Anthropic Integrations

VibeKit

VibeKit turns a chat into a live web app. Describe what you want to build and a dedicated AI agent writes the code, deploys it, and hosts it at your own subdomain, all from your phone or browser. Every app gets its own always-available agent that remembers context between sessions, so you keep iterating: message it a change and see it live in minutes. Bring your own key (Anthropic or OpenAI, including ChatGPT sign-in) and AI runs on your own account with zero markup and unlimited sessions, or use the built-in free tier, a rotating pool of free models at no cost. The free plan hosts 2 apps with a real URL, GitHub integration, environment variables, logs, scheduled tasks, and automated QA included. Add a managed Postgres database, a custom domain (buy one in-app with DNS configured automatically), or always-on hosting as you grow. Native iOS app and web dashboard. Ship an idea from your pocket before you ever open a laptop.

Starting Price: $19/month

View Software

OpenWorker

OpenWorker is an open source, local-first AI coworker that gets everyday tasks done from start to finish instead of only returning answers. Users ask for an outcome, such as a renewal brief, incident report, follow-up message, calendar update, sprint summary, or finished document—and OpenWorker works across the tools where the information already lives. It can connect with Slack, Gmail, Outlook, Google Calendar, Notion, HubSpot, GitHub, Attio, Google Drive, Jira, Linear, Asana, Dropbox, Box, files, and other services through one-click or manual connections. It supports cloud, open-weight, and fully local models, including providers such as OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, Kimi, Qwen, and Ollama, and users can switch models when a task calls for something different. OpenWorker researches, gathers context, performs multi-step work, creates polished outputs in chat, Slack, Markdown, PDF, images, or files, and checks in before consequential actions.

Starting Price: Free

View Software

Flint AI

SandboxAQ

Flint AI is a local-first, framework-agnostic AgentOps CLI that helps developers determine whether an AI agent is reliable before it reaches production. One command, flintai scan, analyzes Python source code for security vulnerabilities, misconfigurations, risky tool access, missing guardrails, and quality issues, then uses AI reasoning to triage likely false positives. A second command, flintai eval, sends functional and adversarial prompts to a running agent and scores its responses across more than 35 built-in evaluations, including factual accuracy, instruction adherence, prompt injection resistance, jailbreak resilience, and other runtime behaviors. Each agent receives a reliability score, with findings mapped to OWASP Agentic Security Initiative risks ASI01 through ASI10 and severity scored using CVSS v4.0. Flint AI works with agent frameworks and SDKs including Claude Agents SDK, LangChain, CrewAI, Anthropic SDK, OpenAI SDK, MCP servers, and AutoGen.

Starting Price: Free

View Software

AICostGuardian

AICostGuardian is an enterprise AI cost management platform that helps organizations track, optimize, and control spending across 25+ AI providers from one unified dashboard. It monitors every API call with millisecond precision, calculates cost instantly, and combines provider usage into cross-platform analytics, automated reports, forecasts, and dashboards. Teams can analyze spending trends, compare usage, identify optimization opportunities, and use machine-learning insights and smart recommendations to reduce unnecessary AI expenses. Predictive alerts and anomaly detection warn users about unusual usage spikes and approaching budget overruns, while configurable spending limits help keep consumption under control. Department-level cost allocation, team analytics, granular permissions, and role-based access make it easier to understand ownership and govern AI use across an organization.

Starting Price: $20 per month

View Software

SatGate

SatGate is an agent authority and accountability Layer that governs what AI agents can access, spend, delegate, and execute before a request reaches an API, model, MCP tool, or paid external service. Deployed as an HTTP reverse proxy and MCP proxy, it applies scoped authority, per-agent budgets, route policies, and next-request revocation directly in the request path. Agents badge in once through existing Kubernetes, AWS, or OIDC identity, and SatGate Mint exchanges that identity for a cryptographically signed Macaroon containing limits for scope, budget, expiration, and delegation depth. Capabilities can only become more restrictive as they move through agent chains, preventing sub-agents from escalating beyond the authority they receive. Observe mode measures requests and attributes usage by agent, team, tool, route, and cost center without changing workflows; Control mode enforces hard budget caps before expensive or unauthorized work executes.

Starting Price: $99 per month

View Software

Cloptima

Cloptima is an AI and cloud FinOps platform that brings LLM spend governance, multicloud cost intelligence, Kubernetes optimization, query analysis, and engineering cost controls into one operating model. Its AI gateway lets teams use their own OpenAI, Anthropic, Gemini, Vertex AI, and Amazon Bedrock credentials behind encrypted controls, then apply virtual keys, model policies, token limits, budgets, guardrails, and attribution before calls reach providers. Spend analytics break down usage by provider, model, team, application, environment, user, agent session, tool, workflow, and dimensions, while agent controls track retries, loops, tool calls, and runaway-cost risk. Exact and semantic response caching can reduce repeated usage, and intelligent routing can shift eligible traffic to cheaper or faster models with canary rollout and rollback if quality, latency, or errors regress.

