Ollama plugins

End-to-end AI and data engineering suite covering data pipelines, ML model development, LLM architecture, MLOps, database optimization, and prompt engineering for production systems.

Multi-LLM orchestration that automates the full development lifecycle — research, design, code review, testing, security auditing, and documentation — by routing tasks across multiple AI providers (Gemini, Codex, Ollama, Copilot) with structured workflows and quality gates.

Run terminal commands, manage processes, and access files beyond the workspace, including structured documents like PDFs, Excel, and DOCX, all from within Claude Code. Also provides system health checks, persistent shell sessions, SSH connections, and a Markdown knowledge base for AI agents.

Run AI models locally with Ollama — automates installation, GPU setup, and hardware-based model selection, then provides Python/Node.js/REST clients for private inference at zero cost.

Query your codebase using natural language by building a local knowledge graph from your repository, with CLI commands to scaffold multi-agent projects, initialize environment configs for LLM providers, and refresh indexed data.

Generate test fixtures that mock LLM responses, tool calls, error injection, multi-turn agent loops, embeddings, structured output, and sequential responses across multiple AI providers.

Run persistent Claude Code agents that route messages and tasks across chat platforms (Telegram, Discord, WhatsApp) with integrations for Gmail, PDF extraction, local LLMs, and code review automation. Includes conversation management and extension support.

Run local AI inference on AMD hardware: route image/audio through local models on Ryzen AI, serve LLMs on Instinct GPUs with vLLM, and analyze PyTorch profiler traces for GPU kernel performance.

Build provider-agnostic type-safe LLM chat applications with streaming, tools, agent loops, and multimodal inputs using OpenAI, Anthropic, Gemini, and Ollama in React, Solid, or Next.js frontends.

Run local semantic code search on your codebase using Go AST parsing and vector embeddings from Ollama or LM Studio, then query the index through Claude via an MCP server — all offline with no cloud dependencies.

Ingest math/physics course PDFs (lectures, homework, solutions) via a vision pipeline to build structured knowledge bases, then generate exam-style drills (twin variants, blind drills, integration chains, mock exams) and grade hand-written answer PDFs using selectable OCR (Claude vision, Ollama Qwen3-VL, Tesseract) with symbolic verification.

Create, manage, and run self-hosted AI agents with 55+ MCP tools via the Station CLI, including agent creation, task execution, environment management, and team deployment.

Accelerates production LLM system development with LangGraph agent workflows, RAG retrieval evaluation, prompt optimization, and AI backend service scaffolding from reference templates.

Watch any video (URL, stream, local file) to extract scene-aware frames, OCR text, and transcribe audio, then ask questions with timestamped evidence from a persistent index. Also record UI, animations, or games and iteratively critique against pass criteria until they pass, with before/after proof.

Index codebases and documentation, then search them using keyword matching, semantic similarity, graph relationships, or a combination of all three. Supports pluggable embedding and summarization providers (Ollama, OpenAI, Anthropic, Gemini) with per-project configuration and caching.

Route LLM tasks to the optimal provider based on task complexity and cost, automatically selecting the cheapest capable model across 20+ AI providers, tracking savings, and sending digest reports to Slack or Discord.

Debug ML training failures (OOM, NaN, divergence), validate hyperparameters and configs against official docs before runs, and generate grounded implementation plans for fine-tuning, RAG, and inference pipelines using a knowledge base of 27k+ pages from Hugging Face, PyTorch, DeepSpeed, and vLLM.

Make Python LLM API calls to 100+ providers (OpenAI, Anthropic, Ollama, llamafile) using a unified OpenAI-compatible format with automatic retries, fallbacks, exception handling, and cost tracking.

Perform local-first hybrid semantic code search across your codebase with dependency graphs, cross-repo search, and impact analysis. Supports onboarding, root cause analysis, refactoring, PR review, and code generation guided by search results.

Provides a set of skills for code review, documentation, project design, and automation. Includes conventions for Go and Python, SQLite database guidance, OpenTelemetry instrumentation, and AI model fine-tuning with Unsloth.

Automatically detect a running FreeRide gateway and route any OpenAI-compatible client through it to access free-tier AI inference from providers like OpenRouter, Groq, NVIDIA NIM, Cloudflare Workers AI, and HuggingFace.

Integrate multiple LLMs (OpenAI, Gemini, Ollama) into your development workflow for second opinions, code review delegation, image generation, side-by-side model comparisons, and data format conversion — all from the terminal.

