Back to vendors
Z

Zaro

Also known as: Zaro, zaro.ai, Zaro AI

Visit site
Entry priceNo public prices. Entry is a fixed fee pilot, then an annual enterprise contract.Full pricing detail

Shared context layer for enterprise AI: company knowledge held as versioned, permissioned files that people and agents read from and write back to, with approval gates and a full action trail.

Zaro is a context layer for enterprise AI. It holds one current, attributable account of how a business runs, kept as plain readable files such as Markdown and YAML, not rows behind an API. Nothing is overwritten: every file keeps its version history, can be read as it stood on any past date and restored in one step, and every answer names the file and version it came from. Agents read from the layer and write back what they learn, so the output of one run becomes the input of the next.

Context arrives through more than 120 native connectors, among them SharePoint, Microsoft 365, Teams, Salesforce, Confluence, Jira, Slack, Snowflake, Databricks, Google Drive and HubSpot. There is also an API for systems a customer built itself, an open agent protocol that lets outside agents read what they are cleared for and write back, and a governed browser session for systems with no API at all.

Access is set per folder path as read, write or deny, and it applies equally to people and automated work. Every agent runs under a scoped service account that can never exceed the permissions of the person who created it. Agents must ask for approval before deleting data, calling paid third party services or running irreversible operations, and the request goes out by email and Slack and times out as denied after 30 minutes. Reads, writes and tool calls are logged with the user, workflow, source context and outcome, and code runs only in isolated sandboxes.

Zaro states ISO 27001 certification and SOC 2 Type II in progress, with an observation period that ran June to September 2026. It offers enterprise SSO over SAML and OIDC and runs production on AWS in London with a Frankfurt recovery site. Model work is routed across several providers, including Anthropic, OpenAI, Google and a default open weights model served by Fireworks AI.

Vendor details

Canonical URL

https://zaro.ai/

Category

Agent infrastructure

Subcategory

Shared context and memory layer for enterprise agents

Funding status

5.1M USD pre seed (June 2026) led by Cherry Ventures; angels include Thomas Wolf and Thomas Dohmke

Company status

independent

Use cases & customers

Primary use cases

Shared, versioned company context that many agents read from and write back toGoverning what agents can read, call and change, per folder path and per tool connectionExplaining why performance moved across stores, plants or reps, with the source behind each conclusionTurning top performer behavior into a written playbook from calls, emails and dealsAuditable record of agent reads, writes and tool actions

Target customers

enterpriseretailmanufacturinggo to market teams

Deployment options

SaaS (AWS London, Frankfurt recovery site)Dedicated deployment on request (healthcare)

Integrations

More than 120 native connectors including SharePoint, Microsoft 365, Teams, Outlook, Salesforce, Confluence, Jira, Slack, Snowflake, Databricks, Google Drive and HubSpot, read with permissions intact. Also an API for custom systems, an open agent protocol for outside agents, and a governed browser session for systems with no API. Third party OAuth runs through Composio.

In practice

A retail chain cannot say why one northern store outperforms its region. Zaro joins sales, footfall, pricing, client feedback and market signals across stores and explains the drivers, citing the file behind each conclusion.

A sales leader wants to know what the top rep does differently. Zaro reads calls, emails and deals, surfaces the pattern and writes it into a versioned playbook the team coaches from.

An operations team wants outside agents working from company context without seeing finance or HR files. Zaro grants read on the playbook paths, denies the rest, and logs every read and write.

Agentic Index coverage score

10.0 / 14 capabilities · 71%

Integrations & Tool Calling Full

Agents take authenticated action in outside systems. More than 120 native connectors read with permissions intact, Composio handles third party OAuth and API orchestration, and a governance layer scopes tool actions (write, send, move, generate) per connection. One guardrail example denies sending email from Gmail.

Sourcezaro.ai/securityread 2026-09-29

Workflow Orchestration Partial

Agents run work against the shared context, and each run writes files the next run reads. There is no workflow model, with no sequencing, branching, retries or multi agent routing, and Zaro positions itself against workflow wiring in its own n8n comparison.

Sourcezaro.ai/platformread 2026-09-29

Knowledge Grounding & RAG Full

Customer context is held as versioned files in PostgreSQL and S3, with OpenSearch search and vector indices mirrored from them, fed by 120 plus connectors, and every answer names the file and version it came from.

Sourcezaro.ai/platformread 2026-09-29

Human Oversight & Guardrails Full

A built in ask_permission tool requires user approval before agents delete data, call paid third party APIs or run irreversible operations. Requests route by email and Slack and time out as denied after 30 minutes. Workspace managers tune the defaults per agent, and a policy layer returns allow, escalate or block on tool calls.

Sourcezaro.ai/trustread 2026-09-29

Security, Identity & Governance Full

Enterprise SSO runs over OIDC and SAML with an SSO only option, per path read, write or deny rules are enforced equally for users, agents and MCP clients, and agents run on scoped service accounts that cannot exceed their creator. Zaro states ISO 27001 certification, and SOC 2 Type II is in progress through Drata (observation period 1 June to 1 September 2026, report pending). The registrar and certificate number are not published.

Sourcezaro.ai/trustread 2026-09-29

Observability & Auditability Full

Agent reads, writes and external tool calls trace to the user, workflow, source context and outcome. Each tool audit record carries provider, status, safety level, latency, timestamp and full command input. History can be exported, and file versions name the agent that last edited them. Application logs are kept for 30 days and events for 90 days.

