Langchain plugins

Design and deploy LLM applications with LangGraph agents, RAG systems, vector search, and advanced prompt engineering. Covers embedding model selection, hybrid retrieval, evaluation, and production scaling for chatbots and AI assistants.

Design, build, and evaluate autonomous AI agents with behavioral testing, RAG systems, prompt engineering, and MCP server creation for external tool integration.

Build and optimize LLM applications with production-ready patterns for RAG pipelines, context window management, prompt caching strategies, and observability using Langfuse.

Build and test AI agents and MCP servers: design autonomous agents, implement RAG pipelines, manage LLM context windows, build MCP servers from scratch, and use observability with Langfuse. Includes prompt engineering, agent testing, and LangGraph patterns.

Run structured AI product evaluation and operations workflows including A/B testing, LLM agent benchmarking, product analytics, and observability.

Build, monitor, and optimize LLM applications with strategies for context management, RAG pipelines, caching, observability, and evaluation. Includes patterns for production deployment, embedding selection, vector database integration, and LLM-as-Judge evaluation.

Design, build, test, and deploy sophisticated AI agents with memory systems, RAG, LangGraph orchestration, and MCP tool integration.

Build, integrate, and debug AI-powered chat and agent features in CopilotKit projects, from setup to production across frontend and backend.

Build Retrieval-Augmented Generation (RAG) systems by connecting LLMs to vector databases for semantic search and knowledge-grounded AI. Enables document Q&A, reduces hallucinations, and integrates external knowledge bases into LLM applications.

Design LLM applications using LangChain 1.x and LangGraph to build autonomous AI agents with state management, memory, and tool integration patterns

Instrument LLM applications with OpenInference tracing for Phoenix AI observability, covering auto and manual instrumentation, custom span types, production deployment, and trace analysis.

Structured meta-prompting and spec-driven development system that guides AI coding agents through a complete project lifecycle: ideation, requirements specification, planning, execution, verification, and archival. Enforces context engineering with persistent memory, knowledge graphs, and cross-session handoffs.

Deploy specialized AI agents to automate data engineering, ML pipeline development, LLM application building, research synthesis, and prompt engineering tasks across your projects.

Build, test, and deploy LangChain, LangGraph, and Deep Agents applications with support for RAG pipelines, human-in-the-loop workflows, state persistence, parallel task dispatch, and LangSmith deployment via the mda CLI.

Accelerate building and operating production LangChain 1.0 and LangGraph 1.0 Python applications with battle-tested patterns for chains, agents, RAG, streaming, HITL, middleware, monitoring, security, and deployment.

Search 2500+ curated open-source repositories for ChatGPT, LLMs, RAG agents, and AI tools directly from Claude Code, using domain-specific keyword expansion and grep-based search.

Manage Langfuse LLM observability across the full lifecycle: installation, configuration, tracing, evaluation, cost monitoring, deployment, scaling, and incident response. Supports OpenAI, LangChain, and other LLM frameworks with CI/CD integration and production-grade patterns.

Build and deploy serverless applications and AI agents on EdgeOne Makers: cloud functions (Node.js, Python, Go), edge functions, middleware, KV/Blob storage, project scaffolding, and CLI management. Includes migration paths from LangChain, OpenAI Agents SDK, and other frameworks to the platform.

Develop Java enterprise applications with Spring Boot, AWS cloud services, and LangChain4j AI agents. Generate CRUD REST APIs, validate architecture, audit security, and test with Testcontainers.

Implements AI/ML features including language model integration, recommendation systems, computer vision, and intelligent automation with prompt engineering, ML pipelines, and model deployment

Implement AI/ML features including LLM integration, recommendation systems, computer vision, and intelligent automation with practical prompt engineering, ML pipelines, and model deployment.

Orchestrate full-stack AI development with 281 skills, 71 agents, and 112 hooks: build React/Next.js UIs, FastAPI backends, LangGraph AI workflows, manage databases, deploy to Kubernetes, run security audits, generate tests, create demo videos, and coordinate multi-agent pipelines across git worktrees.

Implements AI/ML features in applications: integrates LLMs, builds recommendation engines, adds computer vision search, and automates intelligent workflows with prompt engineering, ML pipelines, and model deployment.

Run untrusted AI agent code, browser automation, and parallel sandboxes with suspend/resume and durable workflow orchestration using the Tensorlake SDK.

Build, validate, and ship production-grade n8n workflows with AI assistance for node configuration, expressions, error handling, loops, sub-workflows, auth, binary data, and data tables. Connects to a remote n8n instance to trigger workflows, manage executions, and expose workflows as MCP tools.

