Ollama plugins

Build and deploy production-grade LLM applications with LangGraph for agent orchestration, advanced RAG pipelines leveraging vector and hybrid search, prompt engineering patterns, and automated evaluation. Covers embedding model selection, vector index optimization, and multi-agent architectures for document Q&A, chatbots, and semantic search over proprietary data.

Orchestrate multi-LLM workflows across providers (Claude, Gemini, Codex, Copilot) for the full software lifecycle — research, architecture, implementation, code review, security audit, testing, and delivery — using structured Double Diamond phases and autonomous agents.

Explore and analyze codebases using semantic search, dependency graphs, and context artifacts to understand architecture, find functions and types, trace features, and inspect schemas or specs.

Optimize Python deep learning models using Adam, SGD optimizers, learning rate schedulers, and regularization to improve accuracy and reduce training time. Generate production-ready AI/ML code from context analysis, including validation, error handling, performance metrics, insights, artifacts, and documentation.

Explain machine learning model predictions using SHAP, LIME, and feature importance to identify influential features and debug behavior. Generate production-ready AI/ML code from context, including validation, error handling, performance metrics, insights, artifacts, and documentation.

Generate test fixtures that mock LLM responses, tool calls, errors, multi-turn loops, embeddings, and structured output across multiple AI providers for use with Copilot Kit's aimock library.

Evaluate single ML models or compare multiple ones on test datasets across classification, regression, NLP, and generative tasks. Compute metrics, statistical significance, inference performance, costs, robustness, bias checks; generate visualized reports with confusion matrices, performance profiles, tables, rankings, and recommendations.

Rapidly implement production-ready AI/ML features in apps: integrate LLMs with prompt engineering and response handling, build ML pipelines for recommendation systems, add computer vision for visual search, and enable intelligent automation using OpenAI, Anthropic, LangChain, Hugging Face, or Ollama.

Rapidly implement production-ready AI/ML features in apps: integrate LLMs via prompt engineering and response handling, build ML pipelines for user behavior-based recommendations, add computer vision for photo-based product search, and deploy intelligent automations.

Rapidly implement production-ready AI/ML features in apps, including LLM integrations with prompt engineering, ML pipelines for recommendations, computer vision for visual search, and intelligent automation, using a specialized agent.

Query, search, manage, and explore Weaviate vector databases using natural language, semantic/hybrid/keyword methods; import data from PDF/CSV/JSON files; generate example datasets; get AI answers with source citations; bootstrap clusters—all integrated into your coding workflow for rapid AI app prototyping.

Prevents unsafe agent actions with pre-tool guards (rm -rf, data exfiltration, unsafe publishes), enforces structured development modes (TDD, debugging, sprint), and scores session quality with 4D weighting to produce handoff artifacts for production-grade AI coding sessions.

Index project documentation, codebases, and knowledge graphs for hybrid retrieval: BM25 keywords, semantic similarity, GraphRAG relationships, or fused multi-mode search. Retrieve cited chunks with scores to research dependencies, errors, and concepts in seconds using Ollama, OpenAI, or Anthropic.

Build provider-agnostic, type-safe streaming LLM chats with tools, agent loops, and multimodal support directly in React and Next.js apps using hooks like useChat, compatible with OpenAI, Anthropic, Gemini, Ollama.

Orchestrate self-hosted AI agents via Station CLI to create agents, run tasks with 55+ MCP tools, manage environments, deploy teams, configure providers and backends through browser UI or CLI, and monitor executions with OpenTelemetry telemetry.

Delegate end-to-end ML engineering workflows to specialized agents that construct data preparation and training pipelines with feature engineering and hyperparameter tuning, optimize inference through quantization, pruning, batching, and edge deployment, and manage MLOps for model versioning, monitoring, A/B testing, and production orchestration.

Intelligently route AI tasks across 20+ LLM providers (OpenAI, Anthropic, Gemini, Ollama, etc.) using complexity-first model selection to minimize costs while preserving output quality. Automatically classify prompts and dispatch to the cheapest capable model, track cross-session savings, and receive weekly cost digests via Slack/Discord.

Run multi-agent AI collaboration workflows in Claude via TeamMCP: connect agents to shared channels, DMs, tasks, project state, and inbox; automate standups, reviews, state updates, context search; bridge to WeChat; route to other AI providers like Ollama.

Unify Python LLM API calls across 100+ providers like OpenAI, Anthropic, Ollama, and llamafile servers using OpenAI format, with built-in retries, fallbacks, exception handling, and cost tracking.

Enforce AI-assisted development workflows with governance constraints, adversarial review, literacy assessment, harness health monitoring, and CUPID code reviews across multiple repositories

Semantically search codebases using natural language queries and dependency graphs, then perform tasks like root cause analysis, safe refactoring, PR review, codebase onboarding, and commit message generation with blast radius awareness.