Starting Price: $49 per month

View Software

AICosts.ai

AICosts.ai is a unified AI cost management platform that brings billing and usage data from more than 50 providers into one dashboard. Teams upload provider invoices and exports in PDF, CSV, or JSON format, or push usage events through the developer API, and the platform parses them into a normalized structure without requiring a proxy or changes to production requests. It supports services including OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Vertex AI, Cohere, Groq, Hugging Face, Pinecone, RunwayML, Make, Zapier, and n8n. Daily views break spending down by platform, model, and billed unit, including tokens, operations, characters, and other provider-specific measures, helping users compare services and see where each bill comes from. Budgets can cover the full AI stack or a specific platform or feature, with email alerts when rolling 30-day spending crosses configured thresholds.

Starting Price: $19.99 per month

View Software

Burnwise

Burnwise is an AI cost copilot that shows where an organization’s AI budget goes, why spending changes, and what actions can reduce it without sacrificing product quality. It tracks usage across LLMs, image generation, video, and audio from major providers through a single SDK and unified dashboard. Instead of stopping at aggregate token charts, Burnwise attributes costs to individual product features, users, sessions, teams, and agent workflows, helping teams understand the true cost of functions such as chat support, document analysis, summaries, or translation. Usage intelligence highlights cost-to-value mismatches, while anomaly alerts identify sudden spikes and runaway prompts in real time. Burnwise delivers a small set of prioritized decision cards with estimated savings, risk, and quality impact, covering actions such as switching models, enabling semantic caching, setting limits, or changing how a feature runs.

Starting Price: €9 per month

View Software

TokenAtlas

TokenAtlas is an AI FinOps and cost intelligence platform that helps teams understand, forecast, and optimize AI costs before they become expensive. Users describe a workload by entering the model, input and output token volumes, request counts, and growth assumptions, and TokenAtlas prices the scenario against a maintained catalog of published API rates. The cost modelling dashboard brings configured workloads into one view, while model comparison places provider and model options side by side using transparent assumptions. What-if scenario planning shows the cost impact of launching a new prompt, agent, model swap, retrieval pipeline, or traffic increase before it reaches production. Cost risk analysis identifies the workloads most sensitive to changes in volume, prompt size, or model choice, and benchmark comparisons show how a modeled model mix compares with typical AI product and infrastructure profiles.

Starting Price: $190 per year

View Software

ZenLLM

ZenLLM is an AI cost optimization platform for engineering teams running LLM applications in production. It connects provider invoices to the application behavior behind them, showing which prompts, workflows, models, customers, retries, and request paths are driving spend. Teams send request-level telemetry through the ZenLLM SDK and can attach business context such as workflow, owner, customer, team, or product feature without storing prompt or response content. It monitors token usage, model selection, latency, errors, retries, and cost, then surfaces the waste patterns hidden by aggregate provider dashboards. It detects context accumulation when conversations or agents resend growing histories, premium-model overuse on low-risk work, retry loops that repeat expensive context, stale system prompts, routing mistakes, anomalies, and weak cost ownership.

Starting Price: $49 per month

View Software

LLMeter

LLMeter is an open source AI cost monitoring platform that gives developers one dashboard for tracking spend across OpenAI, Anthropic, DeepSeek, OpenRouter, Mistral, and Azure OpenAI. Teams connect read-only provider keys and can see real costs, daily trends, model-level breakdowns, and optimization opportunities in about 30 seconds without installing an SDK, changing endpoints, or routing production traffic through a proxy. Because requests continue going directly to the model provider, LLMeter adds no latency, does not become a point of failure, and never sees prompts or completions. Budget alerts warn teams before spending crosses daily or monthly limits, while anomaly detection identifies unexpected usage spikes before they grow. The dashboard shows which providers, models, endpoints, customers, and environments are driving costs, and OpenRouter support extends visibility across more than 500 models.

Starting Price: $19 per month

View Software

LLMetrics

LLMetrics is LLM cost tracking software for teams shipping AI products, bringing model spend, token usage, feature attribution, and usage alerts into one live dashboard. It supports more than 100 models across OpenAI, Anthropic, Google Gemini, Mistral, Cohere, Together AI, Groq, and other providers, with pricing data synchronized daily. Teams tag each model call with a feature name, provider, model, input tokens, and output tokens, allowing them to see exactly whether a chatbot, summarizer, search feature, lesson generator, or other workflow is driving spend. Real-time updates and daily trend charts reveal how costs change after releases, prompt edits, traffic growth, or model swaps. Spend thresholds and spike-detection rules can alert teams through email or Slack when usage patterns look wrong, helping them catch runaway loops and unexpected cost increases before the provider invoice arrives.