Manage the full lifecycle of UiPath automation projects from within Claude Code — build, deploy, and debug RPA workflows, agents, coded apps, integration connectors, and governance policies using CLI commands directly in the chat interface.

Work with Neo4j graph databases: Cypher queries, graph modeling, Aura provisioning, GraphRAG pipelines, vector indexes, Graph Data Science algorithms, data imports, Kafka/Spark integrations, and driver management for multiple languages.

Run deterministic merge gates that statically analyze AI agent tool definitions (MCP, OpenAPI, SDK decorators) to enforce tool-use readiness policies and audit host-grant permissions before merging agent capability changes.

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

Scaffold production-grade agents, MCP servers, RAG pipelines, and REST APIs; audit code for security, performance, and quality; generate tests, CI/CD configs, and documentation across 380+ skills and 1470 agents.

Manage LLM evaluation datasets on LangSmith, build and run LLM-as-judge evaluation pipelines, and enable distributed tracing for LLM applications using LangChain auto-tracing or OpenTelemetry.

Instrument LLM applications with Arize AX observability: auto-instrument traces, manage datasets and experiments, run LLM-as-judge evaluators, optimize prompts from production data, and audit for regulatory compliance.

Manage every aspect of PostHog: run product analytics, feature flags, A/B experiments, session replays, error tracking, and LLM/APM observability. Build dashboards, alerts, and automated monitors; review code for correctness and performance; connect external data sources via REST/SQL connectors. Includes a MCP server and Claude Code session capture.

Generate production-ready LLM prompt packages with system prompts, few-shot examples, output schemas, edge cases, and evaluation criteria when asked to engineer or improve prompts.

Scans repositories to inventory ML models, training pipelines, data sources, feature pipelines, and monitoring, answering 'what ML do we have' queries for model inventory and ML assessment.

End-to-end ML/AI engineering — builds ML pipelines from feature engineering to baseline training, evaluates model performance with drift detection, designs LLM integrations (RAG, agents, fine-tuning), and creates production prompt packages with evals.

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.

Instrument, trace, evaluate, and iteratively improve AI agent behavior with MLflow, supporting observability, debugging, evaluation workflows, documentation lookup, and regression testing across Python and TypeScript frameworks like LangChain, OpenAI, and Gemini.

Run a virtual AI university in Claude Code that teaches AI/ML, robotics, medicine, and ethics through structured lectures, practical tasks, and progress tracking across departments

Build AI applications with stateful memory using the Honcho SDK, including integration setup and migration from SDK v1.6.0 to v2.0.0 for both Python and TypeScript.

Build and orchestrate LangChain/LangGraph AI agents in TypeScript and Python with stateful graphs, subagent delegation, persistent memory, human-in-the-loop workflows, and project scaffolding for rapid development.

Orchestrates full-stack PHP development workflows with 5 playbook skills: PHP version upgrades (8.0-8.4+), Composer dependency management, git branch finishing, ticket-to-PR delivery, and isolated worktree operations. Includes 19 specialized agents for architecture, testing, code review, security auditing, and project management.

Design and implement secure backends with REST/GraphQL APIs, authentication systems, and LLM integrations, while performing security reviews and hardening against OWASP Top 10 vulnerabilities.

Provides quick reference for LangChain 1.0 core concepts like Agents, Tools, Memory, Middleware, and runtime context for creating AI agents and integrating models.

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.

Operate the entire Oracle AI Data Platform Workbench in natural language: discover catalogs, run Spark SQL on a Delta lakehouse, ingest files, profile data quality, schedule pipelines, provision clusters, manage RBAC/credentials, debug via Spark UI, and build AI agent flows with guardrails, RAG knowledge bases, and LangGraph agents — all through a 37-skill MCP agent.

Manage the full lifecycle of AI agents on GreenNode AgentBase: scaffold new projects, deploy with custom Docker runtimes, configure MCP API gateways, manage identity providers and LLM access, set up memory stores, monitor runtime logs and metrics, and tear down all resources when done.

Generates tests across Jest, Vitest, Pytest, Cypress, and Playwright; optimizes prompts for AI models; researches external documentation and best practices; creates and updates CLAUDE.md files from staged git changes; and produces formatted documents (PDF, DOCX, HTML) from markdown.

Scaffold LangChain or dcode CLI agents via an interactive interview, generating self-contained Python agents compatible with any OpenAI-compatible API.

Debug AI chains, analyze token costs, and manage LangSmith traces, runs, datasets, and prompts directly from the CLI

Scaffold, review, and enhance Spring Boot projects for Java 8+ with CRUD generation, JPA optimization, security auditing, caching, resilience patterns, OpenAPI docs, and AI integration.