Orchestrate development workflows with infinite-context focus tasks, prompt optimization, agent/skill creation, quorum code reviews, and rules management across sessions.

Search, read, and manage markdown vaults with hybrid FTS5 + semantic search, link graph navigation, and Git-backed write/edit operations.

Deploy a team of AI/ML specialist agents for the full SDLC: architect multi-agent systems, design RAG pipelines, optimize prompts, review MCP servers, and manage AI infrastructure and testing.

Build multi-provider and hybrid LLM clients in Rust using rig-core, with support for agents, tools, extractors, RAG, and streaming across OpenAI, Anthropic, and Ollama.

A structured spec-driven development system that guides AI coding agents through project lifecycle phases: initialization, requirements, planning, execution, verification, and shipping. Provides skills, commands, and agents for context engineering, design contracts, code review, testing, debugging, documentation, and milestone management.

Run and manage local LLMs via Ollama's REST API for text generation, chat, embeddings, tool calling, structured output, and model management.

Build, optimize, and deploy production AI pipelines with DSPy using 95 skills covering the full lifecycle: signatures, LM configuration, data handling, evaluation, optimization, retrieval, adapters, tools, and deployment.

Build and manage a complete Home Assistant smart home platform: deploy Ubuntu servers with Docker, configure automations, sensors, cameras, energy monitoring, and local LLM integration via Ollama, all through natural language commands and YAML generation.

Automated setup wizard for TeaRAGs RAG system: detects environment, installs Node.js, Ollama/ONNX, Qdrant, and configures MCP server, with resumable progress and optional hardware benchmarking for performance tuning.

Relay prompts, repository context, and current conversation to backend AI agents (Claude, Gemini, Codex, Ollama, OpenCode, Antigravity) for second opinions, structured Q&A rallies, and iterative multi-model refinement loops.

Integrates Claude Code with ralph-o-matic iterative AI coding refinement loops, enabling review file generation, full workflow orchestration from brainstorming to submission, and direct code refinement.

Conduct deep research across codebases, tickets, and documents using graph-based retrieval and Jira investigation; capture knowledge as structured artifacts and knowledge graphs; and generate comprehensive documentation for AI engineering projects.

Create professional presentations, extract text from PDFs via local OCR, and generate QR codes for document workflows from within Claude Code.

Improve LLM apps and agents from real production traces: capture traces, build evals, run local optimization (GEPA), compare models/providers, and route through the Understudy gateway to reduce cost/latency and raise quality/reliability.

Store and semantically search personal thoughts and notes using vector embeddings (pgvector) and ltree scoping in a local PostgreSQL knowledge base. Install a local MCP server with tools to capture and search thoughts, choosing between bundled, Docker, native, or RDS PostgreSQL backends.

Coordinates a fleet of 144+ specialized AI agents across memory, governance, research, content, energy, marine, music, and cosmos domains with persistent vaults, cross-repo orchestration, and sovereign policy enforcement.

Orchestrates a spec-driven development workflow across multiple LLMs (Claude, Codex, Gemini, etc.) using portable Spec Kit artifacts, handling spec authoring, subagent task routing, implementation, and multi-model code review with preflight validation.

Automate git workflows, enforce code quality, and manage Claude Code configurations with commands for semantic commits, implementation planning, documentation audits, and agent orchestration.

Extend NanoClaw agents with messaging channels (WhatsApp, Telegram, Slack, Discord, Signal, X/Twitter), email (Gmail), voice transcription (Whisper or local whisper.cpp), image vision, PDF extraction, emoji reactions, agent swarms, menu bar controls, container runtime switching, CLI tools, and code review integration.

Build, deploy, and manage production-ready LangGraph agents with MCP integration, multi-agent orchestration, memory/checkpointing, and CLI accessibility. Covers the full lifecycle from graph design and state management to testing, deployment on cloud/Kubernetes, and bidirectional MCP tool exposure.

Persist project knowledge (decisions, gotchas, patterns) across Claude Code sessions with semantic search, graph linking, and agent-scoped memory. Automatically capture high-signal learnings, check work against stored gotchas, and maintain memory health via CLI commands and dedicated agents.

Run a local RAG-powered code intelligence server that indexes your repository for semantic search, symbol and graph navigation, impact analysis, and source-anchored memory, with automated memory maintenance and dangerous-command guards.

Delegate tasks to external OpenAI-compatible or LM Studio chat endpoints as a subagent, with endpoint alias management and LM Studio MCP tool support.