THE AI TRUST
DIRECTORY

Anthropic's new top-tier model above Opus and the first generally available Mythos-class model. State-of-the-art on nearly all tested benchm...

Anthropic's flagship Opus model with state-of-the-art long-horizon agentic execution, knowledge work, and memory. 84% on Online-Mind2Web, dy...

Anthropic's frontier Opus released February 2026 with 80.8% SWE-bench Verified, breakthrough 68.8% ARC-AGI-2 abstract reasoning, adaptive th...

SUPERSEDED: no longer Anthropic's most capable model — succeeded by Opus 4.6, 4.7, 4.8 (2026-05-28) and Claude Fable 5 (2026-06-09, new top ...

Anthropic's most powerful model with state-of-the-art reasoning, ASL-3 safety level, and exceptional performance on complex tasks. Flagship ...

Anthropic's most powerful model released May 2025. Exceptional reasoning, coding (72.5-79.4% SWE-bench in high-compute), and agentic capabil...

OpenAI's first open-weight model released August 2025. 117B total params (5.1B active), Apache 2.0 license. Matches o4-mini on many benchmar...

OpenAI's edge-optimized open-weight model released August 2025. 21B total params (3.6B active), Apache 2.0 license. Matches o3-mini despite ...

Official MCP reference server for time and timezone operations. Provides AI models with current time information, timezone conversions, date...

Previous-generation Opus flagship, superseded by Opus 4.8. 64.3% SWE-Bench Pro and 94.2% GPQA Diamond at launch. First Claude with high-reso...

Anthropic's best speed/intelligence balance — the value workhorse for agentic and production workloads at $3/$15 per 1M tokens, with a 1M to...

OpenAI's current flagship (codename 'Spud') and first fully retrained base model since GPT-4.5. ~1.05M context, 85.0% ARC-AGI-2, 93.6% GPQA ...

OpenAI's previous-generation flagship (superseded by GPT-5.5 in April 2026). Headline native computer use with 75% OSWorld-Verified, ~33% fe...

SUPERSEDED by GPT-5.4 (2026-03-05) and GPT-5.5 (2026-04-23, current OpenAI flagship). Still served, with 400K context window, 100% AIME 2025...

Google's GA flagship reasoning model with 77.1% ARC-AGI-2 (2.5x Gemini 3 Pro), 94.3% GPQA Diamond, 2887 Elo on LiveCodeBench Pro, and 1M tok...

State-of-the-art AI model with exceptional coding capabilities, extended thinking, and strong safety features. Best-in-class for software de...

Anthropic's Claude Sonnet 4 model released May 2025 with exceptional coding capabilities and advanced reasoning. Hybrid model with extended ...

Anthropic's fastest model released October 2025. Best coding performance (73.3% SWE-bench) at 1/3 cost and 2x speed of Sonnet 4. First Haiku...

DEPRECATED: superseded by GPT-5.3-Codex (2026-02-05); gpt-5.2-codex API shuts down 2026-07-23. Historically OpenAI's specialized coding mode...

Former Google flagship, superseded by Gemini 3.1 Pro (GA 2026-02-19; ARC-AGI-2 77.1% vs 31.1%). Still served, with 1M token context, 1501 LM...

Fully managed AWS service for building and deploying generative AI agents with orchestration, memory, knowledge bases, and action groups. No...

OpenAI's agentic coding specialist: ~80% SWE-bench Verified, 77.3% Terminal-Bench, SOTA on SWE-Bench Pro at release, ~25% faster than GPT-5....

SUPERSEDED by GPT-5.2/5.4/5.5 (GPT-5.5 is the current flagship); gpt-5.1-chat-latest and gpt-5.1-codex variants shut down in the API 2026-07...

OpenAI's latest flagship model with unified thinking capabilities, multimodal understanding, and enhanced reasoning. Successor to GPT-4o ser...

DEPRECATED: o1 variants and o1-pro shut down in the API on 2026-10-23; already removed from ChatGPT (o1-preview/o1-mini removed in 2025). Mi...

Google's GA 'frontier workhorse' launched at I/O 2026. Beats Gemini 3.1 Pro on agentic and coding suites (76.2% Terminal-Bench 2.1, 83.6% MC...

Google's efficiency model with Pro-level performance at 1/4 the price. 78% SWE-bench (beats Pro), 1M context, 3x faster than 2.5 Pro. Thinki...

