AI Agent Tools With Claude Support
46 of the 94 tools in our index can run on Claude models — three exclusively, the rest reaching Claude either through a small vendor-picked set of frontier models or a broad bring-your-own-key layer. Every tool named, sorted by which.
On this page
"Supports Claude" means something different depending on which of these 46 tools you're looking at, and the difference matters if you're choosing one to integrate. We read every listing's own sourced `modelLLM`, `whatItDoes`, `keyFeatures` and `integrations` text rather than trusting the `claude` tag alone. Re-derived against the live corpus on 2026-08-17, that tag still disagreed with the listings themselves in both directions: [LangChain](/langchain) carries the tag and names neither Claude nor Anthropic anywhere in its own copy, while [Julius AI](/julius-ai) and [LlamaIndex](/llamaindex) name Claude models in theirs and carry no tag at all.
**Running on Claude is not the same as being callable by Claude**, and on an index of agent tools the two look identical to a keyword search. [Ada](/ada), [Elicit](/elicit), [Webhound](/webhound) and [Browserbase](/browserbase) each name Claude in their own listing, but only as the MCP client that calls them — Claude drives those four, it does not power them. [SalesTouch](/salestouch) is the sharpest case: its `modelLLM` field itself reads "Connects to Claude, Codex, Hermes, and OpenClaw", which a field-level check would score as a match and which means the opposite. None of the five is on this page.
**Claude-only (3)** — no other model vendor is offered at all: [Claude Agent SDK](/claude-agent-sdk), [Claude Code](/claude-code) and, less obviously, [Bolt.new](/bolt-new), whose own listing names no model but Claude anywhere in its research.
**Claude among a short, vendor-picked list (18)** — the vendor offers Claude alongside a small, fixed set of other frontier models, usually GPT and/or Gemini, not an open provider layer: [Cursor](/cursor), [GitHub Copilot](/github-copilot), [Windsurf](/windsurf), [Antigravity CLI](/antigravity-cli), [Clay](/clay), [Perplexity](/perplexity), [PolyAI](/polyai), [Devin](/devin), [Genspark](/genspark), [Relevance AI](/relevance-ai), [Vecbase](/vecbase), [Replit Agent](/replit-agent), [CodeRabbit](/coderabbit), [Zendesk AI Agents](/zendesk-ai-agents), [Salesforce Agentforce](/salesforce-agentforce), [Glean](/glean), [Augment Code](/augment-code) and [Julius AI](/julius-ai).
**Claude via a broad model-agnostic or BYOK layer (26)** — Claude is one of many, often dozens, of named providers reachable through a generic bring-your-own-key or LiteLLM-style integration, not a vendor-curated shortlist: [Agno](/agno), [Aider](/aider), [Botpress](/botpress), [Cartesia](/cartesia), [Cline](/cline), [Deepgram Voice Agent API](/deepgram-voice-agent-api), [Dify](/dify), [ElevenLabs Conversational AI](/elevenlabs-conversational-ai), [Google ADK](/google-adk), [GPT Researcher](/gpt-researcher), [Juggler](/juggler), [Junie](/junie), [LangGraph](/langgraph), [LiveKit Agents](/livekit-agents), [LlamaIndex](/llamaindex), [Mastra](/mastra), [Microsoft Agent Framework](/microsoft-agent-framework), [n8n](/n8n), [OpenCode](/opencode), [OpenHands](/openhands), [OpenClaw](/openclaw), [Pydantic AI](/pydantic-ai), [Vapi](/vapi), [Warp](/warp), [Zed](/zed) and [Zot](/zot).
[Coding agents](/category/coding-agents) lead the count at 19 of 25 — Claude support is close to the category norm, not a differentiator, there. Behind them sit [agent platforms](/category/agent-platforms) at 9 of 16 and [frameworks](/category/frameworks) at 8 of 14. [Sales & marketing agents](/category/sales-marketing-agents) has just 0 entry, Clay, and [support agents](/category/support-agents) just 1, Zendesk AI Agents — Claude access is still the exception, not the rule, in both categories.
