A local, keyboard-driven diff viewer built for the huge changes coding agents produce - and it remembers what you have already seen.
Python
The Python language, its runtime and the wide library ecosystem built on it.
12 apps, 21 skills and 13 MCP servers tagged Python.
Apps
A vectorless RAG engine that builds a tree index of long PDFs and lets an LLM reason its way to the right section, with page-level citations.
Open-source, self-hosted personal AI agent you run yourself — browser UI, terminal or your chat apps, with memory, MCP tools and scheduled automations.
Interactive coding courses with an AI tutor, covering Python, JavaScript, React, SQL and AI-assisted development through structured career paths.
Secure cloud sandboxes where AI agents can run untrusted code safely, starting in milliseconds.
The embedding database that starts as a Python import and grows into a distributed cloud service.
Serverless GPUs from a Python decorator — deploy models and batch jobs with no containers or cluster to manage.
The standard experiment tracker for machine learning, now with tracing and evaluation for LLM applications.
Open-source LLM observability — trace, evaluate, and improve AI applications with production data.
Document parsing and retrieval built for agents — turn messy PDFs into structured, queryable context.
The framework and observability platform most teams use to build, debug, and ship LLM agents.
The multi-agent framework where agents have roles and collaborate as a crew — plus a platform to run them in production.
Skills
Diagnoses wrong gradients in differentiable NVIDIA Warp programs by measuring first — comparing autodiff against finite differences on a shrunk reproduction before proposing any fix.
Official AWS skill for authoring, deploying and debugging CDK stacks — construct patterns, bootstrap, drift, resource import and the CloudFormation errors that trap people.
Build Gradio web UIs and ML demos in Python with the current API — components, layouts, events, and chat interfaces.
Find where a photo was taken: EXIF, OCR, OpenStreetMap, skyline and satellite matching, with coordinates, error radius and evidence images.
Read-only recipes for the Hugging Face Dataset Viewer API — resolve splits, paginate rows, run text search and row filters, and pull parquet URLs and column statistics.
Train bi-encoders, rerankers, SPLADE sparse encoders and ColBERT multi-vector models with the loss, evaluator and template each type actually needs.
Fine-tune object detection, image classification and SAM/SAM2 segmentation models on Hugging Face Jobs cloud GPUs, with dataset validation before you spend GPU minutes.
OpenAI's skill for language- and framework-specific secure coding: detect the stack, load the matching reference guidance, then write secure-by-default code, flag critical issues passively, or produce a prioritised vulnerability report with fixes.
Skill: Robotics Agent Skills
by arpitg1304
Ten SKILL.md modules that give coding agents real ROS engineering judgement — ROS 1 and ROS 2, design patterns, perception, testing, Docker, bringup and robot security.
Skill: Graphify
by Graphify Labs
Claude Code skill that turns any folder of code, docs, papers and images into a queryable knowledge graph, with every edge tagged as extracted, inferred or ambiguous.
Skill: Portfolio Optimization with cuOpt
by NVIDIA
GPU-accelerated Mean-CVaR and Mean-Variance portfolio construction with NVIDIA cuOpt: scenario generation, variance-capped SOCP allocations, efficient frontiers, backtests and rebalancing.
Turns a plain-language weather question into a working Earth2Studio inference script — picks the AI forecast model, a compatible data source, an IO backend, and the step count.
Skill: Pydantic Validation
by Pydantic
Pydantic's official skill for modelling untrusted data in Python — constraints, model hierarchies, validators and serialisation, plus when not to reach for a BaseModel.
Skill: VideoDB
by VideoDB
VideoDB's official skill giving an agent one interface to ingest, index, search and edit video — including live RTSP feeds and real-time desktop capture.
Skill: Agnost AI Integration
by Agnost AI
Walks a coding agent through wiring Agnost AI conversation analytics into a Python or TypeScript app — inspecting existing OpenTelemetry first and only adding an SDK when the traces are not usable.
Skill: NVIDIA NeMo Data Designer
by NVIDIA
NVIDIA's official skill for building synthetic datasets with NeMo Data Designer — describe the data you want and the agent writes a declarative generation pipeline, column by column.
Skill: Django Performance Review
by Sentry
Sentry's Django performance review skill — hunts N+1 queries, unbounded querysets, missing indexes and write loops, and reports only findings it can prove.
Skill: LLM Fine-Tuning with TRL
by Hugging Face
Fine-tune language and vision models with TRL or Unsloth — supervised, preference, and reinforcement training methods.
Skill: Hugging Face Spaces
by Hugging Face
Deploy and maintain applications on Hugging Face Spaces — SDK choice, GPU hardware, model loading, and debugging.
Skill: Data Visualization
by Anthropic
Anthropic's official data-visualization skill: pick the right chart for the data, then build it with ready-to-run matplotlib, seaborn, and plotly patterns.
Skill: MCP Builder
by Anthropic
Anthropic's guide for building high-quality MCP servers end to end — research, tool design, implementation in TypeScript or Python, testing, and a 10-question evaluation suite.
MCP servers
Context-compression MCP server that shrinks tool outputs, logs, files and RAG chunks before they reach the model, cutting 60-95% of tokens on JSON payloads.
The official W&B MCP server: query experiment runs, Weave LLM traces, artifacts and registries in natural language, and write findings back as a W&B report.
Drive live Jupyter notebooks from an agent — read and edit cells, execute code, see rich outputs, and run against local JupyterLab or a cloud sandbox.
Run AI-generated code safely in an isolated cloud sandbox, with results returned as data rather than text.
Lets AI agents scrape the web through Scrapling, with HTTP, browser and Cloudflare-bypassing stealth fetches and CSS-narrowed, sanitized output.
Astronomer's MCP server for Apache Airflow: 30+ tools over the Airflow REST API, with consolidated helpers that explore a DAG, diagnose a failed run or summarise system health in a single call. Works with Airflow 2.x and 3.x.
Fivetran's own MCP server exposes the Fivetran REST API to agents as discoverable tools, so an assistant can check sync status, inspect connections and destinations, and trigger syncs from chat.
MCP: ROS MCP Server
by robotmcp
Drive real robots from an AI assistant. Bridges MCP clients to ROS 1 and ROS 2 through rosbridge — publish topics, call services, send action goals and read sensors with no change to robot code.
MCP: CVE MCP Server
by mukul975
Vulnerability triage for AI agents: 28 security tools across 24 free intelligence sources — NVD, EPSS, CISA KEV, MITRE ATT&CK, Shodan and VirusTotal — behind a single triage_cve call.
MCP: Alpaca MCP Server
by Alpaca Markets
Alpaca's official MCP server for trading stocks, options and crypto, plus market data and portfolio analysis, in plain language.
MCP: Couchbase Guru
by Couchbase
Couchbase's documentation agent as a single MCP tool: ask a question about any Couchbase product, SDK or version and get an answer with source links. No cluster and no credentials.
MCP: Prefect
by Prefect
Prefect's official read-only MCP server for inspecting flow runs, deployments and automations on Prefect Cloud or self-hosted, with a docs proxy for current CLI and SDK guidance.
MCP: Okta MCP Server
by Okta
Okta's official open-source MCP server: manage users, groups, apps, policies and branding in your Okta org from an AI agent, with scope-gated tools and confirmation on destructive actions.
Related tags
Tags that appear alongside this one, ranked by how often.