Google's latest flagship with 2M token context window, Deep Think mode for complex reasoning, and native multimodal capabilities. Best-in-cl...

Meta's flagship open-source model with 400B parameters, native multimodal capabilities, and state-of-the-art performance. Best-in-class open...

AWS managed conversational AI service for building chatbots and voice assistants with automatic speech recognition (ASR) and natural languag...

REBRANDED: at Cloud Next (April 2026) Vertex AI Agent Builder became the Gemini Enterprise Agent Platform (APIs unchanged), following Agents...

MAINTENANCE MODE: Semantic Kernel now receives bug/security fixes only and is superseded by the Microsoft Agent Framework (1.0 GA on 2026-04...

Microsoft's enterprise bot development platform integrated with Azure AI services. Provides comprehensive tools for building, testing, deplo...

Google's advanced conversational AI platform for building sophisticated virtual agents with visual flow design, state management, and enterp...

Enterprise AI platform for work that unifies information across business tools and applications. Provides intelligent search, knowledge disc...

DEPRECATED: the o3 family is being retired — o3-deep-research shuts down 2026-07-23 and o3-mini's API shuts down 2026-10-23; migration targe...

DEPRECATED: o3-mini's API shuts down 2026-10-23; migration target is GPT-5.5. Historically an efficient reasoning model from OpenAI achievin...

DEPRECATED: removed from ChatGPT 2026-02-13; o4-mini API shuts down 2026-10-23 (o4-mini-deep-research shut down 2026-07-23); migrate to GPT-...

SHUT DOWN: Google shut down the Gemini 2.0 Flash family on 2026-06-01; the model is no longer served via the Gemini API. Historically a fast...

Meta's largest open-source model with 405 billion parameters, offering complete transparency, self-hosting capabilities, and competitive per...

Cohere's Apache 2.0 open-weight 218B sparse MoE (25B active) unifying Command A, A Reasoning, A Vision, and A Translate. Runs on 2xH100 or a...

Amazon's cost-efficient Nova 2 workhorse model, GA on Amazon Bedrock since re:Invent 2025. Offers three thinking-intensity levels, a built-i...

Massive 253B parameter model from NVIDIA's Llama-3.1-based Nemotron line, now superseded: NVIDIA discontinued this line in favor of the nati...

IBM's enterprise-grade conversational AI platform powered by Watson AI. Combines natural language understanding, dialog management, and inte...

TRANSITIONING: Einstein Copilot was retired and absorbed into Agentforce (Jan 2025, Spring '25 release), and Salesforce is steering Einstein...

Enterprise-grade agentic AI platform for designing, deploying, managing, and scaling AI agents across business operations. Offers no-code bu...

Visual automation platform with AI capabilities for building no-code intelligent workflows. Integrates AI models with 1500+ app connections ...

SUPERSEDED by the Nova 2 family announced at re:Invent 2025-12-02 (Nova 2 Lite GA; Nova 2 Pro/Omni in preview), though the original Nova Pro...

No-code automation platform with AI actions for connecting AI models to 6000+ apps. Enables building intelligent automations and AI-powered ...

OpenAI's flagship GPT-4.1 model offering strong general-purpose capabilities across diverse tasks. The standard choice for production applic...

Meta's announced 2T-total/288B-active parameter Llama 4 teacher model that was NEVER RELEASED. It remains 'announced, not released' as of Ju...

Meta's efficient Llama 4 model optimized for speed and resource efficiency. Designed for edge deployment and cost-sensitive applications req...

Meta's powerful 70B parameter Llama 3.3 model offering strong performance with open-source flexibility and an excellent balance of capabilit...

Alibaba's Apache-2.0 flagship open model: Qwen3.5-397B-A17B, a hybrid MoE with 512 experts (397B total / 17B active) that is natively multim...

Mistral AI's open-weight flagship released December 2025 under Apache 2.0: a sparse MoE (675B total / 41B active) multimodal model with ~256...

DEPRECATED: the Assistants API will be sunset on 2026-08-26 (roughly 2.5 months away); OpenAI directs users to the Responses API plus Conver...

MAINTENANCE MODE: AutoGen now receives bug/security fixes only and is superseded by the Microsoft Agent Framework (1.0 GA on 2026-04-03), th...

DEPRECATED: removed from ChatGPT 2026-02-13; the gpt-4o-2024-05-13 snapshot's API shuts down 2026-10-23. Historically OpenAI's flagship mult...