Why this collection
A tool earns a place here only if its own Published, sourced listing's `attributes.modelLLM` field — or, where that field alone was ambiguous, its `whatItDoes`, `keyFeatures` or `integrations` text — names Anthropic or Claude specifically as a model the tool itself runs on. Being callable BY Claude does not qualify: an MCP server or tool API that Claude connects to is excluded even where its own fields name Claude. A generic "model-agnostic" or "bring your own model" claim with no provider named anywhere in the listing does not qualify either, even if Claude would technically work through it. Every entry is additionally sorted into one of three tiers: Claude-only (no other vendor's models are offered at all), Claude among a small vendor-picked set of frontier models, or Claude reachable through a broad model-agnostic/BYOK layer alongside many other named providers. Membership is re-derived from the live corpus entry by entry on every re-read of this page, against each listing's own already-researched, gate-passed fields — never from the `claude` tag, which is maintained on
46 agents in this collection
Best for Developers already building on Claude (or Claude Code) who want its exact agent loop, tools and context management as a callable library, and are comfortable being single-vendor on Anthropic in exchange for the tightest possible integration with Claude Code's own capabilities.
Claude-only by design — Opus 5, Sonnet 5 and Haiku 4.5, with no third-party model support at all.
Best for Developers and teams who want a terminal-native, scriptable agent that composes with CI and real engineering workflows.
Runs exclusively on Claude — Opus and Sonnet 5 — as Anthropic's own first-party coding agent.
Best for Founders, designers and developers who want a working, deployed full-stack app straight from a prompt, Figma frame or Google Stitch design, with zero local setup.
Runs on Claude only — Sonnet 4.6 by default, with Opus 4.7 for harder reasoning and Haiku 4.5 for quick edits.
Best for Professional developers who want a powerful AI agent woven into a familiar VS Code-based editor, with first-class model choice and the option to be hands-off via Cursor Router.
Claude is one of three selectable per-request models, alongside GPT and Gemini.
Best for Enterprise and team developers already in GitHub and mainstream IDEs who want governed, reviewable AI coding at scale, with optional access to Claude Code and OpenAI Codex through the same interface.
Claude is one of three selectable models in Copilot Chat, alongside GPT and Gemini.
Best for Developers who want a full, agent-native desktop IDE and the freedom to run several coding agents, including third-party ones, side by side.
Claude sits alongside GPT and Gemini as a general model option, on top of Windsurf's own SWE-tuned models.
Best for Developers already inside the Google ecosystem (Google AI subscription, GCP billing) who want a free terminal agent with Gemini, Claude and gpt-oss model access, especially anyone migrating off a now-sunset Gemini CLI workflow.
Claude Sonnet & Opus 4.6 are available on the free tier, alongside Gemini 3.1 Pro and 3.5 Flash.
Best for Researchers, analysts and knowledge workers who want fast, sourced answers, plus an autonomous research mode and an agentic browser.
Claude is one of six selectable models for Pro users, alongside Sonar, GPT, Gemini, GLM and Kimi.
Best for Teams that want a proven, enterprise-scale, compliance-certified voice AI vendor with a research-led model roadmap, and are prepared to start with a sales conversation: there is no self-serve or free way to trial it today.
Claude joined PolyAI's own proprietary Raven model as a selectable option in May 2026, alongside GPT-5 and Gemini.
Best for Engineering teams offloading well-scoped migration tasks without adding headcount
Claude runs alongside GPT, Gemini and Cognition's own SWE-tuned models under the hood.
Best for A consultant, marketer, founder or operations lead who wants research, files, code, slides and media handled in one web workspace.
One of nine specialized models — with GPT, Gemini, DeepSeek and others — its Super Agent routes across and cross-checks.
Best for Revenue, ops, and customer success teams running 5+ agents in production, who want multi-agent orchestration with evals, tracing, and SSO-grade governance on one bill.
Claude is one of three models its router can select per task, alongside GPT and Gemini.
Best for Small teams or solo operators who want pre-built AI agent roles, shared files, and OAuth-driven workflows under one credit-based subscription.
Claude is one of several selectable models — alongside GPT, Gemini, Kimi, DeepSeek or Vecbase's own — billed per token.
Best for Non-technical founders who want a chat prompt to become a deployed, database-backed app
Claude runs alongside other frontier models Replit Agent can call on.
