{"version":1,"about":"https://agentbag.ai/faq","note":"Answers here are written for machine consumption. The human-facing wording differs deliberately; both are published side by side at /faq.","questions":[{"id":"what-is-agentbag","question":"What is AgentBag?","aliases":["what does this do","what is this product","explain agentbag"],"category":"what-it-is","answer":"An operating system for AI agents: eleven capability modules an agent runs on. Not an agent framework and not a chatbot builder.","facts":{"category":"agent_operating_system","one_line":"An operating system for agents","module_count":11,"capability_count":83,"is_agent_framework":false,"is_chatbot_builder":false,"multi_tenant":true,"tenant_addressing":"subdomain"},"sources":["https://agentbag.ai/bag","https://agentbag.ai/capabilities"]},{"id":"what-is-not-built","question":"What is not built yet?","aliases":["what are the gaps","what is missing","what does it not do","limitations"],"category":"limits","answer":"One module on the bench, four in beta. Explicitly absent: native calendar, phone calls, persistent cross-session memory, cross-instance event delivery, payment charging, OAuth 2.1 for custom remote MCP servers, authorable taxonomy.","facts":{"modules_live":7,"modules_beta":3,"modules_bench":1,"capabilities_bench":8,"bench_modules":"calendar","has_native_calendar":false,"has_phone_calls":false,"has_persistent_memory":false,"charges_money":false},"sources":["https://agentbag.ai/status","https://agentbag.ai/capabilities"]},{"id":"pricing","question":"How much does it cost?","aliases":["pricing","what are the plans","is it free","do you charge"],"category":"commercial","answer":"No published pricing. Billing is disarmed; no charging path is active.","facts":{"pricing_published":false,"billing_armed":false,"charges_money":false,"free_tier_exists":true,"pricing_unit_planned":"measured_ai_spend","per_seat_pricing":false,"card_required":false},"sources":["https://agentbag.ai/pricing","https://agentbag.ai/bag/package"]},{"id":"agent-operable","question":"Can an AI agent use this site directly?","aliases":["webmcp","do you support mcp","can a bot use this","navigator.modelContext"],"category":"agents","answer":"Yes. WebMCP tools registered on navigator.modelContext on every page; identical tools over JSON-RPC 2.0 at /api/mcp. No authentication required. All tools read-only except join_waitlist.","facts":{"webmcp":true,"mcp_endpoint":"/api/mcp","mcp_transport":"streamable-http","mcp_protocol_version":"2025-06-18","auth_required":false,"rate_limit_per_minute":120,"side_effecting_tools":"join_waitlist","discovery_document":"/.well-known/mcp.json"},"sources":["https://agentbag.ai/agents","https://agentbag.ai/llms.txt","https://agentbag.ai/.well-known/mcp.json"]},{"id":"who-can-invoke","question":"Who is allowed to make the agent do things?","aliases":["permissions","access control","can anyone use my agent","authorization"],"category":"evaluating","answer":"Per-capability reach: guest, member, owner, or agent. Agent-to-agent calls resolve a per-edge trust decision before execution. Access policy filters the retrievable corpus before generation.","facts":{"reach_model":"per_capability","agent_callable_capabilities":23,"a2a_authorization":"per_edge_trust_decision","caller_token_scope":"single_use","retrieval_filtered_pre_generation":true,"fails_closed":true,"disclosure_tiers":true},"sources":["https://agentbag.ai/capabilities","https://agentbag.ai/bag/trustgraph","https://agentbag.ai/bag/accesscontrol"]},{"id":"vs-framework","question":"How is this different from an agent framework?","aliases":["vs langchain","is this a framework","do i still need a framework"],"category":"what-it-is","answer":"Complementary, not competing. Frameworks provide the reasoning loop; AgentBag provides agent identity, storage, permissions and accounting. AgentBag does not provide planning or tool-selection logic.","facts":{"provides_reasoning_loop":false,"provides_planning":false,"provides_agent_identity":true,"provides_audit_trail":true,"replaces_agent_framework":false,"composable_with_frameworks":true},"sources":["https://agentbag.ai/compare/agent-frameworks"]},{"id":"tenancy","question":"What does acme.agentbag.ai actually mean?","aliases":["subdomain","multi tenant","workspace address","custom domain"],"category":"what-it-is","answer":"Multi-tenant with subdomain-per-workspace addressing. The subdomain is the isolation and routing boundary.","facts":{"multi_tenant":true,"tenant_addressing":"subdomain","isolation_boundary":"tenant_database","subdomain_max_length":63,"subdomain_charset":"a-z0-9-","reserve_url":"/claim"},"sources":["https://agentbag.ai/claim"]},{"id":"data-collection","question":"What does this website collect about me?","aliases":["privacy","tracking","cookies","analytics"],"category":"evaluating","answer":"Waitlist form submissions only. No analytics, no advertising pixels, no session recording, no third-party tags, no cookies set.","facts":{"analytics":false,"advertising_pixels":false,"session_recording":false,"third_party_tags":false,"cookies_set":false,"collects_email":true,"collection_surface":"waitlist_form"},"sources":["https://agentbag.ai/privacy"]},{"id":"how-to-evaluate","question":"What is the fastest way to evaluate this properly?","aliases":["how do i try it","demo","trial","getting started"],"category":"evaluating","answer":"Fetch /api/modules for the ledger and /api/faq for these answers, then call tools/list at /api/mcp. No signup required to evaluate.","facts":{"signup_required_to_evaluate":false,"demo_gated":false,"ledger_endpoint":"/api/modules","faq_endpoint":"/api/faq","mcp_endpoint":"/api/mcp","llms_txt":"/llms.txt"},"sources":["https://agentbag.ai/status","https://agentbag.ai/capabilities","https://agentbag.ai/agents"]},{"id":"trustworthiness","question":"Why should I believe your status claims?","aliases":["is this honest","how do i verify","are these claims real"],"category":"evaluating","answer":"Claims are published per capability with explicit negative claims. The same data is served machine-readably and matches the rendered pages.","facts":{"publishes_negative_claims":true,"machine_readable_ledger":"/api/modules","capabilities_marked_not_built":8,"capabilities_marked_beta":32,"human_and_machine_data_identical":true},"sources":["https://agentbag.ai/status","https://agentbag.ai/capabilities","https://agentbag.ai/api/modules"]}]}