DEPRECATED: o1-mini (with o1-preview) was removed from the OpenAI API in 2025 and from ChatGPT; remaining o1 variants shut down 2026-10-23. ...

DeepSeek's ~685B-parameter MoE flagship with DeepSeek Sparse Attention (DSA) for dramatically cheaper long-context inference. The V3.2-Speci...

DeepSeek's standalone reasoning model, now superseded and discontinued as a product line. Its reasoning capabilities were folded into DeepSe...

Production-ready multi-agent orchestration framework built around agents, handoffs, guardrails, and tracing. Open-source (MIT) successor to ...

Open-source SDK and runtime for building AI agents and graph-based multi-agent workflows in .NET and Python. Merges AutoGen and Semantic Ker...

Open-source, model-driven AI agent SDK from AWS, used internally by Amazon Q Developer. Takes a lightweight model-first approach with MCP an...

Fair-code workflow automation platform with AI agent capabilities. Visual workflow builder integrating AI models, tools, and 400+ app integr...

Type-safe Python agent framework from the creators of Pydantic. Reached v1.0 stable on 2025-09-04 with a formal API stability commitment and...

Stripe's official MCP server from the open-source agent toolkit. Exposes tools for customers, products, prices, payment links, invoices, ref...

MCP server enabling AI models to leverage Perplexity's advanced search capabilities. Provides multi-source research with automatic citations...

MCP server enabling AI models to interact with Supabase backend services. Provides schema design, database migrations, SQL query execution, ...

OpenAI's balanced GPT-4.1 variant offering good performance with efficient resource usage. Optimized for production workloads requiring qual...

xAI's current flagship model released in early May 2026, with a 1M token context window, reasoning, function calling, and structured outputs...

xAI's late-2025 flagship that debuted #1 on LMArena Text (1483 Elo) and led EQ-Bench3 for emotional intelligence, with a 2M token context wi...

RETIRED: xAI retired Grok 3 on 2026-05-15; retired API slugs now silently redirect to Grok 4.3 at Grok 4.3 pricing. Historically xAI's flags...

DeepSeek's preview flagship family: V4-Pro (1.6T total / 49B active MoE, the largest open-weight release ever) and V4-Flash (284B/13B). 1M-t...

Open-source, code-first framework for building, evaluating, and deploying AI agents. Supports workflow agents, multi-agent hierarchies, buil...

Conversational AI platform specialized in autonomous customer experience agents. Founded by former Salesforce co-CEO Bret Taylor and ex-Goog...

LangChain's graph-based agent framework for building stateful, multi-actor applications with cycles and controllable execution flow. Reached...

Secure cloud runtime for AI agents with code interpreter capabilities. Provides sandboxed environments for executing agent-generated code sa...

Official MCP reference server enabling dynamic, extended reasoning and problem-solving sequences. Allows AI models to create structured thin...

ARCHIVED: Former Anthropic reference MCP server for the Brave Search API, archived 2025-05-29 to the servers-archived repository and no long...

Google's open-source Gemma 3 model with 27 billion parameters, now superseded by Gemma 4 (released 2026-04-02 under Apache 2.0, a license im...

Z.ai's MIT-licensed 744B-parameter MoE (40B active) with 77.8% SWE-bench Verified, 92.7% AIME 2026, and open-source leadership on BrowseComp...

Multimodal vision-language model from Alibaba, now two generations behind: superseded first by Qwen3-VL (Sep 2025) and then by the natively-...

OpenAI's coding agent spanning a cloud agent that runs tasks in isolated containers and an open-source CLI. Delegates parallel software task...

Open-source LLM application and agentic workflow platform with a visual canvas, built-in RAG pipeline, agent nodes, and 50+ built-in tools. ...

Leading open-source conversational AI framework for building contextual assistants and chatbots. Provides full control over NLU, dialogue ma...

Open-source NLP framework for building production-ready LLM applications, RAG pipelines, and semantic search systems. Modular architecture w...

Data framework optimized for building LLM applications with advanced RAG (Retrieval-Augmented Generation) capabilities. Agents can reason ov...

MCP server built into the shadcn CLI (run via npx shadcn@latest mcp) that lets AI agents browse, search, and install UI components from any ...