Best for Engineering teams, using a coding agent or writing code by hand, that want automatic, consistent PR review plus triage, explanation and continuous security across GitHub, GitLab, Bitbucket or Azure DevOps before a human reviewer looks at it.
Claude Opus/Sonnet/Haiku power its review backend alongside OpenAI models, orchestrated internally rather than user-selectable.
Best for Support teams already committed to (or actively evaluating) Zendesk as their core helpdesk who want the AI agent to come from the same vendor and billing relationship, rather than layering a third-party agent on top.
Anthropic models are supported alongside the primary GPT-4o backend and Google/Amazon Bedrock options.
Best for Salesforce service, sales, field-service and employee-support teams that need agents to act on CRM records and have Salesforce admin or developer capacity.
Claude is one of the model options admins can select, alongside GPT-5.x, Gemini or a bring-your-own-model, not the default.
Best for Large and mid-market enterprises whose biggest AI-agent blocker is fragmented, permission-sensitive knowledge scattered across 100+ internal tools, and who want employees building department-specific agents on that indexed knowledge without writing code.
Admins enable and switch to Claude from an LLM admin console, alongside GPT and Gemini, on top of Glean's own retrieval layer.
Best for Knowledge workers who want to query data in plain language without writing SQL
Claude Sonnet 5 and Claude Fable 5 are among the licensed frontier models it runs on, with GPT-5.6 and its own in-house models, depending on plan tier.
Best for Python developers who want an Apache 2.0 SDK with memory, knowledge, learning, guardrails and a Control Plane they run inside their own cloud account, and who are comfortable running Docker or a cloud deploy template themselves.
One of 20+ providers reachable through its model-agnostic Python interface, alongside OpenAI, Ollama and others.
Best for Developers who want free, model-agnostic AI pair programming in their terminal
Anthropic is a named provider in its bring-your-own-key setup, alongside OpenAI, DeepSeek and local models.
Best for Engineering-led teams building a multi-channel AI support agent who want an open-source, self-hostable core with an optional managed cloud layer.
Anthropic Claude is one of the model-agnostic options, alongside OpenAI, Google Gemini and open-weight models.
Best for Engineering teams that want an open-source voice-agent SDK with real LLM choice, built on speech models several rival platforms in this category already license as a component.
Reachable for the Line agent layer via its LiteLLM integration (100+ providers); Cartesia's own Sonic/Ink speech models are separate and proprietary.
Best for Developers and teams who want a transparent, open-source, model-agnostic agent they fully control and pay for by usage, with optional flat-rate access to open-weight models.
Anthropic is a named provider in its bring-your-own-key setup, alongside OpenAI or a local Ollama model.
Best for Engineering teams that want a managed speech pipeline with real LLM-provider choice, and regulated enterprises that need a self-hosted or VPC deployment option a typical closed-source voice-agent vendor does not offer.
One of six bring-your-own-key LLM providers — with OpenAI, Google, NVIDIA, Groq and Amazon Bedrock — or Deepgram manages the model for you by default.
Best for Developers and teams who want an open-source, self-hostable platform to build RAG apps and agents with full data control.
One of hundreds of model-agnostic options it can connect, alongside OpenAI, Google and open/local models.
Best for Developers and product teams who want ElevenLabs' voice quality and cloning as the foundation of their agent, and are comfortable assembling the rest of the stack themselves.
One of three bring-your-own-key providers, with OpenAI and Google, or ElevenLabs' own hosted default.
Best for Teams that want Google's own official, actively-developed agent SDK, especially polyglot teams (Python/Go/Java/TypeScript/Kotlin) or anyone building multi-agent systems that need to interoperate across vendors via the A2A protocol.
Reachable via LiteLLM alongside 100+ other providers, on top of native first-party Gemini support.
Best for Developers and AI engineers who want a free, self-hosted research agent they can embed via Python, REST or MCP and run against their own LLM and search keys.
One of several model-agnostic providers — with OpenAI, Google and local Ollama models — it can run on.
Best for Developers who want hands-on visibility into what an AI coding agent is doing to their codebase and accept early-stage, self-hosted, open-source software.
One of six selectable providers — with OpenAI, Gemini, Ollama, OpenRouter and DeepSeek — in its visual, model-agnostic canvas.
