# Maven AGI — Enterprise AI agent platform for customer support across chat, email, voice and web. > Source: The Agents Index — https://theagentsindex.com/maven-agi (structured, researched, re-verified) > Facts last verified: 2026-09-03 Maven AGI is an enterprise AI agent platform that resolves customer support conversations across chat, email, voice and web, acting in the helpdesk, CRM and telephony systems a company already runs. Agent Designer is the console where CX teams build, test and govern those agents. | Fact | Value | | --- | --- | | Website | https://www.mavenagi.com | | Price | from $25000/year billed annually | | Free tier | No | No standing $0 plan and no self-serve signup: app.mavenagi.com offers sign-in only, /pricing redirects to the demo form, and the only published entitlement is a 12-month contract with a $25,000 minimum. The Master Services Agreement contemplates a free trial but grants it at Maven's discretion, for a period “communicated to Customer” privately and terminable at will. ## What it does **Writes code** · No — Maven's only contact with a customer repository is read-only knowledge ingestion; its own GitHub FAQ disclaims writing to repositories, and the agent authors support answers and system actions, not source files. > Repository data is encrypted in transit and at rest, and Maven never writes to your repositories. > — https://www.mavenagi.com/integrations/github · Frequently Asked Questions, answer to “Is the GitHub integration secure?” **Done-for-you service** · Partly — Maven staffs Forward Deployed Engineers who embed with the customer to integrate and configure the first agents, after which the buyer's own CX team runs it in Agent Designer. That is assisted delivery, not a managed service. > Forward Deployed Engineers (FDEs) are embedded engineers who work alongside customer teams to carry AI capability across the final distance into production > — https://www.mavenagi.com/resources/forward-deployed-engineers · Section “The Solution: Forward Deployed Engineers”, body paragraph ## How much it does unattended **Runs autonomously** · Yes — Full end-to-end resolution without a human is the product's headline claim, hedged with “up to”; the same platform still routes anything past a configured threshold to a person. > automates customer support across chat, email, voice, and web, resolving up to 93% of incoming queries without human intervention > — https://www.mavenagi.com/product/agent-platform · Hero paragraph directly under the H1 “The AI Agent Platform Built for Enterprise CX” **Multi-agent** · Partly — Several specialised skills, each with its own knowledge and actions, are composed behind one agent the customer talks to; that is orchestration of skills rather than peer agents negotiating a shared task. > Each skill has its own knowledge, actions, and channels. The customer never sees any of that. They see one agent that knows their account and can act on it. > — https://www.mavenagi.com/use-cases/support-agent · Skills section, intro paragraph above the per-skill cards **Agent permissions** · Yes — Permissions are hard constraints fixed before the agent runs. Access, actions and the escalation threshold are set by surface, role and policy, so the model cannot widen its own scope mid-conversation. > the platform defines what the agent is allowed to do before the agent starts. Access, actions, escalation thresholds, and participant-specific permissions are established upfront, as hard constraints > — https://www.mavenagi.com/resources/deterministic-control-blog · Section “Two Ways to Govern an AI Agent”, closing paragraphs ## Which models it runs on **Claude** · Yes — The Master Services Agreement names Anthropic, alongside OpenAI, as one of exactly two LLM providers generating output today, and lists it as a contracted sub-processor rather than an optional integration. > At this time, Maven AGI uses OpenAI and Anthropic large language models (“LLMs”) to generate Outputs. > — https://www.mavenagi.com/legal/msa · Section “AI/Machine Learning”, bullet “AI Tools; Inputs and Outputs” **GPT** · Yes — OpenAI models are contractually named as a current generator of output, and the voice channel is built on OpenAI's realtime stack; this is the provider Maven has shipped on longest. > At this time, Maven AGI uses OpenAI and Anthropic large language models (“LLMs”) to generate Outputs. > — https://www.mavenagi.com/legal/msa · Section “AI/Machine Learning”, bullet “AI Tools; Inputs and Outputs” **Open models** · No — The agreement enumerates its LLM providers as OpenAI and Anthropic and promises written notice if any other is added, a closed list with no open-weight or self-hosted model in it. > If, at any time following the Effective Date, Maven AGI uses other LLM sub processors or AI Tools to process customer content, it will provide you with notice either in this Agreement > — https://www.mavenagi.com/legal/msa · Section “AI/Machine Learning”, bullet “AI Tools; Inputs and Outputs”, sentence after the provider list **Model choice** · Partly — Maven claims its own architecture is LLM-portable on the platform page, but the contract