GitHub's OFFICIAL MCP server, successor to the archived Anthropic reference server. Open source (Go, MIT, 30,558 stars), distributed as a bi...

OpenAI's efficient multimodal model combining text and vision capabilities at competitive pricing. Designed for cost-sensitive applications ...

Google's open-weight family released April 2026 under Apache 2.0 (a shift from the custom Gemma license). Spans E2B/E4B edge models with 128...

Moonshot AI's open-weight 1T-parameter MoE (32B active) with vendor-reported 80.2% SWE-Bench Verified and 58.6 SWE-Bench Pro. Agent Swarm or...

TypeScript-first AI agent framework from the Gatsby founders, combining agents, durable workflows, RAG, and evals in one toolkit. Provider-a...

MCP server enabling AI models to perform real-time web search, content extraction, and web crawling. Designed specifically for AI agents wit...

ARCHIVED: Former Anthropic reference MCP server for GitLab integration (merge requests, CI/CD pipelines, issues), archived 2025-05-29 to the...

Official MCP reference server providing AI models with controlled access to the local filesystem (file reading, writing, and directory opera...

OpenAI's smallest and most efficient GPT-4.1 variant, designed for high-volume, cost-sensitive applications. Optimized for speed and resourc...

MiniMax's MIT-licensed 230B MoE with only 10B active parameters, optimized for agentic tool calling and coding. Topped open-model agentic ra...

Anthropic's agentic coding tool available as a terminal CLI, IDE extensions, web, and desktop app. Plans and executes multi-step coding task...

No-code AI agent platform that enables teams to build, customize, and deploy AI workforce agents. Features visual workflow builders, tool in...

Microsoft's official MCP server for browser automation via Playwright. Exposes 25+ tools (navigation, clicking, typing, form filling, screen...

Vercel's official hosted MCP server at mcp.vercel.com. Provides Vercel documentation search and tools to inspect teams, projects, deployment...

Official MCP reference server for fetching web content and converting HTML to markdown. Enables AI models to retrieve and process web pages,...

Official MCP reference server for Git repository operations. Enables AI models to interact with local Git repositories, perform commits, bra...

Official Datadog MCP server for observability and monitoring integration. Enables AI models to query metrics, logs, traces, dashboards, and ...

DeepSeek's March 2025 open-weights V3 checkpoint, now superseded by DeepSeek V3.1 (Aug 2025), V3.2 (Dec 2025), and V4 (Apr 2026). The legacy...

SDK exposing Claude Code's production agent harness (tool loop, permission system, subagents, MCP) for building general-purpose agents in Ty...

Minimalist Python agent library from Hugging Face. Its signature CodeAgent writes actions as executable Python code instead of JSON tool cal...

Role-playing multi-agent framework for orchestrating collaborative autonomous agents. Agents work together as a crew with defined roles, goa...

Open-source no-code business automation platform with AI capabilities. Self-hostable alternative to Zapier with visual workflow builder, 200...

Upstash's documentation-retrieval MCP server. Two tools (resolve-library-id, get-library-docs) inject up-to-date, version-specific library d...

Official Firecrawl MCP server giving AI models web scraping, crawling, site mapping, web search, and structured extraction capabilities. Ava...

Official MCP reference server demonstrating all protocol features (tools, resources, prompts, sampling) for testing and development. One of ...

Official Cloudflare MCP server for managing CDN, DNS, Workers, Pages, and security services. Enables AI models to configure edge computing, ...

ARCHIVED WITH UNPATCHED VULNERABILITY: Former Anthropic reference MCP server for SQLite, archived 2025-05-29 to the servers-archived reposit...

Community-maintained MCP server for Linear project management integration. Enables AI models to create, read, update issues, manage projects...

Official Atlassian MCP server for Jira and Confluence integration. Enables AI models to interact with project management, issue tracking, an...

Official Sentry MCP server for error tracking and monitoring integration. Enables AI models to query errors, analyze stack traces, manage is...

Open-source low-code platform for building customized LLM orchestration flows and AI agents. Visual node-based editor for creating RAG pipel...

REBRANDED: MemGPT became Letta (Letta Inc., a UC Berkeley spinout) in September 2024; "MemGPT" now refers only to the underlying research te...

Zapier's hosted, proprietary MCP server that gives AI agents access to user-selected actions from 9,000+ connected apps (Gmail, Slack, Sales...