Starting Price: $49 per month

View Software

AI Cost Board

AI Cost Board is an AI API observability and cost control platform that brings costs, requests, tokens, latency, errors, and usage from multiple model providers into one real-time dashboard. Applications route LLM traffic through a single proxy endpoint, while requests are forwarded to the connected provider and logged with model, token, status, timing, costs, input, output, and raw JSON context. In most cases, teams only replace the provider base URL and use an AI Cost Board project key, keeping the original request structure intact. It supports providers including OpenAI, Anthropic, and Google Gemini, with a consistent setup that standardizes usage data across integrations. Cost analytics break spending down by project, provider, model, and timeframe, showing trends, cost per request, success rates, and operational performance. Searchable request logs help developers inspect payloads, troubleshoot failures, compare models, and investigate slow or expensive calls.

Starting Price: $9.99 per month

View Software

FlowRunner

Midnight Coders

FlowRunner is a visual workflow automation platform with native AI agent orchestration. Agents run workflows autonomously and pause for human judgment where it is required. The difference is how oversight works. On most platforms, approval is a step the workflow passes through. In FlowRunner, an agent invokes a human as a callable tool at runtime: it assembles the context and choices, routes to a named person by email, Slack, WhatsApp, or phone, and resumes with the answer. A run can stay suspended for up to a year, so a decision that takes three days does not time out. Audit trails, RBAC, and SLA tracking arrive at mid-tier, not in a custom enterprise contract, and a BAA is available. Every tier includes unlimited users, unlimited workflows, and the entire integration catalog, with nothing gated by seat or connector. Billing is per workflow run, not per action step. Agents use your own AI provider keys, with no markup on inference. Cloud-hosted or self-hosted.

Starting Price: $45/month

View Software

Archestra

Archestra is an open source, self-hosted AI platform for deploying and governing agents across an organization. It provides agentic chat for non-developers, apps and skills, shared projects, a server-side agent runtime, MCP orchestration, permission-aware RAG, LLM and MCP proxies, security guardrails, and observability in one platform. Users sign in with SSO, and every tool call runs under that person’s own identity rather than a shared service account. Projects keep chats, files, scheduled tasks, and instructions together, while agents run in sandboxed containers and can start from schedules, emails, or webhooks. MCP servers run in the organization’s own Kubernetes environment and move through security-reviewed promotion flows with separate credentials and network policies. Knowledge bases can connect Confluence, Jira, drives, and internal documents while preserving source-system ACLs, so users only retrieve content they are already allowed to access.

Starting Price: Free

View Software

Better Claw

BetterClaw is a no-code AI agent builder for teams that need agents working, not infrastructure. Users can describe a job in chat, connect tools and an LLM provider, and deploy autonomous agents without Docker, YAML, config files, or VPS hosting. Agents can run on schedules across Telegram, Slack, Discord, Gmail, and custom webhooks, while tracked task states show work as backlog, ready, running, success, or failure and let failed runs be re-queued. The platform runs any OpenClaw-compatible skill and includes curated skills that pass a four-layer security audit. Teams can turn successful conversations into reusable skills, connect more than 30 LLM providers, and have agents return real deliverables including PDF, DOCX, XLSX/CSV, images, audio, video, and Markdown rather than chat text that must be copied manually. Built-in security includes AES-256 encrypted credentials, isolated containers per agent, five-minute secrets auto-purge, per-agent credential grants, access audit logs, etc.

Starting Price: $49 per month

View Software

ZGI

ZGI is an open source enterprise AI platform for building business-ready agents with company data, tools, workflows, models, and skills. Its Agent Runtime lets agents load Skills, use company knowledge and live data, call tools, and return useful work fast. The Model Gateway connects global and domestic providers such as OpenAI, Anthropic, Google, DeepSeek, and Qwen, allowing teams to choose the right model for each agent by quality, availability, cost, or region while centrally controlling access, quotas, routing policies, and fallback. The product workspace covers the full agent lifecycle: Agent Studio combines Skills, knowledge, tools, and models; Workflows orchestrate multi-step work and let users inspect every execution; Database supports natural-language queries over live business data with governed access; Model Management handles provider connections and enterprise routing; and Knowledge Assets turn company files into searchable, source-aware knowledge.

Starting Price: Free

View Software

Agiloop

Agiloop is an AI-native product development platform that connects the complete software lifecycle, from idea and requirements through implementation, measurement, and continuous improvement. INVENT uses AI-guided interviews and repository analysis to turn a new idea or existing application into structured functional and technical specifications, detailed features, user stories, and acceptance criteria. IMPLEMENT takes approved specifications and builds complete features directly in your Git repository, with integrated code review, test scaffolding, acceptance-criteria validation, security checks, and support for existing CI/CD pipelines. INSPECT instruments generated features at build time, providing real-time usage analytics, user journeys, event tracking, metric goals, and AI analysis without separate tracking setup. ITERATE evaluates business outcomes, application health, architecture, and technical debt, then recommends implementation-ready improvements and can push them directly.

