# Learn Hyperagent Source: https://www.hyperagent.com/docs Core concepts and reference for working with Hyperagent. Hyperagent is a platform for building AI agents that do real work. Not chatbots that answer questions and forget you. Agents with names, instructions, tools, knowledge, and multiple ways to start a run. You configure an agent once. Then you use it across threads, trigger it from Slack, Telegram, email, or a webhook, schedule it on a timer, or let it watch for changes on its own. Everything it creates (documents, tables, webpages, images, videos, maps) lives in your Library and is searchable forever. The platform compounds. Skills let you teach reusable methods that any agent can pick up. Memories (global or agent-scoped) let agents remember what matters across every conversation. Rubrics measure whether your agents are actually getting better over time. Teams let you share everything with colleagues. *** ## Where do you want to start? [#where-do-you-want-to-start] *** ## Browse by topic [#browse-by-topic] The core of Hyperagent. An agent has an identity (name, icon, system prompt), configuration tabs, multiple ways to start a run, and the ability to delegate to other agents. * [What is an Agent?](/docs/concepts/agents) : The mental model. Not a chatbot, a colleague. * [Agent configuration](/docs/concepts/agents#what-you-configure) : Identity, tools, skills, knowledge, model, invocations, and autonomy. * [Agent delegation](/docs/concepts/agents/agent-delegation) : When one agent hands work to another. * [Knowledge access](/docs/concepts/agents/knowledge-access) : Personal, Curated, Team learning, Custom. Your conversation workspace. @mention skills, memories, documents, and tables to bring context in. Use the Actions menu to suggest learnings, build skills, and run evaluations. * [What is a Thread?](/docs/concepts/threads) : A workspace with @mentions and actions. Portable methods you teach once. Process, context, and integration skills. Pin, attach, or discover them. Fix a skill and every agent using it improves. * [What is a Skill?](/docs/concepts/skills) : Reusable methods that compound across agents. * [How agents load skills](/docs/concepts/skills/how-agents-load-skills) : Pinned, attached, discoverable. * [Edit and import skills](/docs/concepts/skills/skills-edit-and-import) : Day-2 operations and import rules. Facts and preferences that persist across conversations. Memories can be global (visible to all agents) or agent-scoped. Importance 4+ loads automatically. Lower-importance memories surface when relevant. * [What are Memories?](/docs/concepts/memories) : Scoped facts. Global or agent-specific. Auto-surfacing. * [Knowledge access](/docs/concepts/agents/knowledge-access) : What a shared agent can see and learn. Shared workspaces for agents and skills. Two roles (Owner, Member). Three skill-sharing modes (share credentials, BYO, fork). Four Knowledge Access presets control what shared-agent users can see and modify. * [What are Teams?](/docs/concepts/teams) : Share agents and skills without starting from scratch. * [Knowledge access](/docs/concepts/agents/knowledge-access) : Personal, Curated, Team learning, Custom. The gallery of everything your agents create across all threads. Images, webpages, tables, documents, maps, videos, slides, apps. Searchable, filterable, publishable. * [What is the Library?](/docs/concepts/library) : Your artifact gallery across all threads. Tools are built-in capabilities. Integrations are connected external services. Custom MCP attaches your tool server. Hosted MCP lets other clients drive Hyperagent. * [Tools & Integrations](/docs/concepts/tools-and-integrations) : Choose between built-in tools, integrations, MCP, and skills. * [Available tools](/docs/concepts/tools-and-integrations/available-tools) : Built-in tool list. * [Integrations](/docs/integrations) : Connect apps. * [Custom MCP](/docs/integrations/custom-mcp) : Attach an external MCP server. * [MCP server](/docs/concepts/agents/mcp-server) : Drive Hyperagent from MCP clients. *** ## FAQs [#faqs] Hyperagent supports the following models. See the [Supported Models](/docs/concepts/agents/models) documentation for more information. **Anthropic:** Claude Fable 5, Opus 5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 5, Sonnet 4.6, Haiku 4.5 **OpenAI:** GPT 5.6 Sol, GPT 5.6 Terra, GPT 5.6 Luna, GPT 5.5 **Google:** Gemini 3.6 Flash, Gemini 3.5 Flash **Moonshot AI (Kimi):** Kimi K3, Kimi K3 Fast, Kimi K2.6 **Z.ai:** GLM 5.2, GLM 5.2 Fast **Alibaba:** Qwen 3.7 Plus **DeepSeek:** DeepSeek V4 Pro **Sakana AI:** Fugu Ultra **xAI:** Grok 4.5 **Meta:** Muse Spark 1.1 **Thinking Machines:** Inkling See also: [Supported models](/docs/concepts/agents/models) for how to choose effort, budget, and Live Mode defaults. A thread is a persistent workspace, not a disposable conversation. Everything the agent creates (images, tables, webpages, documents) stays in the thread and is searchable later. You can @mention skills, memories, and documents to bring them into context, and use the Actions menu to extract learnings afterward. [Read more: What is a Thread?](/docs/concepts/threads) Skills are methods (how to write a report, how to call an API). Memories are facts (your fiscal year starts in August, your CEO goes by her first name). Skills are always portable across agents. Memories can be global (all agents) or scoped to specific agents. Both have scope settings and both compound over time. [Read more: What is a Skill?](/docs/concepts/skills) Knowledge Access presets control the boundary between creator and user. * **Curated** (recommended for Slack-deployed agents): teammates can run the agent; only linked knowledge is visible; learning from shared chats stays off. * **Team learning**: same linked boundary, but team conversations can improve the agent over time. * **Personal**: broader library access for agents you use yourself. * **Custom**: tune the switches one by one. [Read more: Knowledge access](/docs/concepts/agents/knowledge-access) and [Teams](/docs/concepts/teams) Yes. Global memories are visible to all your agents automatically. Agent-scoped memories are exclusive to one agent. You can also junction-link a memory to specific agents. The memoryScope setting on each agent controls what pool it draws from: "global" sees everything, "selected" sees only its own. [Read more: What are Memories?](/docs/concepts/memories) A run can start from a thread, Slack, Telegram, a schedule, Live Mode, email, a webhook, or another agent (delegation). Live Mode is watch-and-alert on an interval. Hyperagent's hosted MCP server lets external MCP clients drive threads; it is not a separate agent trigger type in settings. * [Invocations and deployment](/docs/concepts/agents/invocations) * [Live Mode](/docs/concepts/agents/invocations/live-mode) * [MCP server](/docs/concepts/agents/mcp-server) * [Agent delegation](/docs/concepts/agents/agent-delegation) Tools are built-in platform capabilities (web search, code execution, image generation, maps). They toggle on instantly per agent. Integrations are connected external services (Slack, Gmail, GitHub, Airtable) that require a connect flow first. Custom MCP attaches an external tool server. Skills teach methods. [Read more: Tools & Integrations](/docs/concepts/tools-and-integrations) Rubrics. Define weighted quality criteria for the type of output your agent produces. Evaluate outputs to get per-criterion scores. Analyze patterns across evaluations to find consistent weak spots. Then A/B test a fix (new skill, updated memory, revised prompt) against the baseline before committing it. The Library. Every artifact your agents create across all threads (images, webpages, tables, documents, maps, videos, slides, apps) is collected in one gallery at /library. You can search, filter by type, publish publicly with one click, and track version history on documents and webpages. [Read more: What is the Library?](/docs/concepts/library) Start with the [Troubleshooting FAQ](/docs/reference/troubleshooting-faq), then [Troubleshoot a stuck run](/docs/reference/runtime-limits). Open the thread tool trail before rewriting the whole prompt.