shows the vendor picks the models and may change them on notice; no buyer-facing model selector is published anywhere. > Vendor agnostic and LLM portable > — https://www.mavenagi.com/product/agent-platform · Section “Integration-First Architecture”, third capability bullet ## Where you use it **In your editor** · No — The vendor enumerates its surfaces as voice, chat, messaging, email and internal tools; no editor or IDE extension appears in that list or anywhere else on the site. > Maven brings a single AI agent to voice, chat, messaging, email, and internal tools — all powered by one reasoning engine and one set of policies. > — https://www.mavenagi.com/features/agent-channels · Hero paragraph under the H1 “One AI Agent for Every Customer and Employee Channel” **On the command line** · No — No terminal surface is claimed: the same enumeration of channels covers voice, chat, messaging, email and internal tools, and the docs that would describe a CLI are behind a login. > Maven brings a single AI agent to voice, chat, messaging, email, and internal tools — all powered by one reasoning engine and one set of policies. > — https://www.mavenagi.com/features/agent-channels · Hero paragraph under the H1 “One AI Agent for Every Customer and Employee Channel” **In your pipeline** · No — The GitHub connector reads documentation and re-indexes on push; the vendor states outright that it never writes to a repository, so acting on a pull request or in CI is ruled out. > Maven focuses on the documentation layer: README files, wiki pages, markdown docs, and code comments or docstrings. It does not index raw source code line by line > — https://www.mavenagi.com/integrations/github · Frequently Asked Questions, answer to “Does Maven index source code or just documentation?” **In a browser** · Yes — Web chat and in-app messaging are named customer surfaces, and Agent Designer is the hosted browser console where CX teams tune and validate agents before release. > Web chat, in app messaging, SMS, WhatsApp, social DMs, email > — https://www.mavenagi.com/features/agent-channels · Section “Supported Channels”, sub-block “Chat, Messaging, and Email”, capability bullet ## Whose machine it runs on **Self-hosted** · No — The vendor's own marketplace listing classes delivery as SaaS and states the software is not deployed in the buyer's AWS account; no on-premise, VPC or single-tenant option is published on any tier. > Delivery method Software as a Service (SaaS) > — https://aws.amazon.com/marketplace/pp/prodview-l2djyrnxnfffq · Details panel, “Delivery method” row (adjacent “Deployed on AWS” row reads “No”) **Open source** · No — The licence bars any attempt to reach the platform's source code; the only public repositories are generated API client libraries, and they carry no open-source licence file at all. > reverse engineer, disassemble, decompile, decode, or otherwise attempt to derive or gain access to the source code of the Application or any part thereof > — https://www.mavenagi.com/legal/msa · Section “Restrictions”, clause (c) ## What it costs to run **How it meters** · Partly — The vendor names resolution volume as what the price scales with, but publishes no per-resolution rate; the contract meters against a subscription usage allowance with overage priced privately in the order form. > Starting prices listed here - contact us for custom pricing based on your expected scope, complexity, and volume of resolutions. > — https://aws.amazon.com/marketplace/pp/prodview-l2djyrnxnfffq · Pricing, “12-month contract (1)” table, Description cell of the “Enterprise Custom Pricing - Minimum” row **Free tier** · No — The cheapest entitlement the vendor publishes is a twelve-month contract with a $25,000 floor; mavenagi.com routes /pricing to the demo form and app.mavenagi.com offers sign-in with no self-serve registration. > Starting prices listed here - contact us for custom pricing based on your expected scope, complexity, and volume of resolutions. > — https://aws.amazon.com/marketplace/pp/prodview-l2djyrnxnfffq · Pricing, “12-month contract (1)” table, single row “Enterprise Custom Pricing - Minimum”, Cost/12 months cell $25,000.00 **API access** · Yes — A platform API sits under the packaged agents, with generated client libraries for TypeScript, Python, Java, Go, Swift and .NET published publicly; the API reference itself, however, sits behind a Maven login. > Beyond these ready-to-deploy products, Maven AGI offers unparalleled flexibility through direct access to its underlying platform via robust APIs and integrations. > — https://aws.amazon.com/marketplace/pp/prodview-l2djyrnxnfffq · Overview, product description paragraph **MCP server** · No — MCP support runs one way only: Maven is the client that connects out to MCP servers a customer already hosts. No Maven-hosted MCP endpoint is published, so another agent has no MCP route in. > If a system has an MCP server, your team can configure access through Maven’s UI in just a few steps; no additional engineering required. > — https://www.mavenagi.com/resources/model-context-protocol · Body prose, paragraph before the heading “How Teams