Best for Developers and teams already standardized on a JetBrains IDE who want an agent that shares the same debugger, project index, and version control already built into their editor.
Reachable via JetBrains AI credits or bring-your-own-key, alongside OpenAI and Google frontier models, plus local runtimes via Ollama/LiteLLM.
Best for Engineering teams building production agents who need cyclical graphs, durable state and replayable runs
Anthropic is a named provider in the standard model interface its agent runtime exposes, alongside OpenAI, Google and others.
Best for Engineering teams that want to own their voice-agent stack end to end, self-hosted or on LiveKit Cloud, without being locked into one vendor's API.
A named LLM provider in its default pipeline alongside OpenAI and ElevenLabs, or bring your own via LiveKit-hosted Inference.
Best for Engineers building RAG-heavy or document-heavy agents who want an MIT-licensed OSS core with an optional managed parsing and extraction platform on top.
Anthropic Sonnet 4.0 is named as a model LlamaParse's agentic parsing mode can run on, at up to 90 credits per page.
Best for Full-stack JavaScript and TypeScript teams, especially those already building in Next.js or Node, who want agents, durable workflows and memory unified in one framework without adopting a Python-first stack.
One of the 90+ providers its model-agnostic layer supports, documented by name alongside OpenAI and Gemini.
Best for .NET or Python teams already invested in Azure or Microsoft Foundry who want one supported agent SDK, an optional managed hosting path, and a documented migration off AutoGen or Semantic Kernel.
A named provider alongside Azure OpenAI, OpenAI, Ollama and Gemini (via its Go SDK).
Best for Ops and automation teams who want to build agentic workflows visually while keeping data on self-hosted infrastructure.
A named model-agnostic option alongside OpenAI and Ollama that its AI nodes can call.
Best for Developers who want a genuinely free, fully open-source coding agent that works with any model provider, including their own local Ollama models, without being locked into one vendor's terminal tool.
Reachable through its 75+-provider Models.dev integration, alongside GPT, Gemini and local Ollama models.
Best for Open source-minded engineering teams and enterprises that want a self-hostable coding agent platform
One of the two providers its own text names by example — Claude or GPT — for a bring-your-own-key setup that's otherwise model-agnostic.
Best for Developers and self-hosters who already run their own infrastructure and want one personal AI agent that reaches WhatsApp, Telegram, Slack, Discord, Signal and iMessage instead of a separate app.
One of three hosted-account options, with OpenAI/ChatGPT and DeepSeek, plus bring-your-own-key or a fully local model — genuinely model-agnostic, not Claude-first.
Best for Python teams building type-safe agents who also want realtime voice, image generation and embeddings in one SDK, with optional durable execution via Temporal, DBOS, Prefect or Restate.
A named provider in its type-safe, model-agnostic interface, alongside OpenAI, Gemini, Mistral and Ollama.
Best for Engineering teams that want maximum control to build custom voice agents on their own choice of model, voice and telephony.
A named provider — with OpenAI and Google — in its otherwise bring-your-own-model pipeline.
Best for Developers and teams who want one open platform that runs and coordinates multiple coding agents (Claude Code, Codex, Gemini CLI, Warp Agent) side by side across terminal, CLI and cloud, with shared team context and programmatic API access to cloud agent runs.
A named provider its terminal can orchestrate, alongside OpenAI and z.ai — and it runs Claude Code itself as a hosted agent.
Best for Developers who want a fast, open-source editor and the freedom to run Claude Code, Codex, Gemini CLI or other vendors' own agents natively via the Agent Client Protocol Zed created, instead of being locked into one editor's built-in agent.
First-class, named support alongside OpenAI, Google, Mistral, DeepSeek and more — and it natively runs Claude Code as an external agent via the ACP it created.
Best for Developers who want a fast, free, Go-native coding-agent harness with real session-branching control and are comfortable running fast-moving, self-described "beta forever" software from an independent maintainer.
One of 30+ named providers — with OpenAI/Codex, Gemini, Kimi, DeepSeek and more — in its self-hosted, model-agnostic CLI.
Best for Engineering leaders at organizations who want AI agents running full SDLC loops end to end, with humans at the quality gates, rather than inline completion assistants.
Claude Sonnet 4.5 is the recommended default, one of four selectable premium models.
