Tag
Your own MCP server exposes your data and functions to any AI assistant through the Model Context Protocol. With the official Python SDK and its FastMCP class you write a server in about twenty lines: you define tools, resources and prompts as type-annotated functions, and you connect it to Claude, Cline or Goose over stdio or HTTP.
DeepEval is the open-source framework for evaluating AI systems as if you were writing Pytest tests: you define cases, pick research-backed metrics (G-Eval, faithfulness, tool correctness) and get a score from 0 to 1 that passes or fails each response, both on your machine and in continuous integration.
DSPy is a Python framework from Stanford that treats calls to an LLM as code: you define signatures with typed inputs and outputs, pick a module such as chain of thought, and let an optimizer write the prompts for you from examples and a metric. That way you compile programs instead of hand-tuning prompts.
Outlines is a Python library for constrained generation: it forces the model to produce output that conforms to a JSON schema, a regular expression or a grammar, with a guarantee by construction rather than statistics. It works with vLLM, Transformers, Ollama and llama.cpp, and its Rust engine adds barely any overhead per token.
Instructor is the most widely used Python library for getting reliable structured outputs from a language model: you define the result you expect as a Pydantic model, Instructor patches the client so the model honours it, and it retries on its own, with the validation error included, until it returns a valid, already-typed object.
Function calling lets a model you run with Ollama on your own machine ask your code to call a function (check the weather, query a database) and use the result to answer. Ollama has supported tools since July 2024; in 2026 models such as qwen3 and llama3.3 do it with reasonable reliability.
Qwen-Agent is the Qwen team's official framework for giving their models tools: function calling, a sandboxed code interpreter, RAG and MCP. It is on version 0.0.34, released in February 2026, has around 16,800 GitHub stars and holds the canonical implementation of Qwen3 tool calling, both in the cloud and on your own machine.
Agno, the Python framework formerly known as Phidata, builds AI agents with one clear goal: performance. It creates each agent in about two microseconds and uses roughly 3.75 KiB of memory, so it scales to thousands of concurrent agents. It offers agents, teams and workflows, over twenty model providers and the AgentOS runtime.
Google ADK (Agent Development Kit) is Google's open-source framework for building, evaluating and deploying AI agents. It is code-first, works with Gemini and other models via LiteLLM, and offers workflow agents, tools and memory. Version 2.5.0 landed in July 2026 and deploys straight to Vertex AI.
smolagents is Hugging Face's agent library: in under a thousand lines of code it lets you build an agent that reasons by writing Python instead of filling in JSON. Its CodeAgent runs those actions as code, takes around 30% fewer steps than classic tool calling and works with any model, local or API.
Pydantic AI is the agent framework from the Pydantic team: you build agents in Python where every model output is validated against a type you define. You declare the expected answer as a Pydantic model and the agent guarantees that structure, with dependency injection, tools and support for more than twenty model providers.
Python 3.13 introduce de forma experimental la ejecución sin GIL mediante PEP 703. Tras unos meses de rodaje empiezan a verse pruebas reales fuera del laboratorio. Conviene entender bien qué ganas, qué pierdes y qué no cambia todavía.
Polars lleva dos años pidiendo relevo a pandas. Con Polars 1.x estable y una comunidad creciente, toca revisar dónde de verdad compensa migrar, dónde pandas sigue ganando y cómo convivir entre ambos sin pagar dos veces.
Python 3.12, released in October 2023, brings inline generic syntax through PEP 695, tracebacks that pinpoint the exact error, and an average speedup of around 5% over 3.11 on pyperformance, plus experimental sub-interpreters with their own GIL. Migrating from 3.10 or 3.11 is straightforward: major libraries already ship compatible wheels.
LangChain is a Python framework that unifies building LLM applications: prompt templates, retrievers over vector databases, function-calling agents, and conversational memory. It earns its keep in fast prototypes and multi-model systems, but for a single well-defined production use case, direct code usually stays more maintainable.
Chroma is the easiest vector database to get started with embeddings and semantic search: install it with pip install chromadb, no extra infrastructure required, and it exposes a minimal API (add, query, delete). It suits prototypes and mid-sized RAG systems well; past a few million vectors, Qdrant or Milvus scale better.
OpenAI Code Interpreter extends ChatGPT Plus with an isolated Python sandbox: it runs code on demand, reads files you upload (CSV, Excel, PDF, images, ZIPs) and returns results plus charts within the same chat. Sessions are ephemeral and offline, but remarkably effective for exploratory ad-hoc analysis without spinning up a notebook.
Spark DataFrames are distributed, schema-based tables that the Catalyst engine optimises automatically, while pipelines chain those transformations into a reproducible end-to-end flow. Together they let you process large data volumes efficiently across a cluster, scaling from a laptop to hundreds of nodes without rewriting code.
LazyPredict is a Python library that automatically evaluates dozens of scikit-learn classification and regression models on your dataset in seconds, without writing training code for each one. LazyClassifier and LazyRegressor return a comparative metrics table that shows which models are worth tuning further.
