Anthropic's desktop agent for non-coding knowledge work: point it at a folder, describe the outcome, and it does the multi-step work itself.
Agents
Frameworks and helpers for building autonomous agents that plan, call tools and delegate work to subagents.
70 apps, 21 skills and 4 MCP servers tagged Agents.
Apps
Showing 60 of 70.
An Apache-2.0 TypeScript framework for building AI agents — workflows, memory, RAG and evals — with a local studio and an agentic software factory on top.
Agentic data platform that turns business questions into defensible, auditable narratives — with sources, assumptions and lineage attached.
Mac app that exposes your browser, CLI, files and saved logins to Claude, Codex or any MCP agent — with an approval gate on every request.
Open-source computer-use infrastructure: a desktop driver, cloud desktop fleets, local macOS VMs and a benchmark for agents that click.
An AI-native CRM that captures emails, calls and meetings automatically, then runs prospecting, research and follow-up through built-in sales agents.
Gives agents secure, authenticated access to 1,500+ SaaS apps — managed OAuth, a tool router that filters the catalogue, and sandboxed execution.
Open-source, self-improving AI agent from Nous Research that remembers, writes its own skills, runs scheduled jobs and talks to you from desktop, terminal, Telegram, Slack and more.
Free, open-source AI agent app for desktop and mobile that wraps Claude Code, Codex and Pi in one interface and links all your devices.
Open-source, self-hosted control plane that runs teams of AI agents like a company, with org charts, tasks, budgets and approvals.
AI teammate for startups that works from Slack, Telegram, Discord or the web, joins your video calls and handles the follow-up tasks.
Personal AI agent for iPhone that runs multi-step errands in the background — research, files and email from its own @muze.bot address.
An open-source TypeScript framework for building AI agents, paired with VoltOps, a console for tracing, evals, prompt management and deployment.
An open-source platform for durable AI agents and background workflows written in TypeScript, with retries, queues, realtime streaming and run observability.
Agentic analytics platform: ask questions of company data in plain English with Spotter, and use AI agents to build data models, Liveboard dashboards and embedded analytics.
Work management platform with AI agents for research, reporting and risk insights, the Sidekick assistant, AI columns and a vibe app builder, metered by AI credits.
Work and project management platform with 30+ prebuilt AI Teammates, the Asana Dash assistant, no-code AI Studio workflows and MCP connectors for outside AI tools.
Issue tracking and product planning for software teams, with Linear Agent, automated triage and scheduled agent loops built into issues, projects and cycles.
Microsoft's low-code platform for building, testing and governing custom AI agents, workflows and apps, published to Teams, Microsoft 365 Copilot and the web.
Computer-use agent that clicks and types through desktop apps and browsers on its own cloud computer or your Mac/PC, and reruns recurring tasks on a schedule.
Anthropic's proactive personal agent: a morning brief across your connected apps, background monitoring, and tasks it finishes on its own, asking before anything consequential.
Open-source, self-hostable managed agent platform: run durable AI agents on any model and any machine through one API, CLI and SDK.
A research community where independent AI agents discuss open problems and publish reviewed papers.
Microsoft's open-source, policy-driven sandbox SDK for running agents, model-generated code, tools and plugins with only the files and network access you grant.
One key and one balance for 2,500+ data APIs from 90+ providers your AI agent can call over MCP or CLI. Pay per call, price shown first.
Security scanner and runtime monitor for AI agents that audits skills, MCP servers and CLI tools for malicious code and prompt injection.
An agent-native cloud computer that pairs 20+ frontier models with skills, connectors, email and scheduled automations in one sandbox.
Google Labs' household agent: a shared daily brief across up to six family members, with calendars, tasks, meal plans and school paperwork handled for them.
Finds every AI agent an enterprise is running across AWS, Databricks, Google, Microsoft, Salesforce and Snowflake, then measures and risk-ranks them.
Build, test and ship customer-facing AI agents on a visual canvas, with evaluation runs and per-step logs rather than vibes.
AI engineering platform for tracing, evaluating and improving LLM apps and agents — with Phoenix, its open-source local-first counterpart, for teams that want to start without a vendor.
Open-source CLI framework that gives AI agents one command grammar across Salesforce, ServiceNow, DocuSign and Google Workspace, loading each schema only when asked.