Official Microsoft MCP server for Azure cloud services integration. Enables AI models to interact with Azure resources including Virtual Mac...

Community-maintained MCP server for Redis cache and data structure operations. Enables AI models to interact with Redis for key-value operat...

Community-maintained MCP server for AWS S3 storage operations. Enables AI models to upload, download, list, and manage objects in S3 buckets...

Community-maintained MCP server for Google Calendar integration. Enables AI models to create, read, update, and delete calendar events, mana...

ARCHIVED: Former Anthropic reference MCP server (gdrive) for accessing and searching Google Drive files, archived 2025-05-29 to the servers-...

Open-source terminal AI agent from Google that brings Gemini into the command line. Uses a ReAct loop with built-in tools, MCP server suppor...

Visual, drag-and-drop interface for building LangChain-based AI apps and agents; now owned by IBM via the Feb 2025 DataStax acquisition. SEC...

Google's official MCP server that gives AI agents full Chrome control via the Chrome DevTools Protocol. Around 26 tools span input automatio...

Hugging Face's official MCP server connecting AI assistants to the Hub. Ships 7 built-in tools (search for models, datasets, Spaces, and pap...

Official Apify MCP server (renamed from actors-mcp-server) exposing thousands of Apify Store Actors to AI agents — scrapers for social media...

Notion's official MCP integration. Primary offering is the hosted MCP server at https://mcp.notion.com/mcp (Streamable HTTP and SSE transpor...

Autonomous data labeling agent framework for creating self-improving AI systems. Combines LLMs with ground truth learning to automate and im...

Open-source semantic coding toolkit from Oraios AI that turns any MCP-capable agent into an IDE-grade coding assistant. Uses language server...

Community-maintained MCP server for Docker container management. Enables AI models to interact with Docker Engine for container lifecycle ma...

Community-maintained MCP server for Kubernetes cluster management. Enables AI models to interact with Kubernetes API for pod management, dep...

Community-maintained MCP server for Elasticsearch search and analytics operations. Enables AI models to perform full-text search, aggregatio...

ARCHIVED: Former Anthropic reference MCP server for Slack workspace interaction, archived 2025-05-29 to the servers-archived repository. NO ...

MCP reference server providing persistent memory and knowledge graph capabilities: long-term retention, entity relationship tracking, and co...

Open-source autonomous AI agent framework for running and managing multiple AI agents concurrently. Features GUI-based management, tool mark...

Figma's official Dev Mode MCP server connecting AI coding tools to design files. Provides design-context extraction (code from frames, varia...

Community-maintained MCP server for MongoDB database operations. Enables AI models to query, insert, update, and delete documents, manage co...

Community-maintained MCP server for Gmail email operations. Enables AI models to read, send, search, label, and manage emails through the Gm...

Autonomous background coding agent built into GitHub. Assign it a GitHub issue or prompt and it works in an ephemeral GitHub Actions sandbox...

DEPRECATED: archived since 2025-03-11; the README redirects users to the OpenAI Agents SDK as the production successor. Swarm was an experim...

MCP server enabling AI models to interact with AWS cloud services including S3, EC2, Lambda, and more. Supports infrastructure management, r...

Agent mode of Cursor, Anysphere's AI-native IDE. The product's primary surface is now agentic: parallel local agents, cloud/background agent...

ARCHIVED WITH UNPATCHED VULNERABILITY: Former Anthropic reference MCP server for PostgreSQL, archived 2025-05-29. A SQL injection flaw discl...

ARCHIVED: Former Anthropic reference MCP server for Puppeteer browser automation, archived 2025-05-29 to the servers-archived repository and...

Asynchronous autonomous coding agent from Google. Jules clones a repository into an isolated Google Cloud VM, plans and writes code in the b...

Autonomous AI software engineer from Cognition that plans and executes multi-step engineering tasks in a sandboxed cloud workspace with its ...

DISCONTINUED: the AgentGPT repository was archived on 2026-01-28 (last release v1.0.0, Nov 2023) and the hosted site is frozen. Formerly a b...

Autonomous AI agent that attempts to achieve user-defined goals by breaking them into sub-tasks, using internet access, memory management, a...

ARCHIVED: the original BabyAGI repo was archived to babyagi_archive in September 2024 and replaced by an experimental self-building framewor...

General-purpose autonomous agent that executes end-to-end tasks in a cloud VM equipped with a browser, shell, and file tools. Launched viral...