Build your AI stack
Tools, MCP servers, and skills that work together — from editor to production.
AI Coding Tools
View all →ChatGPT
ChatGPT is a large language model-based chatbot developed by OpenAI, launched in November 2022. It uses the GPT-4 architecture to generate human-like text responses across conversation formats. The model supports multi-modal inputs including text, images, and voice interactions. A free tier is available with GPT-3.5, while ChatGPT Plus provides access to GPT-4 with faster response times and plugin capabilities. It serves as a versatile tool for writing, analysis, coding assistance, and creative tasks.
Gemini
Gemini is Google's family of multimodal AI models designed to compete with OpenAI's GPT series. Formerly known as Bard, it rebranded to Gemini in 2024 and directly integrates with Google services. The Ultra 1.0 model achieved state-of-the-art performance on multiple benchmarks. Gemini is available through the Google AI app, web interface, and integrates with Gmail, Docs, and other Google Workspace applications.
Claude
Claude is Anthropic's AI assistant based on the Constitutional AI and RLHF-aligned methodology. Launched in 2023, Claude emphasizes helpful, harmless, and honest interactions. It supports extremely long context windows of up to 200K tokens, making it effective for analyzing lengthy documents. Claude 3.5 Sonnet represents the mid-tier model with strong coding and reasoning capabilities. The iOS app and web interface provide easy access across devices.
DeepSeek
DeepSeek is a Chinese AI company that gained prominence in 2025 with its DeepSeek-V3 model, achieving performance comparable to leading US models at significantly lower training costs. The company released DeepSeek-R1 in January 2025, an open-source reasoning model that competes with OpenAI's o1. DeepSeek's models are available through their web interface, API, and have been integrated into various applications. Their open-source approach has democratized access to frontier-level AI capabilities.
Cursor
Cursor is an AI-first code editor built on VS Code, launched in 2023 by Anysphere. It integrates AI capabilities directly into the coding workflow with features like code completion, natural language commands, and pair programming. Cursor 0.5 introduced Agent capabilities that can autonomously modify codebases. The editor supports Python, JavaScript, TypeScript, Go, Rust, and other major languages. It offers a free tier with 1000 code completions and paid plans for extended usage.
GitHub Copilot
GitHub Copilot is Microsoft's AI coding assistant integrated directly into IDEs like VS Code, JetBrains, and Vim. Powered by OpenAI's GPT-4 and specialized code models, it provides real-time code suggestions, entire function implementations, and documentation generation. Copilot Chat enables conversational debugging and code explanation. Launched in 2021 as a technical preview, it became generally available in 2022. Business plans offer team management, policy controls, and SAML SSO integration.
Windsurf
Windsurf is an AI-powered code editor by Codeium, launched in 2024. Its signature feature is Cascade, a chat interface that maintains project context across editing sessions. Windsurf distinguishes itself with SUPERCLINE, a context engine that tracks cursor position and project state for highly relevant suggestions. The editor is built on the same foundation as Codeium's enterprise tooling, emphasizing speed and privacy. A free tier exists alongside Pro and Enterprise plans.
Midjourney
Midjourney is an independent AI image generation lab that operates primarily through a Discord bot. Launched in 2022, it produces highly artistic and stylized images from text prompts. Users interact via Discord commands, with generation happening on Midjourney's servers. Version 6 (V6) released in late 2024 offers improved coherence, text rendering in images, and photorealism capabilities. The platform has developed a distinctive aesthetic that has influenced digital art and design communities.
MCP Servers
More →BigQuery MCP Server
Google Cloud documents a remote BigQuery Model Context Protocol server at docs.cloud.google.com/bigquery/docs/use-bigquery-mcp, enabled when the BigQuery API is enabled. Connect MCP clients to the managed HTTP endpoint `https://bigquery.googleapis.com/mcp` with OAuth 2.0 and IAM (API keys are not accepted). Documented IAM roles include MCP Tool User (`roles/mcp.toolUser`), BigQuery Job User (`roles/bigquery.jobUser`), and BigQuery Data Viewer (`roles/bigquery.dataViewer`). Tools include `execute_sql` and `execute_sql_readonly` per the use guide; `execute_sql_readonly` allows only read-only operations while `execute_sql` is the sole non-read-only tool. Limitations documented: query processing capped at three minutes by default, results limited to 3,000 rows, and Google Drive external tables unsupported for those SQL tools.
Graphiti MCP Server
Zep documents an experimental Graphiti Model Context Protocol server at help.getzep.com/graphiti/getting-started/mcp-server, with AI client integration also referenced at `https://help.getzep.com/_mcp/server` per Zep docs. The open-source implementation lives in getzep/graphiti/mcp_server with HTTP transport at `/mcp/` (default localhost:8000) or stdio mode. Tools include `add_episode`, `search_facts`, `search_nodes`, `get_episodes`, `delete_episode`, `clear_graph`, and `get_status` per the Graphiti MCP README; newer README entries also list `add_memory`, `add_triplet`, `search_memory_facts`, `summarize_saga`, `build_communities`, and `get_episode_entities`. Graphiti is Zep's open-source temporal knowledge graph framework for Context Graphs with real-time incremental updates and hybrid retrieval.