AI browser that runs real tasks inside your logged-in accounts, with credentials sealed in an on-device vault the agent never reads.
Agent infrastructure for messaging: describe one AI agent and run it on iMessage, WhatsApp, Telegram, Slack, SMS and email.
Abacus.AI's multi-model assistant: one $10/month subscription across 100+ frontier models, plus an autonomous agent, live meeting transcription and media generation.
Multi-agent workspace where teams hire reusable "digital employees" — an orchestrator runs specialists in parallel and returns finished decks, dashboards, reports and Excel files.
Open-source platform for running a standing team of AI agents — you hire, schedule and review them, and they keep working while you are offline.
Open-source, self-hosted personal AI agent you run yourself — browser UI, terminal or your chat apps, with memory, MCP tools and scheduled automations.
Open-source AI research agent with a CLI and a local science workbench for deep literature review, paper retrieval and replication planning.
A pay-per-call tool layer for AI agents: one balance and one credential across 1,700+ tools from 55+ providers, reachable as a skill, an MCP server or a CLI.
AI-native practice management for small law firms: agents run intake, drafting, deadlines and billing; the lawyer approves every action.
A Y Combinator-backed AI coworker you text from Slack or iMessage: it runs on its own cloud computer, signed into your tools, and keeps a self-updating company wiki as its memory.
An OpenTelemetry-native control plane for AI agents that enforces policy mid-run instead of paging you after the incident, with cost attribution and EU AI Act evidence built in.
Write an agent as a TypeScript function and deploy it in seconds onto KVM-isolated Linux microVMs, with the loop, sessions, streaming and versioning managed for you.
Payment rails for AI agents — a drop-in wallet widget and Purchase API that let an agent buy things on a real card, with the user approving each charge.
AI workspace agent that turns one prompt into slides, documents, spreadsheets, images or video, with reusable Skills you can define and share.
An IT control plane that puts every internal AI agent — whoever built it and in whatever tool — behind one identity, access policy and audit trail.
Reads your production chat and voice agent conversations to surface the silent failures, frustration loops and policy breaches that offline evals never catch.
An open-source layer that lets your customers describe a feature and get a working micro-app inside your product — sandboxed to their own permissions.
Mistral's unified AI agent — Work mode for long-horizon research, analysis and drafting, Code mode for sandboxed coding with GitHub pull requests.
AI agent platform where a coordinator called Otto runs AI "Experts" and scheduled workflows, available in the cloud or self-hosted.
Open-source, MIT-licensed visual builder for AI agents, RAG apps and MCP servers, maintained by IBM's DataStax and extensible in Python.
Retool's AI layer: generate internal apps from prompts on live company data, plus AI workflows and hourly-billed agents with enterprise controls.
Integration layer for AI agents: managed OAuth, 10,000+ prebuilt tools across 3,000+ APIs, an MCP server and an API proxy. Owned by Workday.
Visual automation platform (formerly Integromat) for building app workflows and AI agents, with the Maia assistant and an MCP server.
No-code automation platform linking 9,000+ apps, with AI steps, AI agents, chatbots and an MCP server for AI assistants.
Agentic meeting platform that files issues, drafts follow-ups and logs decisions during Zoom, Teams and Meet calls, without a bot.
AI notes workspace whose agent tracks tasks from your notes and meetings, with voice capture and an MCP connector for Claude and ChatGPT.
Zoom's AI teammate (formerly AI Companion): meeting summaries and notes, agentic search, custom agents and workflows across Zoom and other apps.
Generative AI built into Slack's paid plans: channel summaries, huddle notes, AI search answers, daily recaps and the Slackbot agent.
Skills
Build crash-safe AI agents on AgentKit and step.ai — durable tool calls, human-in-the-loop approval, realtime progress, and when not to reach for an agent loop at all.
The official Genkit skill for Node.js and TypeScript — flows, Dotprompt files, tools and the beta agent API with sessions, interrupts and branching.
Google's entrypoint skill for building ADK agents with agents-cli: a phased lifecycle from spec and recipes through scaffold, build, eval, deploy, publish and observe, with code-preservation rules and a debugging routine.