Starting Price: $0.25 per story point

View Software

Slack Code

Slack

Slack Code is a collaborative coding experience that brings teammates and AI agents together to build software in the open. Mentioning an agent can start a temporary code channel for a specific task, giving the team a dedicated place to follow the work, provide direction, review changes, and approve the result without cluttering regular channels. Agents begin with the conversations and knowledge they are permitted to access, helping them work with useful team context from the start. Users can describe what they want built and let an agent produce working code while everyone follows along, weighs in, and decides what ships. Code channels archive automatically when the task is complete, while their context remains searchable for future reference. Agents are organized in the Agents tab, where users can check sessions, monitor live status, and see when input is needed. Smarter threads create clearer titles so previous work is easier to find and resume.

Starting Price: $4.38 per month

View Software

Inflowave

Inflowave is an all-in-one CRM and marketing platform built for niche agencies that manage content, ads, messages, leads, and client accounts at scale. A unified inbox lets setters and closers handle DMs, comments, and messages from all connected client accounts in one place, while Smart AI automatically assigns tags, updates custom fields, and moves leads through pipeline stages. Its AI chatbot learns a brand’s conversational style, answers questions, qualifies leads, books appointments, and follows up automatically across Instagram and other supported channels. AI Workflows combine more than 34 triggers and 50 actions for automating Instagram DMs, email, SMS, voice, forms, appointments, payments, CRM updates, and webhooks through either a visual canvas or natural-language instructions. The platform also centralizes multiple ad accounts, helping teams analyze campaign performance, identify high-performing hooks, and connect ad results with customer feedback from conversations.

Starting Price: $149 per month

View Software

Assistable

Assistable is an AI conversation platform for building, testing, deploying, and observing hybrid AI agents that answer calls, texts, WhatsApp messages, and web chats with one persistent memory across every channel. Agents can handle full customer conversations, understand intent, pull information, qualify leads, book, reschedule, or cancel appointments, create tickets, update contacts, add notes and tasks, and escalate to humans when configured to do so. Because memory carries across channels, a customer can call first and continue later by text or chat without repeating the conversation. Users can describe what an agent should do in plain English, connect Assistable through MCP, and have the system create the agent, attach tools, connect channels, and assign a phone number. Agents can read live calendar availability, follow up with leads, and support both inbound and outbound conversations.

Starting Price: $225 per month

View Software

Model Hardware Standard (MHS)

Model Hardware Standard (MHS) is a shared specification that enables AI agents to safely operate physical equipment used in scientific research and advanced manufacturing. It provides a standardized way for agents to discover, understand, and control programmable devices such as microscopes, liquid handlers, robotic arms, sensors, and other lab or factory instruments without requiring bespoke integrations for every machine. MHS introduces standardized drivers built around simple primitives such as read and write, making device capabilities discoverable in a common format across networks. Drivers can also include natural-language metadata about machine characteristics, adjustable parameters, measurements, and enforced safety limits, giving agents the context they need to operate unfamiliar equipment. Once connected, agents can control devices through MCP, command-line interfaces, or APIs, sequence operations across multiple instruments, monitor results, and adjust parameters.

Starting Price: Free

View Software

Switch

Flint AI

Switch is a shared workspace where human teams and AI agents get real work done together in the same room. Instead of keeping knowledge inside a single agent or person, it keeps people, agents, decisions, documents, references, instructions, conversations, and work history together so context survives handoffs and work can continue without repeating what already happened. Switch rooms connect to the messaging apps teams already use, including Slack, Microsoft Teams, Discord, Mattermost, and Telegram, so participants can work with agents without installing anything extra. Agents can be invited into rooms, addressed directly, and reused across teams without being rebuilt for every new workspace. The platform works with existing agent frameworks and providers such as Claude Code, LangChain, Google ADK, OpenAI, Amazon Bedrock, and custom agents, coordinating them through the same shared environment without requiring migration or lock-in.

Starting Price: Free

View Software

OpenTag

OpenTag is a model-agnostic AI coworker that lives in Slack and Microsoft Teams, works with company context, and takes real work off a team’s plate instead of only answering questions. Mention it in a thread, and it can plan the job, use connected tools, complete the work, and return the result where the request started. It runs on its own cloud machine, with each run sandboxed and limited to the tools and permissions connected by the person who asked. OpenTag can work across services such as GitHub, Stripe, Zendesk, Notion, PostHog, HubSpot, Gmail, and internal databases, and can handle recurring tasks by suggesting automations when it notices repeated requests. It also maintains a self-updating company wiki by turning decisions from team conversations into sourced pages and revising them when policies change. Shared context remains available across the team, helping knowledge survive employee turnover.

