# Kore.ai — Enterprise agent platform whose agents are written in a compiled, typed DSL and governed by a deterministic validator. > Source: The Agents Index — https://theagentsindex.com/kore-ai (structured, researched, re-verified) Kore.ai is an enterprise agentic AI platform whose {Artemis} release compiles agent definitions written in its own Agent Blueprint Language and runs them with orchestration, guardrails and tracing. Its Arch AI authors and optimises those agents for customer service, employee and process work. **Best for:** Large regulated enterprises putting governed AI agents into service and operations | Fact | Value | | --- | --- | | Website | https://kore.ai | | Category | Conversational agent builders, Agent platforms | | Open source | No | | Price | Price on request | | Price source | https://koreai.mintlify.site/agent-platform/administration/workspace-account.md | | Price checked | 28 October 2026 | | MCP server | Yes | | API | Not stated | | Self-host | Yes | | Facts | 21 facts from 11 sources | | Facts checked | 28 October 2026 | Screenshot of Kore.ai: https://theagentsindex.com/img/1920/screenshots/kore-ai.webp, captured 29 October 2026 **What we checked** - Pages last read: 28 October 2026 - Facts checked: 21 facts (From 11 sources) - AI answers: Named in 6 of 151 (Our October check) ## What we checked on Kore.ai ### How much it does unattended **Multi-agent** · Yes — The runtime ships four named orchestration patterns, so several specialist agents can hand off, delegate, fan out or talk across runtimes on one task. > Compose specialists with HANDOFF, DELEGATE, FAN_OUT, and A2A — typed payloads, governed handoffs, unified traces. > — https://docs.kore.ai/home · Kore.ai Agent Platform card grid, 'Multi-Agent Orchestration' card, checked 28 October 2026 **Agent permissions** · Yes — Policies and constraints are enforced by the engine rather than by the model, and guardrails can block a tool call, a tool result or a handoff before it happens. > Policies are enforced outside the LLM, so agents can reason while staying within approved business, security, and compliance boundaries. > — https://kore.ai/ai-agent-platform · The ABL Advantage section, 'Scale autonomy without losing control', checked 28 October 2026 ### Which models it runs on **Open models** · Yes — Open-weight families are in the supported-model catalogue through Groq, Fireworks, Together and Microsoft Foundry, including Llama, Mixtral, Qwen and DeepSeek distills. > OpenAI, Anthropic, NVIDIA, Cohere, LLaMA 2, and additional providers. Open-source and custom fine-tuned models are supported through the same interface. > — https://koreai.mintlify.site/agent-platform/index.md · Enterprise ecosystem table, AI Models row, checked 28 October 2026 **Model choice** · Yes — You pick the models: agents reference Fast, Balanced, Powerful or Voice tiers and admins bind each tier to a model from any registered provider. > The Agent Platform is provider-neutral. Agents can use models from multiple LLM providers, and you can switch between them without changing agent definitions. > — https://koreai.mintlify.site/agent-platform/administration/ai-configuration.md · LLM providers section, opening paragraph, checked 28 October 2026 ### Whose machine it runs on **Self-hosted** · Yes — Besides the SaaS default, the vendor documents on-premises and private VPC deployment, offered to enterprise customers with residency or compliance needs. > Self-hosted (Enterprise) | For organizations requiring on-premises deployment. Same platform capabilities, available for enterprise customers with data-residency or compliance requirements. > — https://koreai.mintlify.site/agent-platform/index.md · Deployment options table, Self-hosted row, checked 28 October 2026 ### Building with it **SDK languages** · Partly — The documented SDK set is client-side only: a JavaScript/TypeScript Web SDK plus React Native, Flutter, Android and iOS mobile SDKs, with no server-side SDK listed. > The Web SDK is a JavaScript/TypeScript SDK that provides programmatic access to chat and voice interactions, including streaming responses, message history, file uploads, and voice interaction. > — https://koreai.mintlify.site/agent-platform/sdk/overview.md · Web SDK section, and the 'How to choose an SDK' table listing all nine SDKs, checked 28 October 2026 **Tracing and evals** · Yes — Every session is traced in structured detail and evaluation suites run before and after release, with the vendor claiming full rather than sampled coverage. > Captures over 200 trace events per session. Includes runtime inspection, alerting, and session-level debugging across multi-agent interactions. > — https://koreai.mintlify.site/agent-platform/index.md · Key components table, Deep Observability row, checked 28 October 2026 ### What it costs to run **How it meters** · Yes — Billing runs on a subscription tier plus workspace credits and billing units you can top up, with your own model spend metered separately per provider key. > Credits allocated to your workspace. > — https://koreai.mintlify.site/agent-platform/administration/workspace-account.md · Billing and usage section, Plan and credits table, checked 28 October 2026 **Free tier** · No — There is no self-serve way in: sign-up is gated to approved domains and the quick start tells everyone else to contact the company for access. > Agent Platform is available to Kore.ai customers and partners. Sign-up is enabled only for approved domains. > — https://koreai.mintlify.site/agent-platform/getting-started.md · Access the platform section, first paragraph, checked 28 October 2026 **MCP server** · Yes — Kore.ai ships its own stdio MCP server, so an outside assistant such as Claude Code or Cursor can build, evaluate and analyse agents on the platform. > Agent Platform exposes its features through a Model Context Protocol (MCP) server. Your AI assistant can connect to the platform and perform platform operations to let you build, evaluate, optimize, debug, and analyze agents. > — https://koreai.mintlify.site/agent-platform/mcp-server.md · Install and configure MCP server, opening paragraph, checked 28 October 2026 **Bring your own key** · Yes — You register your own provider API keys for inference, and may also supply your own encryption keys from AWS, Azure, GCP or an external KMS on the Enterprise plan. > LLM provider credentials: API keys for LLM providers (for example: Anthropic, OpenAI, Azure, Google, Bedrock). > — https://koreai.mintlify.site/agent-platform/administration/workspace-account.md · Secrets section, Types of secrets list, checked 28 October 2026 ### Buying it for a team **A company can buy it** · Yes — This is bought by organisations, not individuals: an optional organization layer carries shared billing and governance over several workspaces. > Organization | Optional. It sits above workspaces and carries shared billing and governance across several teams. A single-workspace setup doesn't need one. > — https://koreai.mintlify.site/agent-platform/administration/workspace-and-team.md · Workspace structure table, Organization row, checked 28 October 2026 **Seat model** · Partly — Access is granted per invited member with a workspace role, but no seat price, seat floor or seat ceiling is published anywhere I read. > Invitations carry the role you choose, so decide the role before you send one rather than correcting it afterward. > — https://koreai.mintlify.site/agent-platform/administration/workspace-and-team.md · Managing members section, 'Invite a member', checked 28 October 2026 **Pooled budget** · Yes — Credits are held as one workspace balance that projects draw on, with token budgets and rate limits set at workspace level rather than per user. > Which AI models and providers your team can reach, through LLM policies, token budgets, and rate limits. > — https://koreai.mintlify.site/agent-platform/administration/workspace-and-team.md · Workspace structure, 'What the workspace controls' list, checked 28 October 2026 **Admin controls** · Yes — Admins constrain agents centrally: project-level guardrail policies apply to every agent, and a workspace approval policy gates production deployments. > Project guardrails | Centralized governance and reusable safety policies across agents. | Govern > Guardrails | Enterprise-wide safety enforcement. > — https://koreai.mintlify.site/agent-platform/safety-and-guardrails.md · Guardrail configuration levels table, Project guardrails row, checked 28 October 2026 **Audit log** · Yes — Administrative action is recorded per tenant with actor, target, IP and trace, filterable by category; CSV export and 90-day retention need Professional or Enterprise. > Audit logs give you a tenant-scoped, filterable record of every significant workspace action. Use them to investigate incidents, confirm compliance, and review team activity. > — https://koreai.mintlify.site/agent-platform/administration/workspace-and-team.md · Audit logs section, opening paragraph and Export note, checked 28 October 2026 **Single sign-on** · Partly — Both SAML 2.0 and OpenID Connect are supported, with JIT provisioning and group-to-role mapping, but the whole SSO tab is gated to the Enterprise plan. > SSO lets your users authenticate through an external identity provider. Plan requirement: Enterprise plan only. > — https://koreai.mintlify.site/agent-platform/administration/workspace-and-team.md · Security and compliance > Single sign-on, checked 28 October 2026 ### What happens to your code **Opt out of training** · Yes — No opt-out is needed: the privacy notice states customer data is used only to deliver the service and never to train generalised models or improve the product. > Kore.ai does not use that Customer Data for internal training, knowledge-base updates, internal product enhancements or updates, or to train generalized AI models offered as part of the Services. > — https://kore.ai/privacy-policy/ · Section 5, Customer Data and AI model training, checked 28 October 2026 **Data residency** · Yes — Thirteen regional clouds are named, from the UK and Germany to Japan, Saudi Arabia and India, and on-premises or private VPC deployment is offered as well. > The platform runs in multiple regions. > — https://koreai.mintlify.site/agent-platform/getting-started.md · Access the platform, 'Region-specific URLs and allowlist of IPs' table, checked 28 October 2026 **Getting out** · Yes — Agent definitions are Git-native YAML artifacts you hold in version control, and the audit log exports to CSV; credit expiry is nowhere stated. > Agent definitions are immutable YAML artifacts that are Git-native, diffable, and reviewable in pull requests. > — https://koreai.mintlify.site/agent-platform/index.md · Key capabilities table, Agent Lifecycle as Code row, checked 28 October 2026 **Certifications** · Yes — The enterprise foundation is stated to carry PCI, SOC 2, GDPR and FedRAMP certifications, with KMS compliance profiles selectable per tenant. > Provides versioning, environment management, and certifications for PCI, SOC 2, GDPR, and FedRAMP. > — https://koreai.mintlify.site/agent-platform/index.md · Key components table, Enterprise Foundation row, checked 28 October 2026 ## Kore.ai price and terms **Terms** - Free plan or trial: No **What needs a higher plan** - Enterprise: Single sign-on ## For AI agents - MCP server: Yes Read on https://koreai.mintlify.site/agent-platform/administration/workspace-account.md, 28 October 2026. ## Kore.ai alternatives - [Blits.ai Agentic AI for the Enterprise](https://theagentsindex.com/blits-ai-agentic-ai-for-the-enterprise) · Price on request: Enterprise platform for governed agentic workflows across models, tools, data and systems. - [ElevenLabs Agents](https://theagentsindex.com/elevenlabs-conversational-ai) · Free plan, then $6 a month: Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM. - [Gumloop](https://theagentsindex.com/gumloop) · From $37 a month: Multiplayer AI agent builder: teams build agents over their apps while IT keeps governance and spend control. - [Dust](https://theagentsindex.com/dust) · Free plan, then €30 a seat a month (about $34): Platform for building and running company agents on connected tools, data and 20+ models. - [Dify](https://theagentsindex.com/dify) · Free plan, then $59 a month: Visual platform for agentic workflows and RAG, on Dify Cloud, your VPC or self-hosted. - [Manus](https://theagentsindex.com/manus) · Free plan, then $20 a month: General-purpose AI agent that plans and executes multi-step tasks on its own cloud computer. - [Letta](https://theagentsindex.com/letta) · Free plan, then $20 a month: Stateful agent harness, cloud and SDK for agents with persistent, git-versioned memory. - [Genspark](https://theagentsindex.com/genspark) · Free plan, then $24.99 a month: All-in-one AI workspace with an autonomous Super Agent plus agents for slides, docs, media and code. - [PitchAI Agent Engine](https://theagentsindex.com/agent-engine) · From €400 a month (about $447): Scheduled agents that run recurring office administration across accounting, CRM and mail systems. 8 of the 9 publish a price. [All 9 alternatives](https://theagentsindex.com/kore-ai/alternatives/) ## Questions about Kore.ai ### How much does Kore.ai cost? Kore.ai gives its price on request. From koreai.mintlify.site/agent-platform/administration/workspace-account.md, checked 28 October 2026. ### Does Kore.ai have an API or an MCP server? It has an MCP server. ### Is Kore.ai open source, and can you host it yourself? You can host it yourself. ### What have we checked on Kore.ai? 21 facts, under these headings: How much it does unattended, which models it runs on, whose machine it runs on, building with it, what it costs to run, buying it for a team, what happens to your code. ### How do we check Kore.ai? We hold 21 facts on Kore.ai, quoted from 11 pages. Facts and price last checked 28 October 2026. How we check every listing: https://theagentsindex.com/methodology/ ## Sources and changes Last changed 29 October 2026 **Sources** (11) - https://koreai.mintlify.site/agent-platform/administration/workspace-and-team.md (Independent source), read 28 October 2026 - https://koreai.mintlify.site/agent-platform/index.md (Independent source), read 28 October 2026 - https://koreai.mintlify.site/agent-platform/administration/workspace-account.md (Independent source), read 28 October 2026 - https://koreai.mintlify.site/agent-platform/getting-started.md (Independent source), read 28 October 2026 - https://koreai.mintlify.site/agent-platform/administration/ai-configuration.md (Independent source), read 28 October 2026 - https://koreai.mintlify.site/agent-platform/mcp-server.md (Independent source), read 28 October 2026 - https://koreai.mintlify.site/agent-platform/safety-and-guardrails.md (Independent source), read 28 October 2026 - https://koreai.mintlify.site/agent-platform/sdk/overview.md (Independent source), read 28 October 2026 - https://kore.ai/ai-agent-platform, read 28 October 2026 - https://docs.kore.ai/home, read 28 October 2026 - https://kore.ai/privacy-policy/, read 28 October 2026 ## Is this yours? AI assistants like ChatGPT and Claude opened The Agents Index pages 2,746 times in September. Claim Kore.ai: https://theagentsindex.com/claim/kore-ai Report an error if a fact is wrong: hello@theagentsindex.com, subject "Report an error: Kore.ai (kore-ai)".