Google's agents-cli skill for creating, enhancing and upgrading ADK agent projects: scaffold create with the adk_python or adk_go template, deployment targets (Agent Runtime, Cloud Run, GKE), CI/CD runners and a prototype-first workflow.
Vercel's official skill for the AI SDK (the ai package): it makes the agent check the version-matched docs bundled in node_modules instead of memory, set up AI Gateway, list current model IDs and build agents with ToolLoopAgent.
Google's skill for deploying agents with agents-cli to Agent Runtime, Cloud Run or GKE: choosing a target, CI/CD pipelines, service accounts, secrets, rollback, Agent Gateway and production troubleshooting.
Microsoft's official skill for building, deploying, evaluating, fine-tuning and operating agents and models on Microsoft Foundry with azd and the Foundry MCP tools, from project setup and RBAC to quota, tracing and CI/CD.
Mastra's official framework skill: makes an agent check embedded docs in node_modules before writing agents, workflows, tools or memory, verify models against the provider registry, query traces with mastra api, and deploy to Mastra Platform.
Google's skill for writing agent code with the Agent Development Kit (ADK) in Python or Go: agent types, tools, callbacks, state, multi-agent orchestration, the graph Workflow API and a catalogue of reference recipes, used with agents-cli.
Skill: SerpApi Agent Usability Test
by SerpApi
A protocol for measuring whether agents can discover and use your tool without being told about it — WITH/WITHOUT trials, binary scoring, and lift as the only metric. The subject under test is your docs, not the model.
Skill: Sandbox SDK (1.0 Preview)
by Cloudflare
Build on @cloudflare/sandbox@next, the Sandbox SDK 1.0 preview — with a package gate that stops an agent mixing preview APIs into a stable app.
Skill: Handoff
by Matt Pocock
Compress the current Claude Code session into a portable handoff document so a fresh agent can continue the work without re-reading the whole conversation.
Skill: SAIL — Secure AI Lifecycle
by Pillar Security
Pillar Security's SAIL V2 framework as an agent skill: a 91-risk catalogue across seven lifecycle phases, for AI security gap assessments, roadmaps, and ISO 42001 / EU AI Act compliance checklists.
Skill: Composio Tool Router
by Composio
Composio's official skill for reaching 1,000+ external apps from an agent — CLI-driven actions, Tool Router sessions, per-user auth and trigger events.
Skill: VoltAgent Best Practices
by VoltAgent
VoltAgent's official conventions skill — when to reach for an agent versus a workflow, the expected project layout, and the core snippets for agents, workflows, memory and servers.
Skill: Sentry AI Agent Monitoring Setup
by Sentry
Sentry's official skill for instrumenting LLM and agent code — detects your installed AI SDK and wires up traces for model calls, tool use and token spend.
Skill: AGENTS.md Authoring
by Sentry
Write and maintain concise AGENTS.md and CLAUDE.md files that document the conventions an agent actually needs.
Skill: Cloudflare Agents SDK
by Cloudflare
Build stateful AI agents on Cloudflare Workers — durable state, scheduling, RPC, WebSockets, and MCP servers.
Skill: Dispatching Parallel Agents
by Jesse Vincent
Run two or more genuinely independent tasks concurrently, with the briefing and isolation that makes it safe.
Skill: Subagent-Driven Development
by Jesse Vincent
Execute an implementation plan by dispatching independent tasks to subagents, keeping the main context focused.
Skill: Skill Creator
by Anthropic
Create, edit, and optimize Agent Skills — scaffold new skills, refine existing ones, run evals, and tune descriptions for reliable triggering.
MCP servers
Aave's official MCP server: live V3 and V4 markets, wallet positions and health factor, DAO governance, and unsigned transactions your own wallet signs.
MCP: tinymcp
by Golioth
Golioth's experimental MCP server that lets an LLM drive real embedded devices — device RPCs become MCP tools, with schemas stored in LightDB State and calls routed through the Golioth cloud.
MCP: Vapi MCP Server
by Vapi
Vapi's official MCP server for building voice agents — create assistants, place and schedule outbound phone calls, and manage phone numbers from your AI client.
MCP: Sequential Thinking
by Model Context Protocol
A tool for dynamic, reflective problem-solving through structured, revisable sequences of thoughts.
Related tags
Tags that appear alongside this one, ranked by how often.