Embeds a team of AI security specialists into your coding workflow to enforce Secure SDLC practices across the entire development lifecycle, from threat modeling and secure requirements to IaC review, compliance mapping, and release gating.

Pull server-rendered web content from any URL into Claude Code with conditional-GET caching, then search, read, and index documentation sources without a browser or API keys.

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.

Audit AI agent code (OpenAI Agents SDK, Claude Agent SDK, Google ADK, MCP) for security and reliability misconfigurations, then automatically apply fixes like missing guardrails, timeouts, and type annotations.

Optimize LLM agent code with autonomous evolution loops using LangSmith evaluations and isolated git worktrees, including multi-agent proposers, stagnation detection, evaluator audits, and test input generation.

Add Opik observability to LLM applications with automatic tracing, evaluation, and production monitoring for agents. Includes session telemetry control and code review for agent architecture and security.

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.

Scaffold agent applications across multiple harnesses, create Claude Code and OpenCode plugins, commands, agents, skills, and custom tools with AI assistance, and validate plugin structure.

Manage YugabyteDB environments end-to-end: deploy infrastructure with Terraform and Kubernetes, design distributed SQL schemas, optimize queries, integrate LLM search, and automate the YBA control-plane API.

Build and orchestrate multi-agent systems using Google's A2A protocol: create Agent Cards, manage task lifecycles, handle streaming and push notifications, implement authentication, and integrate with frameworks like LangGraph and CrewAI.

Build production-ready LLM applications with RAG, embeddings, LangChain agents, prompt engineering, and vector search — includes hybrid retrieval strategies, evaluation metrics, and index tuning for scaling.

Automate evaluation of LangChain4j RAG pipelines with faithfulness, relevance, and hallucination checks using Dokimos.

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.

Fetch and index documentation from any URL into Claude Code, with conditional-GET caching and searchable access via MCP tools. Supports fast-moving libraries like Next.js, FastAPI, LangChain, and React, enabling grounded answers with source citations.

Author and refine Claude Code skills, agents, MCP servers, and prompts using Anthropic best practices, prompt engineering techniques, and a test-driven skill template. Includes guides for API usage, context optimization, and external service integration.

Build and optimize production-ready LLM applications with prompt engineering, multi-agent orchestration, and performance profiling. Includes a prompt optimizer (/lyra), agent failure analysis, and context management for RAG and vector search.

Manage the full Domino Data Lab lifecycle from Claude: create projects, run batch jobs and Spark/Ray/Dask clusters, deploy web apps and model APIs, track MLflow experiments, trace GenAI apps, configure compute environments and workspaces, and automate workflows via SDK or MCP.

Build production RAG pipelines, vector search systems, and LLM integrations with agent orchestration, while diagnosing and refining prompts, system instructions, and agent behaviors through structured analysis.

Write idiomatic Python code for the OpenGradient SDK to perform verified LLM inference via TEE, on-chain ONNX model inference, LangChain agent integration, digital twins chat, and model hub operations.

Analyze trade association and nonprofit executive-director responsibilities from organizational documents, score automation potential with a 6-factor algorithm, then generate and deploy LangGraph multi-agent workflows across environments with monitoring, simulation, and ROI reporting.

Connect to ScyllaDB Cloud clusters and manage them via AI agents, design CQL schemas with query-first patterns, and implement Vector Search using HNSW indexes for semantic similarity and RAG.

Orchestrates spec-driven DevOps workflows with PDCA sprints, role-based agents for architecture, QA, and security, plus automated PR reviews, release management, and project health diagnostics.

Implement AI/ML features using an agent specialized in LLM integration, recommendation systems, computer vision, and intelligent automation. Handles prompt engineering, ML pipelines, and model deployment.

Convert knowledge from 17 source types (docs, GitHub, PDFs, videos, Jupyter, Confluence, etc.) into AI-ready skills for 16+ LLM platforms like Claude, OpenAI, and Gemini. Auto-detect source type, generate skill packages, and sync documentation configurations.

Implement AI/ML features: integrate LLMs, build recommendation systems, computer vision, and intelligent automation with prompt engineering and model deployment

Implement AI/ML features, integrate language models, build recommendation systems, and add intelligent automation to applications.

Build production-ready LLM applications with LangGraph agents, RAG systems, vector search, and prompt engineering. Covers embedding model selection, hybrid search fusion, evaluation metrics, and vector index tuning for scalable AI systems.

Deploy LangGraph 1.0 agents on AWS Bedrock AgentCore with multi-agent orchestration, persistent memory (STM/LTM), and Gateway MCP tools via CLI for production observability and scaling.