Use MCP to Move Faster” **Bring your own key** · No — Inference is Maven's to arrange: the contract names the two LLM providers it uses and reserves the right to change them on notice, with no provision for customer-supplied keys, accounts or cloud. > At this time, Maven AGI uses OpenAI and Anthropic large language models (“LLMs”) to generate Outputs. > — https://www.mavenagi.com/legal/msa · Section “AI/Machine Learning”, bullet “AI Tools; Inputs and Outputs” ## Buying it for a team **A company can buy it** · Yes — This is bought by a company, not a person: a signed order form binds the organisation and covers named Customer Users, and the listing is also purchasable through an existing AWS account. > Customer shall, and shall ensure that any of its employees, agents, or individual end users authorized to use the Application on Customer’s behalf (“Customer Users”), comply with this Agreement. > — https://www.mavenagi.com/legal/msa · Section “Provision of Application”, first bullet **Pooled budget** · Yes — Usage is metered against one account-level subscription allowance rather than per user, and the vendor must warn the organisation at ninety percent of that shared limit before overage begins. > Company will notify Customer in writing when Customer’s usage reaches 90% of the agreed subscription usage limit. > — https://www.mavenagi.com/legal/msa · Section “Payment”, bullet “Fees and Overages” **Admin controls** · Yes — Policy is an org-level setting an admin configures once and the platform enforces on every action: routing rules, workflow policy, identity controls and deterministic logic, not per-conversation discretion. > Routing rules, workflow policies, identity controls, and deterministic logic ensure every AI action follows your internal standards. Nothing operates outside governance. > — https://www.mavenagi.com/features/trust-compliance · Section “Why Security-Conscious CX Teams Choose Maven”, card “Policy-aligned workflows you can actually enforce” **Audit log** · Partly — Agent activity is logged, traceable and exportable to a SIEM, but every audit claim is scoped to AI decisions and agent behaviour; administrative actions such as role or policy changes are not covered anywhere public. > Every AI decision is logged, traceable, and exportable. SIEM integrations provide line of sight into inputs, outputs, system references, and policy checks across the full agent lifecycle. > — https://www.mavenagi.com/features/trust-compliance · Section “Why Security-Conscious CX Teams Choose Maven”, card “Full transparency and auditability” **Single sign-on** · Partly — SSO is asserted as a platform capability beside RBAC and MFA, and Maven says it federates to the identity system a customer already runs, but no protocol, no SAML or OIDC, and no IdP is named publicly. > RBAC, SSO, MFA, secure SDLC practices > — https://www.mavenagi.com/features/trust-compliance · Section “Security, Trust, Compliance, and AI Ethics – Built In, Not Bolted On”, first accordion panel, feature bullet _Not established: Seat model_ ## What happens to your code **Opt out of training** · Yes — No opt-out is needed because the default is contractual refusal: Maven undertakes not to train on inputs or outputs and binds its LLM providers to the same prohibition, backed by a zero-retention claim. > MAVEN AGI DOES NOT USE YOUR INPUTS AND OUTPUTS TO TRAIN ITS AI MODELS, AND THE THIRD-PARTY AI TOOLS INCLUDING LLM PROVIDERS ARE PROHIBITED FROM USING YOUR INPUTS AND OUTPUTS TO TRAIN THEIR MODELS. > — https://www.mavenagi.com/legal/msa · Section “AI/Machine Learning”, bullet “Customer Ownership and License; No Model Training” **Getting out** · Partly — You own your inputs and outputs and agent decisions are exportable, but no export right or mechanism attaches to termination: Maven may delete all customer data sixty days after it, and fees are non-refundable with no rollover clause. > Within sixty (60) days of termination or expiration of this Agreement or an uncured failure to pay Subscription Fees when due, Company shall have the right to delete all Customer Data. > — https://www.mavenagi.com/legal/msa · Section “Termination”, bullet “Deletion” **Certifications** · Yes — An unusually broad stack, stated by the vendor and independently audited: ISO 27001, PCI DSS Level 1 and SOC 2 Type II here, plus ISO 42001, 27701, 27017 and 27018 and a HIPAA BAA on the trust centre. > Certified for ISO 27001:2022, PCI DSS 4.0 Level 1, and SOC 2 Type II. > — https://www.mavenagi.com/features/trust-compliance · Section “Why Security-Conscious CX Teams Choose Maven”, card “Enterprise-grade compliance from day one” _Not established: Data residency_ ## Provenance 1 of 10 sources behind the facts above are independent of the vendor. ## Coverage elsewhere None recorded. Every fact above comes from the vendor and is not independently corroborated yet. ## What changed - 2026-09-03 — Capabilities · Commercial terms · Free tier · Price ## Correcting this record Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Maven AGI, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth. Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.