use mellea's provider-agnostic backend abstraction to build LLM applications that automatically survive outages through three layers of failover: validation retries, capability escalation (SOFAI), and infrastructure switching across providers.
→Automatically Fixing Deprecated Qiskit Code with Instruct-Validate-Repair
How we used Mellea's Instruct-Validate-Repair pattern with flake8-qiskit-migration to automatically catch and fix deprecated Qiskit APIs in LLM-generated code.
→Hooks: A New Way to Extend Your LLM Application
Hooks are a simple but powerful way to tap into your LLM application's lifecycle and add custom behavior without touching your core logic.
→Outside-In and Inside-Out: Imperative, Inductive, and Generative Computing
What is “generative computing,” and is it different enough from other things to deserve a name?
→We’re thinking about AI all wrong
Presenting an opinionated view on generative AI.
→