LanceDB MCP Server
LanceDB maintains a reference Model Context Protocol server in the lancedb/lancedb-mcp-server repository (linked from lancedb/lancedb issue #2341), implemented with FastMCP and LanceDB embeddings. Tools include `ingest_docs` (embed and store documents), `query_table` (semantic retrieval with configurable top_k and query_type), and `table_details` (schema and row counts) per the README. Configuration uses `uv run lancedb_mcp.py` with environment variables `LANCEDB_URI` (default `~/lancedb`), `TABLE_NAME`, `EMBEDDING_FUNCTION` (default sentence-transformers), and `MODEL_NAME` (default all-MiniLM-L6-v2). The repo describes itself as a basic serverless MCP reference for building more complex LanceDB agent apps—not a full production managed endpoint.
MotherDuck MCP Server
MotherDuck documents a remote Model Context Protocol server at motherduck.com/docs/sql-reference/mcp hosted at `https://api.motherduck.com/mcp` with OAuth (or Bearer token) and read-write SQL access to MotherDuck cloud databases. Tools include `list_databases`, `list_tables`, `list_columns`, `search_catalog`, `query`, `query_rw`, `ask_docs_question`, Dive tools (`list_dives`, `read_dive`, `view_dive`, `save_dive`, etc.), and Flight scheduling tools (`list_flights`, `create_flight`, `run_flight`, etc.) per MotherDuck MCP docs. For local DuckDB files or custom configs, MotherDuck points to the open-source `mcp-server-motherduck` package (`uvx mcp-server-motherduck --db-path md:`) on github.com/motherduckdb/mcp-server-motherduck.
Mem0 MCP Server
Mem0 documents an official cloud-hosted Model Context Protocol server at docs.mem0.ai/platform/mem0-mcp, exposed over Streamable HTTP at `https://mcp.mem0.ai/mcp` with no local install required. Setup uses `npx mcp-add --name mem0-mcp --type http --url https://mcp.mem0.ai/mcp` for Claude, Claude Code, Cursor, Windsurf, VS Code, and OpenCode per Mem0 docs. Tools include `add_memory`, `search_memories`, `get_memories`, `get_memory`, `update_memory`, `delete_memory`, `delete_all_memories`, `delete_entities`, `list_entities`, `list_events`, and `get_event_status`. Authentication uses a Mem0 Platform API key (`MEM0_API_KEY`); the legacy mem0ai/mem0-mcp GitHub repo is archived in favor of this hosted server.
Weaviate MCP Server
Weaviate documents a built-in Model Context Protocol server in the main `weaviate/weaviate` binary from v1.37.1 onward at docs.weaviate.io/weaviate/mcp/mcp-server, exposed as a Streamable HTTP endpoint at `/v1/mcp` on the same port as the REST API (default 8080). Enable with `MCP_SERVER_ENABLED=true`; optional `MCP_SERVER_WRITE_ACCESS_ENABLED=true` registers `weaviate-objects-upsert`. Tools include `weaviate-collections-get-config`, `weaviate-tenants-list`, `weaviate-query-hybrid`, and `weaviate-objects-upsert` (write-gated). Authentication uses existing API keys/Bearer tokens with RBAC permissions `read_mcp`, `create_mcp`, and `update_mcp` per Weaviate 1.37 release notes. The standalone weaviate/mcp-server-weaviate repository is deprecated in favor of this built-in server.
Claude Code Skills
More →SAP–Google agentic commerce architecture due diligence
Turns AI News reporting on June 19, 2026 about SAP and Google Cloud deploying agentic commerce architecture into a data, retail-ops, and procurement checklist. The workflow separates verified partnership facts—SAP research cited that 78% of businesses consider AI essential for retaining customers in 2026 while fewer than two in five share customer data across CX (37%) or CRM (39%) platforms; SAP Commerce Cloud adopting Universal Commerce Protocol; SAP Business Data Cloud Connect for Google BigQuery with bidirectional zero-copy linking; SAP Engagement Cloud multi-agent framework; Google Gemini including Nano Banana 2 for localized messaging and Google Rich Communication Services; Shopping Assistant with live inventory checks—from internal rollout decisions your org must still make. It references AI News that the architecture lets agents execute full retail sequences via UCP, merchants retain customer relationships in third-party channels, and marketing teams set business goals rather than manual campaign execution.
ChatGPT Enterprise spend controls due diligence
Turns Reuters-via-Yahoo Tech reporting on OpenAI's June 18, 2026 ChatGPT Enterprise analytics and spend-control launch into a finance, IT, and procurement checklist. The workflow separates verified product facts—global admin console visibility for ChatGPT and Codex credits, per-user/product/model breakdowns, usage trends, top users, workspace default credit limits, group limits with individual overrides, employee self-service usage views and credit requests, availability starting Thursday—from internal policy decisions your org must still make. It references Yahoo Tech (Reuters) that growing enterprise adoption by power users has drawn attention to escalating AI consumption costs and that OpenAI framed the release as helping manage costs and track credit usage.