Starting Price: $50 per month

View Software

Kilo Gateway

Kilo

Kilo Gateway is a universal AI inference gateway that routes LLM requests to any provider through one standardized endpoint, giving developers access to hundreds of hosted and open models without rewriting their applications for each provider. It provides unified access to models from Anthropic, OpenAI, Mistral, and other providers, while also supporting bring-your-own-key configurations that let teams connect existing provider credentials through centralized infrastructure. The gateway is compatible with standard AI SDKs, making it possible to switch providers while keeping the same integration surface. Its infrastructure handles routing complexity and load balancing across direct providers and external gateways to improve availability and resilience. Auto Model can route each request to the best available model while keeping routing decisions, model behavior, and usage visible and controllable.

Starting Price: $19 per month

View Software

VibeView

ScriptX

VibeView – Browser-based iOS, Android, Apple TV and Android TV cloud simulators with agentic live connection capabilities, AI-powered mobile app testing, an embeddable device SDK, and instant shareable app previews. The tools lets developers, QA teams and product managers run mobile apps in the browser without a Mac, Xcode, Android Studio or physical devices. Upload an iOS or Android build and stream a live simulator in seconds, then share a link so teammates, clients, beta testers or sales prospects can interact with the app instantly – no install, no TestFlight, no provisioning profiles. VibeView can also be used as a development tool, not just a testing one. Run vibeview dev and your React Native app streams to a browser simulator with full hot reload – edit code locally, see it live in seconds, without a Mac, Xcode, Android Studio or a physical device.

Starting Price: $19/month

View Software

Rune IDE

Rune is a fast, keyboard-driven IDE for power users that brings code, terminals, CLI tools, language intelligence, debugging, and AI agents into one composable, multi-workspace environment. Built around the Unix way, it keeps powerful development tools close together without forcing developers into a mouse-heavy workflow. Rune ships with three built-in editing modes, a standard editor for users coming from VS Code, Cursor, or Sublime; modal editing for Vim and Neovim users; and an Emacs-style editor, with keybindings applied throughout the interface. Workspaces combine files, terminals, tasks, debugging, search, and language intelligence, and can run locally or on remote machines. Rune Agent lives in the same workspace as the code, where it can read and edit files, search the codebase, run commands, use tools, and maintain full conversations. It supports OpenAI, Codex, Anthropic, Claude, Gemini, Amazon Bedrock, local models, and custom OpenAI-compatible endpoints.

Starting Price: $10 per month

View Software

Sprinklr

Sprinklr is the definitive AI-native customer experience management platform, built to help the world's biggest brands deliver extraordinary experiences across every touchpoint. Its Unified-CXM approach breaks down silos by connecting conversations across marketing, insights, social, and customer service on one platform, so customer-facing teams can collaborate seamlessly and act on a single, real-time source of truth. With over a decade of AI purpose-built for customer experience infused into every workflow, Sprinklr helps enterprises unify their teams, tools, data, and channels, elevate every interaction with human-AI collaboration, and turn customer experience into a lasting competitive edge.

View Software

WEM

WEM No-Code B.V.

WEM No-Code is an enterprise application platform combining no-code development with governed agentic AI orchestration. Business teams build and deploy production-grade applications, automate complex workflows, and run AI agents across operations — without writing a single line of code. Unlike generic automation tools, WEM No-Code's micro-agent architecture ensures AI operates only within structured, auditable workflows. Every agent action is validated by business rules and human checkpoints, making it the platform of choice for regulated industries including financial services, government, healthcare, and logistics. Trusted by KPN, Novo Nordisk, Achmea, Arval, Getronics, and the Dutch Ministry of Finance. ISO 27001 and ISO 9001 certified. 500+ enterprise teams across Europe. Headquartered in Amsterdam since 2012.

View Software

LayerLens

LayerLens is an independent AI model evaluation platform for understanding how models perform through verified results across benchmarks, prompt-level results, agentic benchmarks, and audit-ready comparisons across vendors. It helps teams compare more than 200 AI models side by side, with transparent benchmarks, model comparison tools, and consistent evaluation methods for accuracy, latency, behavior, and real-world applicability. LayerLens is built for deep model analysis through Spaces, where teams can group benchmarks and evaluations, explore task strengths, and track performance patterns in context. It supports continuous evaluation by running ongoing evals across model versions, prompt changes, judge updates, and live traces, helping teams detect quality regressions, drift, silent failures, contamination, and policy issues before they affect production.

View Software

AccessOwl

AccessOwl is an Access Governance and SaaS management tool that simplifies the management of employee access to SaaS applications, from onboarding to offboarding. As the central hub for SaaS access, it eliminates the need to ask who manages specific tools or what approval is required, while tracking every app, user access, and permission used in the organization. AccessOwl automates user account provisioning, access requests, approvals, reviews, and Shadow IT detection, helping teams replace spreadsheets with a source of truth and reduce the risk of missed offboardings. It integrates with Slack so employees can request access directly where they already work, and HRIS integrations automate employee onboarding and offboarding while syncing employee details such as title, department, and manager. AccessOwl can provision and deprovision users across hundreds of SaaS applications without requiring SCIM or SAML.