Routes OpenAI-compatible clients through FreeRide, a local gateway that distributes inference requests across free-tier AI providers (OpenRouter, Groq, NVIDIA NIM, Cloudflare Workers AI, HuggingFace). Detects a running FreeRide instance and wires any OpenAI-shaped client against it for cost-free model access.

Delegate coding tasks to OpenAI Codex, Google Gemini, or Ollama models for generation, review, refactoring, and fixes; compare responses across LLMs; get proactive second opinions on architecture, design, and security; run iterative review loops with build/test verification until clean; generate AI images via Gemini.

Deploy full Home Assistant smart home platforms on Ubuntu servers via Docker Compose, configure Lovelace dashboards, automations, energy monitoring, cameras, sensors, and local LLM voice assistants with Ollama; manage entities, troubleshoot issues, audit security, and optimize via natural language commands, YAML generation, and agentic workflows.

Search, read, edit, and manage an Obsidian-style markdown vault with hybrid full-text and semantic search, backlink graph, and git versioning. Supports local LLM embeddings via Ollama for AI-powered note retrieval and reasoning.

Install modular skills to add messaging channels (Discord, Slack, Telegram, WhatsApp, Gmail, Emacs), AI integrations (Ollama, Parallel, OpenAI Whisper), multimodal tools (image vision, voice transcription, PDF extraction), code review automation (Qodo), CLI access, menu bar status, and runtime switches to NanoClaw agents via guided git merges, setups, and configurations.

Build production-grade LLM apps in Python: implement RAG pipelines with embeddings and hybrid search, design LangChain/LangGraph agents, optimize prompts, tune vector indexes, and evaluate performance using AI agents, skills, and commands for architecture, code gen, and benchmarking.

Search, manage, and embed project documentation with zero-config RAG — ingest docs from files, git history, or web crawls, run semantic/keyword search, benchmark retrieval quality, and keep knowledge bases synced with code.

Equip Claude Code and compatible AI agents with biomimetic long-term memory via local MCP server. Recall relevant repo facts, user preferences, prior fixes, and architecture decisions before coding tasks; curate and store high-salience context during workflows; consolidate episodic data into compact semantic memory for persistent continuity across sessions.

Enables Claude Code to collaborate with multiple AI backends (Codex, Gemini, Ollama, Claude) through structured Q&A rallies, second-opinion calls, and iterative refinement rounds. Developers can delegate tasks to backend agents, get feedback loops, and synthesize results across models.

Automate end-to-end network infrastructure delivery on Itential Platform using AI agents and CLI commands: start from use case specs or reverse-engineer projects to generate requirements, feasibility assessments, designs, builds via FlowAgent/IAG services/workflows, device/golden config management, compliance checks, and as-built documentation.

Orchestrate a sovereign fleet of 150+ specialized AI agents with persistent memory, identity, and governance across multiple coding tools (Claude Code, Cursor, etc.) — run multi-step workflows, cross-repo coordination, security attestation, and vault-based knowledge management for autonomous agent ecosystems.

Swiss legal intelligence for precedent research, case strategy, legal drafting, and citation verification across all 26 cantons with attorney-client privilege protection.

Generate professional PPTX presentations with custom themes, bullet slides, images, tables, and shapes using python-pptx; create customizable QR codes in SVG, PNG, EPS, or PDF from URLs, text, WiFi, or contacts; extract clean markdown from PDFs by rendering pages to images and running local GLM-OCR via Ollama.

Set up a personal knowledge base with semantic search using PostgreSQL/pgvector and vector embeddings. Capture thoughts and retrieve them via semantic similarity, deployable with Docker or AWS RDS, and integrated with a local MCP server.

Provides a comprehensive collection of DSPy skills for building, optimizing, debugging, and deploying AI systems—covering signatures, modules, pipelines, retrieval-augmented generation, agents, evaluations, guardrails, monitoring, and deployment patterns

Iterative AI-driven code refinement workflows: submit code to ralph-o-matic for automated refinement loops, or orchestrate full development from idea to submission including brainstorming, planning, and parallel execution.

Streamlines Claude Code development with git automation, documentation audits, command optimization, and implementation plan tracking. Includes agents for verifying completion claims and auditing code quality against project requirements.

Build production-ready LLM applications by delegating to expert AI agents that engineer prompts, manage dynamic contexts with vector DBs and knowledge graphs, optimize single and multi-agent performance, and orchestrate RAG, multimodal, and enterprise AI workflows.

Delegate tasks to subagents powered by external OpenAI-compatible chat endpoints or LM Studio native APIs. Manage endpoint aliases by saving, listing, and removing them, with built-in support for MCP tools in LM Studio.

Store, semantically search, and graph-link persistent project knowledge like decisions, gotchas, patterns, and learnings across Claude sessions. Capture memories from conversations or git changes, check recent work against stored warnings, create multi-agent thinking docs, and monitor memory health with agents and CLI commands.