Anthropic Mythos export-control directive due diligence
Structures verification of frontier-model export-control headlines into a legal, security, and product-access checklist. The workflow separates Commerce Department directives from Anthropic compliance statements, maps Mythos versus Fable access changes, and tracks licensing language without inferring undisclosed national-security details. It references CNN reporting on June 13, 2026 that Anthropic disabled customer access to its most capable systems after the US government ordered it to suspend all use by foreign nationals of Mythos 5 and Fable 5 over national security concerns about cybersecurity vulnerabilities; CNN said Anthropic complied by removing access for everyone because it could not filter users by nationality in real time; the government did not provide specific national-security details though Anthropic believed officials became aware of a Fable 5 jailbreak demonstrating relatively minor, previously known vulnerabilities other public models can also find; Anthropic disputed that a narrow jailbreak should recall a commercial model deployed to hundreds of millions and argued applying the standard industry-wide would halt frontier deployments; CNN cited Axios that Commerce would require licenses for export, re-export, or domestic transfer; the piece notes Mythos capabilities spooked government and Wall Street, Fable 5 shipped last week as a safer public version, a recent executive order asks companies to share advanced cyber-capable models with government up to 30 days before other partners, and earlier supply-chain-risk designation and lawsuit context with continued White House contact.
Frontier model token price-war due diligence
Structures verification of frontier-LLM pricing headlines into a finance and procurement checklist. The workflow separates reported price-cut discussions from confirmed public rate cards, maps token-billing impacts to gross-margin assumptions, and tracks IPO-timing context without treating leaks as finalized pricing. It references The Wall Street Journal reporting on June 11, 2026 that OpenAI is considering drastically lowering prices charged for tokens—the unit AI firms use to bill products—in anticipation of similar cuts the company expects at Anthropic, according to people familiar with the matter; WSJ notes discussions are still in flux; both companies' business models are under scrutiny ahead of hotly anticipated IPOs; OpenAI confidentially filed for an IPO earlier that week following Anthropic's filing, and CEO Sam Altman told employees in a recent Slack message the company plans to go public within the next year (as earlier reported by the Information). WSJ framed the move as OpenAI seeking to win customers from rival Anthropic amid an expected token-pricing competition.
EU AI Act Article 50 content labelling due diligence
Structures verification of EU generative-AI transparency headlines into a compliance readiness checklist for providers and deployers. The workflow separates voluntary Code of Practice signing from mandatory Article 50 obligations, maps provider versus deployer labelling duties, and tracks pending Commission guidelines. It references AI News reporting on June 16, 2026 that the European Commission released a final voluntary Code of Practice on 10 June ahead of Article 50 transparency rules applying from August 2, 2026; the Code is optional but the obligations are not; from August, deepfakes and AI-generated or AI-manipulated text on matters of public interest must carry labels, and interactive AI systems such as customer-service bots must disclose machine interaction; Executive Vice-President Henna Virkkunen is quoted that Europeans have a right to know whether content was made or altered by AI; providers should mark output in machine-readable format while deployers handle visible labelling when public-interest text goes out without human review; the Code uses open technical standards and a common EU icon; it was drawn up by six independent experts with input from more than 180 stakeholders and still awaits Commission and AI Board adequacy judgment plus separate guidelines for gaps AI News says remain unpublished with under two months before enforcement.
AI chipmaker debt capital raise due diligence
Structures verification of AI-infrastructure debt headlines into a treasury and investor-relations checklist. The workflow separates SEC filing facts from unnamed source sizing, compares new issuance to existing debt stacks and prior raises, and maps proceeds language to refinancing versus buyback narratives. It references CNBC reporting on June 15, 2026 that Nvidia disclosed plans in an SEC filing for its first investment-grade corporate bond sale since 2021, with sources telling CNBC the chipmaker is aiming to raise at least $20 billion (possibly closer to $25 billion) in its first bond sale since the AI boom began; CNBC notes Nvidia shares rose 3.5% Monday and are up about 14% year-to-date; the piece situates Nvidia alongside Alphabet ($85 billion equity-related plans plus $55 billion+ debt since November), Super Micro ($7 billion equity-related financing), and Amazon (~$54 billion U.S./European debt plus ~$10 billion Canadian sale plans); CNBC cites Nvidia's ~$7.5 billion long-term and ~$1 billion short-term debt, its $5 billion 2021 raise with notes maturing as late as 2031, revenue growth from ~$27 billion in fiscal 2022 to $216 billion in fiscal 2026, ChatGPT's late-2022 catalyst for GPU demand, a spokesperson saying proceeds are for general corporate purposes including repayment/refinancing of existing debt, and May dividend/buyback moves ($0.25 dividend, $80 billion repurchase plan, ~50% of free cash flow return target, $49 billion quarterly free cash flow).