Starting Price: $4.50 per month

View Software

RouterBase

RouterBase is a unified API gateway that gives developers and teams access to 200+ AI models, including GPT, Claude, Gemini, Llama, Mistral and DeepSeek, through a single OpenAI-compatible endpoint. Instead of maintaining separate keys and billing for each provider, you switch models with one line of configuration. RouterBase adds smart routing, automatic failover across providers, and unified billing, so your application keeps running even when an upstream provider has an outage. A free tier is available with no credit card required.

Starting Price: $0

View Software

DeepInfra

DeepInfra is an AI inference cloud that makes it simple to run the latest machine learning models at scale, including LLMs, vision models, embeddings, image generation, video generation, speech, and more. It provides serverless inference through simple APIs, allowing developers to integrate production-ready AI models without managing GPU infrastructure, autoscaling, deployment complexity, or model hosting operations. DeepInfra supports OpenAI-compatible APIs for LLMs and embeddings, making it easier to switch from existing OpenAI-style integrations while accessing a broad catalog of open and commercial models. Its Native API gives access to every model type available on the platform, including image generation, speech recognition, object detection, token classification, fill-mask, image classification, zero-shot image classification, and text classification. DeepInfra is optimized for scalable, low-latency inference and runs models on high-performance GPU infrastructure.

Starting Price: $1.98 per hour

View Software

JackHamr

JackHamr is the AI coding agent that ships software end-to-end. Instead of a single AI assistant, it orchestrates specialist agents: a spec agent writes requirements, a planner breaks them into tasks, a builder writes code, a tester runs tests, a reviewer checks quality, and a shipper deploys. Agents run on hosted cloud dev environments with VS Code, Docker, SSH, and WireGuard-encrypted networking, so you can close your laptop and they keep working. Talk to them with push-to-talk voice chat or type naturally. GitHub is built in: one-click clone, automatic branch-per-task, real-time commit sync, and PR creation. Bring your own LLM keys (OpenAI, Anthropic, Google, or self-hosted) or use ours at cost, and swap models mid-pipeline. Pay-as-you-go with itemized billing: infrastructure at cost, LLM tokens with zero markup. $10 free credit to start, no card required.

Starting Price: $0 to start, pay-as-you-go

View Software

OpenParser AI

OpenParser AI is an AI-powered truth hub for document-heavy businesses, built to turn documents, databases, and website content into a single secure knowledge layer. Ask a question and let AI find answers across your documents, databases, and websites, with every answer cited back to the exact document page, database row, or web paragraph it came from. OpenParser provides intelligent document management, plain-English document Q&A, database querying with no SQL required, website content search, cross-document intelligence, role-based access, document approval workflows, instant verification, and structured outputs your team can act on directly. Teams can upload documents or connect to Google Drive, SharePoint, SQL databases, and website URLs, while auto-sync keeps sources current. The OpenParser AI Engine reads and reasons across everything, powered by Llama by default or the user’s own LLM, including OpenAI, Anthropic, Gemini, and more.

View Software

flo2

Data Products LLP

flo2 is an LLM gateway and router that provides access to major AI model providers (OpenAI, Anthropic, Groq, Cerebras, DeepInfra) through one unified, OpenAI-compatible API. Smart routing picks the cheapest or fastest model per request. Automatic fallback keeps applications running when a provider goes down. Racing mode runs requests across providers in parallel. Full cost accounting per request, per model, per project. Developers use their own provider keys via flo2.com — RapidAPI's testing tier includes free tokens for evaluation.

Starting Price: 0

View Software

Claude for Teachers

Anthropic

Claude for K-12 Teachers helps educators get back to why they started teaching by reducing the time spent on planning, prep, and paperwork, so they can focus more on students. Built for K-12 teachers, Claude can draft lessons, quizzes, assessments, student materials, presentations, emails, newsletters, and differentiated classroom resources in minutes, while keeping the teacher in control to review, adjust, and decide what is right for the class. Claude can connect to Learning Commons, giving it access to academic standards across all 50 states and grounding lesson plans in evidence-based curricula, including materials from Illustrative Mathematics and OpenSciEd. Educators can ask Claude to plan a standards-aligned lesson, update existing files, create a do-now, worked example, exit ticket, or presentation, and use the connected curriculum context to make the output more classroom-ready.

View Software

Command Code

Command Code is a frontier coding agent that lives in the terminal, builds full-stack projects, ships features, fixes bugs, writes tests, and refactors code while continuously learning how each developer works. Powered by the meta neuro-symbolic taste-1 model and continuous reinforcement learning, it treats every accepted suggestion, rejection, and edit as a signal, turning recurring choices, structures, patterns, and tooling preferences into project-level skills and persistent memory. Instead of relying only on generic best practices, it learns code-review habits, style preferences, architectural decisions, package managers, libraries, and small conventions developers rarely document, then applies the relevant taste context in future sessions. Command Code supports interactive CLI work, headless prompts, automated execution, plan mode, background sandboxes, custom agents, checkpoints, and memory across sessions.