Sourcezaro.ai/securityread 2026-09-29

Memory & State Persistence Full

What agents learn is written back into the shared context, and a reserved workspace memory path is protected from generic write tools. Scope is set per folder path, and file versions are kept per workspace policy, readable as of any past date and restorable. Lifetime is set by workspace policy, not a fixed duration.

Sourcezaro.ai/platformread 2026-09-29

Deployment & Data Residency Partial

Production runs on AWS London with a Frankfurt recovery site, which is Zaro's own infrastructure, not a region customers select. For healthcare, dedicated BAA ready deployments are offered on request. There is no VPC, on premises, self hosted or region selection option, and model inference leaves the region for US and globally routed LLM sub processors.

Sourcezaro.ai/trustread 2026-09-29

Prebuilt Agents, Templates & Packs Partial

Assets are assembled per customer, not adopted from a catalog. The pilot scopes one use case on the customer data with Zaro, and the homepage shows three worked use cases (retail, go to market, distributed operations). Launch coverage in June 2026 describes an app store and marketplace of preconfigured workflows, but no such catalog is published.

Sourcezaro.ai/getting-startedread 2026-09-29

Triggers & Channel Coverage Not documented

There are no schedules, webhooks, event triggers or inbound queues. The platform graphic of three runs one week apart illustrates compounding, not a schedule, and approval notices by email and Slack go outbound. There is no public documentation site.

Sourcezaro.ai/platformread 2026-09-29

Model Flexibility & Routing Partial

Routing across providers happens inside Zaro. Its sub processor list names Anthropic, OpenAI, Google Gemini (optional), a default GLM family model served by Fireworks AI through the Requesty gateway, and OpenRouter for fallback routing. There is no customer or admin control of model choice and no bring your own key, beyond Gemini being listed as optional.

Sourcezaro.ai/trustread 2026-09-29

APIs, SDKs & MCP Extensibility Partial

Zaro states an API to read and write the context and an open agent protocol through which outside agents read what they are cleared for and write back. API keys are issued once and stored as hashes. No API or SDK reference, endpoint, auth documentation or tool list is published.

Sourcezaro.ai/platformread 2026-09-29

Testing, Debugging & Optimization Partial

The pilot runs one use case beside the existing process against success criteria agreed up front and measures before and after, but it is a fixed fee engagement, not a surface the customer invokes. In the product, version diffs, restore, and monitoring of blocked actions and errors support debugging. There is no evaluation harness, scored tests or quality gates.

Sourcezaro.ai/getting-startedread 2026-09-29

Browser & Computer Use Full

For systems with no API, agents work through a governed browser session that Zaro hosts, and the sub processor list names Browserbase for isolated cloud browser sessions used for agent driven web automation. The session is scoped to reading what it is cleared for, and Zaro does not describe actions taken through the browser separately.

Sourcezaro.ai/platformread 2026-09-29

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Pricing

No public prices. Entry is a fixed fee pilot, then an annual enterprise contract.

A fixed fee pilot, then an annual enterprise contract scoped to the customer estate and not priced per seat.

What is public

The purchase path and its shape are public, a fixed fee pilot tied to deliverables and then an annual enterprise contract that is not priced per seat. No figures are.

Billing mechanics

The pilot fee is fixed and tied to deliverables, with success criteria agreed before building and a convert, expand or stop decision at day 30. The enterprise contract is annual and scoped to the customer estate.

Cost watchouts

Model inference runs through several third party providers. Whether heavy agent usage changes the annual price is not stated.

Variable cost rationale

Nothing is metered on a published basis. The pilot fee is fixed, and the enterprise contract is annual and not per seat, so cost is set once signed. The contract is scoped to the customer estate with no published unit, and no usage, connector or overage terms are published, so what makes the annual price grow is not known.

Additional watchouts

No unit is published, so cost cannot be modeled before a call.

Sales call required

Yes, required for paid access

Free / trial

None published. Entry is a paid pilot with a decision at day 30.

Lowest paid plan

Not published. Entry is a fixed fee pilot.

Commercial notes

If the customer stops at day 30 it keeps the pilot use cases, the documentation and the before and after measurement.

Key ambiguities

Whether the annual enterprise price scales with connectors, data volume, users or model usage is not stated.

Cancellation / refund

The pilot ends in a convert, expand or stop decision at day 30. A customer that stops keeps the pilot use cases, the documentation and the before and after measurement.

Missing data

Pilot fee, enterprise contract range, what drives the annual price, any usage limits or overage terms.

Agentic Index verified 2026-09-29

Alternatives to Zaro

The closest documented capability profiles to Zaro among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Momentic12.5 / 14Adds documented Triggers & Channel Coverage
  • OpenAI Agents platform12.5 / 14Adds documented Triggers & Channel Coverage
  • Redis9.5 / 14Fuller documented coverage on Deployment & Data Residency and APIs, SDKs & MCP Extensibility
  • Cloudflare13.0 / 14Adds documented Triggers & Channel Coverage
  • Kernel8.5 / 14Fuller documented coverage on Deployment & Data Residency and APIs, SDKs & MCP Extensibility
  • nexos.ai11.5 / 14Adds documented Triggers & Channel Coverage

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.