Anthropic

Anthropic’s Constitutional AI training approach research focuses on developing AI systems safe by design and aligned with human values. By prioritizing safety, we can create strong and corrigible AI systems that are safe for humans to use.

General
CompanyAnthropic
Founded2021
Discordhttps://discord.gg/lablab-ai-877056448956346408

Anthropic Claude

Claude is your friendly and versatile AI language model that can assist you as a company representative, research assistant, creative partner, or task automator.

Claude is Safe, Clever, and Yours. Built with safety at its core and with industry leading security practices, Claude can be customized to handle complex multi-step instructions and help you achieve your tasks.

You can easily use Claude for your app, and all necessary APIs, boilerplates, tutorials explaining how to do so and more, you can find on our Claude tech page.

Claude Code

Claude Code is a command-line tool from Anthropic for agentic coding. It enables Claude to refactor, debug, and manage code directly in the terminal. You can find more information on our Claude Code tech page.

Anthropic AI Technologies top builders

Explore the top contributors showcasing the highest number of Anthropic AI Technologies app submissions within our community.

Anthropic AI Technologies Hackathon projects

Discover innovative solutions crafted with Anthropic AI Technologies, developed by our community members during our engaging hackathons.

Digital Academic Document workflow System

Digital Academic Document workflow System

Agent_Trap_Evals

Agent_Trap_Evals

The problem: agents rarely fail hard questions. They fail chores. They report "backup verified" because the log says success, while the archive is truncated. These false claims slip out during routine work, and a real shell makes them dangerous. What Receipts does: you give it a real task, like checking a backup or triaging a failing build. A control layer plans the work and runs every action in an isolated Vultr sandbox [gVisor pods on VKE]. The sandbox has no secrets, has time and memory caps, and is destroyed after each task. Every command's output, exit code, and files become a receipt. Before any claim reaches you, a verifier checks it against those receipts: did the agent check the layer that matters, or just the easy one? An unsupported claim is blocked and sent back to be verified, or reported as unverified. You get the answer together with its proof. Containment: [demo moment, e.g. the agent runs rm -rf / and the sandbox absorbs it; the host is untouched]. Measured: we score Receipts with agent-trap-evals, an open-source trap set we built before the hackathon from real agent incidents. Verifier off vs. on: [X/Y vs. X/Y caught], [n] false alarms on honest controls. For: platform and DevOps teams putting agents on operational work, where a confident false "done" costs more than a slow answer. Sandboxes like E2B contain actions but don't check claims. Eval tools score offline but don't stop a bad claim at runtime. Receipts does both, live. [Business model; next steps.] All LLM calls use Vultr Serverless Inference.

Agent_Trap_Evals

Agent_Trap_Evals

The problem: agents rarely fail hard questions. They fail chores. They report "backup verified" because the log says success, while the archive is truncated. These false claims slip out during routine work, and a real shell makes them dangerous. What Receipts does: you give it a real task, like checking a backup or triaging a failing build. A control layer plans the work and runs every action in an isolated Vultr sandbox [gVisor pods on VKE]. The sandbox has no secrets, has time and memory caps, and is destroyed after each task. Every command's output, exit code, and files become a receipt. Before any claim reaches you, a verifier checks it against those receipts: did the agent check the layer that matters, or just the easy one? An unsupported claim is blocked and sent back to be verified, or reported as unverified. You get the answer together with its proof. Containment: [demo moment, e.g. the agent runs rm -rf / and the sandbox absorbs it; the host is untouched]. Measured: we score Receipts with agent-trap-evals, an open-source trap set we built before the hackathon from real agent incidents. Verifier off vs. on: [X/Y vs. X/Y caught], [n] false alarms on honest controls. For: platform and DevOps teams putting agents on operational work, where a confident false "done" costs more than a slow answer. Sandboxes like E2B contain actions but don't check claims. Eval tools score offline but don't stop a bad claim at runtime. Receipts does both, live. [Business model; next steps.] All LLM calls use Vultr Serverless Inference.

Quarantine

Quarantine

The user clicks on a suspicious link or downloads an attachment. The agent opens them in a disposable browser container, gathers evidence about what the page or file is attempting to do, and issues a verdict backed by evidence. High-risk final actions (downloading a file, submitting test data to a form, adding a domain to a blocklist) are performed only after human confirmation. - verdict (safe / suspicious / malicious) with a confidence level; - evidence: redirect chain, domain and certificate, network requests, forms and fields, download attempts, page text, checkpoint screenshot; - a log of the agent’s actions and everything the sandbox allowed or blocked.

Agent ai contents generation

Agent ai contents generation

Agent AI Contents Generation is a multi-step AI agent that turns a short brief into ready-to-publish content. The user provides a topic, target audience, tone of voice and desired channels (blog, LinkedIn, X, newsletter). The agent then plans the content, gathers relevant context through web search, and generates drafts for each channel. The system is built as a pipeline of specialised agents: a Planner that breaks the brief into tasks, a Researcher that collects up-to-date facts, a Writer that produces the draft, and an Editor that reviews it for clarity, factual consistency, style and length limits. If the Editor finds issues, the draft goes back for revision until the quality criteria are met. Our goal is to save marketers, founders and creators hours of manual work while keeping a consistent brand voice. Users can adjust tone, length and format, regenerate individual sections, and export the results. In the future we plan to add image generation, post scheduling and analytics-driven optimisation of content.

FlowMedic

FlowMedic

FlowMedic is an AI-powered self-healing workflow agent designed to make workflow automation more reliable, intelligent, and resilient. Built to autonomously detect, diagnose, test, and repair broken n8n workflows, FlowMedic reduces the need for manual debugging and minimizes workflow downtime. When a workflow fails, FlowMedic analyzes the execution errors, identifies the underlying cause, and determines an appropriate fix. Instead of simply suggesting solutions, the agent attempts to implement repairs and validates them through testing in an isolated Vultr sandbox environment. This sandbox provides a controlled space to experiment with potential fixes before applying changes to the actual workflow. By combining AI-driven reasoning, automated debugging, workflow analysis, and isolated testing, FlowMedic transforms traditional workflow maintenance into an intelligent, proactive process. Our vision is to move beyond automation that simply executes predefined tasks toward automation that can understand failures, learn from errors, and recover independently. FlowMedic aims to help developers, businesses, and automation teams build more dependable systems while saving valuable time, reducing operational overhead, and ensuring that critical workflows keep running smoothly. FlowMedic: When workflows break, AI brings them back to life.