Starting Price: $1 per month

View Software

Ask Sage

BigBear.ai

Ask Sage is a secure, model-agnostic generative AI platform built for government, defense, and regulated organizations that need to use sensitive data across mission-ready workflows. It provides one multimodal workspace for more than 150 commercial, frontier, and open-source models, supporting text, code, image generation and analysis, video, and audio without locking teams into a single provider. Users can ingest organizational data once and reuse it across models for grounded document Q&A, drafting, summarization, knowledge management, policy checks, data analysis, and role-specific outputs. Ask Sage Chat offers a conversational interface, while Workbook brings sources, memos, shared chat history, and team collaboration into one document-centered environment. Agent Builder uses a visual, node-based canvas to create, preview, reuse, monitor, and orchestrate automated workflows without code.

View Software

Cloudgov.ai

Cloudgov.ai is an agentic AI FinOps platform for continuous cost and policy governance across cloud, multicloud, data, container, and AI environments. It brings AWS, Azure, Google Cloud, Oracle Cloud, Snowflake, Databricks, Kubernetes, OpenAI, Anthropic, and Gemini into one control plane, giving teams a live view of cost, allocation, policy, and risk. Continuous Multicloud Observability connects accounts, analyzes historical spending, filters costs by region, account, and service, and forecasts future spend from history. AI-driven insights identify waste and optimization opportunities, while anomaly detection highlights unexpected spending surges and their financial impact. Ready-to-use Infrastructure as Code remediation snippets help engineering teams apply recommended changes, and Jira integration turns insights and anomalies into assignable work.

View Software

Waterfall

Waterfall is a credit infrastructure for platforms building on large language models, designed to turn AI usage into a business model without requiring teams to build their own billing stack. It gives each user, agent, or team a stablecoin-backed credit wallet, then meters every model call by provider, model, token count, and cost. Requests can be routed through the Waterfall Gateway or integrated through TypeScript and Python SDKs, with usage attributed to the correct wallet in real time. Each API call settles atomically against the wallet as it happens, so credits decrease, and revenue is recognized per request instead of through delayed invoices and manual reconciliation. Waterfall supports more than 300 models across providers such as OpenAI, Anthropic, DeepSeek, and xAI, allowing products to use multiple AI services while maintaining one accounting layer.

Starting Price: $20 per month

View Software

FinOps LLM

FinOps LLM is an AI cost management and LLM observability platform for engineering teams running production GenAI. It makes token spend visible across OpenAI, Anthropic, Amazon Bedrock, Google Gemini, Azure, Groq, and other providers and reconciles internal usage data against provider invoices. Token-level costs can be filtered by provider, model, feature, team, customer, environment, and custom dimensions, giving every dollar a clear owner. Attribution and chargeback tools map usage to product surfaces and customer cohorts, support showback, and export data to NetSuite, QuickBooks, CSV, or APIs. Real-time anomaly detection monitors spend, latency, and quality against rolling feature baselines, sending alerts through Slack, PagerDuty, email, or webhooks when behavior changes. Optional budget enforcement and auto-throttling can stop runaway agents, retries, or model shifts before they become expensive.

Starting Price: $1,500 per month

View Software

Mongrel

VisorCraft, LLC

Mongrel is a desktop database systems workbench that unifies 30+ database engines, terminals, file transfer, containers, Kubernetes, and an API client in one native app for Windows, macOS, and Linux. Query PostgreSQL, MySQL, MongoDB, SQL Server, Oracle, Redis, ClickHouse, Snowflake, BigQuery, and more in native SQL or engine dialects. Edit data inline, drill through foreign keys, run EXPLAIN plans, design schemas on a visual ER canvas, sync data between databases, and schedule encrypted backups. Built-in SSH/Mosh/Telnet/Serial terminals, SFTP/SCP file transfer, Docker and Podman management, Kubernetes operations, and an HTTP/GraphQL/WebSocket/gRPC client replace a stack of tools. An opt-in AI assistant supports OpenAI-compatible, Anthropic, and Gemini providers, with keys in your OS keychain and writes always approval-gated. Mongrel is local-first: your queries, data, and logs never leave your machine. All plans include every feature; start with a 7-day trial, no card required.

Starting Price: $99/user/year

View Software

DeskFerry

DeskFerry is an agentic platform for building an AI team just by describing what you need in plain English. It creates AI agents, connects them to the tools your team already uses, and runs recurring work across 1,500+ apps without code. Agents can read, write, and act inside services such as Gmail, Slack, Notion, Salesforce, HubSpot, Jira, Stripe, and more, while users can choose from AI models by OpenAI, Anthropic, Google, xAI, and others. Custom skills let teams teach agents to match brand voice, build branded artifacts, and file outputs in the right tools and formats. Built-in scheduling and triggers allow automations to run hourly, daily, weekly, or when events occur in connected apps. Human-in-the-loop controls can require approval before emails are sent, records are updated, or other critical actions are taken. Knowledge can be added through documents, databases, and URLs, and memory helps automations retain past conversations and preferences over time.

