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, 14 skills and 8 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
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.
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.
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.
Alpaca's official MCP server for trading stocks, options and crypto, plus market data and portfolio analysis, in plain language.
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.