Starting Price: $19 per month

View Software

Keenable

Keenable is an independent web search infrastructure built for AI labs, inference platforms, agents, and developers that need fast, high-quality access to the live web. Its Search API gives AI systems a web-scale index of more than 100 billion documents and is designed for low-latency retrieval, with performance optimized for production agent workloads. Agents can search web pages and fetch page content through a REST API, MCP server, or command-line interface using the same account and API key. It continuously evaluates and improves search quality using its NEEDLE benchmark, which compares retrieval performance across search providers and measures results against an oracle ranking built from pooled results. For larger AI workloads, Keenable supports dedicated search capacity as well as cloud and on-premises deployment options. Its Time Machine capability extends retrieval beyond the current web by providing point-in-time search across historical versions of pages.

View Software

Claude Computer Use

Anthropic

Claude Computer Use is a feature that allows Claude to interact directly with your computer to complete tasks. It enables the AI to click, type, open applications, and navigate files just like a human user. The system prioritizes using built-in connectors, but can fall back to browser navigation or full screen interaction when needed. It can perform tasks such as compiling reports, filling spreadsheets, and testing applications. Users must grant permission before Claude accesses any application, ensuring control over what it can do. The feature includes safeguards to reduce risky actions and protect sensitive data. Overall, Claude Computer Use extends AI capabilities beyond chat into real-world task execution on your device.

View Software

Claude Security

Anthropic

Claude Security is an AI-powered cybersecurity tool designed to help organizations scan their codebases and fix vulnerabilities efficiently. It analyzes code to identify potential security issues and validates findings to reduce false positives. The platform provides clear explanations of each vulnerability, including severity and potential impact. It also generates suggested patches that developers can review and approve before implementation. Claude Security integrates directly into existing workflows, making it easy to adopt without complex setup. It supports scanning entire repositories or specific sections based on user needs. The system helps streamline the process from detection to resolution in a single workflow. By automating security analysis, Claude Security improves efficiency and strengthens software protection.

View Software

Claude Dispatch

Anthropic

Claude Dispatch is a feature that allows users to assign tasks to Claude from anywhere and have them completed on their desktop automatically. It enables continuous conversations across devices, letting users start a task on mobile and receive results once the work is done. This helps streamline workflows by turning Claude into an always-available task executor.

View Software

Cherry Studio

Cherry Studio is an all-in-one AI assistant and cross-platform desktop client that brings hundreds of AI models into one unified workspace for Windows, macOS, and Linux. It connects to major model providers and lets users switch between different AI services without juggling separate apps, browser tabs, or fragmented workflows. It is designed as a powerful local AI productivity hub, supporting everyday chat, writing, translation, research, coding help, document understanding, image understanding, and multimodal AI workflows from a single interface. Users can configure model providers, manage assistants, organize conversations, and work with different models depending on the task, making Cherry Studio useful for both casual AI use and more advanced experimentation. Its assistant system allows users to create, subscribe to, and manage role-based assistants with specialized prompts for scenarios such as product management, community operations, technical support, strategy, etc.

View Software

PromptUnit

PromptUnit is an AI inference proxy that reduces AI costs automatically by sitting between an app and its AI providers with no code changes required. Teams swap the base URL, keep the same SDK, endpoints, response parsing, and error handling, then PromptUnit handles routing, failover, cost tracking, and quality validation. It logs every API call by model, feature, user segment, token count, latency, and cost, giving real-time visibility into where AI spend is going before any routing changes go live. In observation mode, PromptUnit watches traffic, shadow-classifies requests, forecasts savings, and explains routing decisions so teams can see exact savings before enabling live routing. Once enabled, Smart Routing uses task classification to route each request to the cheapest model that clears the configured quality bar. PromptUnit also includes prompt compression, token inflation defense, prompt efficiency scoring, semantic request caching, and multi-model consensus.

View Software

Anthropic Integrations

126 Integrations with Anthropic

VibeKit

OpenWorker

Flint AI

AICostGuardian

SatGate

Cloptima

AICosts.ai

Burnwise

TokenAtlas

ZenLLM

LLMeter

LLMetrics

AI Cost Board

FlowRunner

Archestra

Better Claw

ZGI

Agiloop

Slack Code

Inflowave

Assistable

Model Hardware Standard (MHS)

Switch

OpenTag

Kilo Gateway

VibeView

Rune IDE

Sprinklr

WEM

LayerLens

AccessOwl

RouterBase

DeepInfra

JackHamr

OpenParser AI

flo2

Claude for Teachers

Command Code

Ask Sage

Cloudgov.ai

Waterfall

FinOps LLM

Mongrel

DeskFerry

Keenable

Claude Computer Use

Claude Security

Claude Dispatch

Cherry Studio

PromptUnit

Related Categories

Related Categories That Integrate With Anthropic