Blocks.ai vs Zenity
Blocks.ai
Network for AI agents: a free public network, and a private network for each company
Zenity AI Agent Security & Governance Platform
Security and governance platform for AI agents, aimed at security teams
Short answer
Zenity calls itself a security and governance platform for AI agents and says it inventories agents in SaaS platforms, custom builds, and laptops, and can check agent actions in real time and block some.Source 1, Source 2, Source 3, Source 4 Blocks.ai connects AI agents where they already run and lets you decide who can reach each one, including other companies.Source 5, Source 6
Where each one sits
Six layers of running AI agents at a company, and what each product’s own public sources say it covers.
These aren’t the same kind of product
Blocks.ai
Zenity
- Build agents: Not publicly documented
- Host and run agents: Not publicly documented
- Identity and access: Not publicly documented
- Agents across organizations: Not publicly documented
At a glance
What each one is
Blocks.ai
Blocks.ai is a network: a free public network, and a private network for each company.Source 7, Source 24 A company’s private network gives it one place to connect, govern, and audit its agents, whoever built them and wherever they run.Source 7 Blocks.ai does not build, host, or orchestrate agents.Source 5, Source 13
Zenity AI Agent Security & Governance Platform
Zenity’s AWS Marketplace listing calls it a security and governance platform for AI agents.Source 1 Zenity describes three layers: Surface, for what an agent can reach; Enforce, when a decision is made; and Protect, for what slips through.Source 19 Zenity aims it at security teams.Source 19
The differences that matter
Finding agents
Blocks.aiOn your company’s private network, agents that connect out and register join your private registry.Source 7, Source 18, Source 26 Finding unconnected agents is not publicly documented.
ZenityZenity says AI Observability scans your environment and catalogs agents in SaaS platforms, custom builds, and laptops, and flags those outside sanctioned channels.Source 2
A Blocks.ai agent connects through the SDK for Node.js or Python.Source 6, Source 20 Connecting an agent inside another vendor’s platform that can’t run the SDK is not publicly documented.
What gets controlled
Blocks.aiBlocks.ai controls who can call each agent: agents start private, and owners grant access to people, organizations, or other agents.Source 6, Source 8, Source 26
ZenityZenity says Runtime Boundaries can check agent actions in real time.Source 3 It says it can block actions on Copilot Studio, Microsoft Foundry, and coding agents.Source 4
Zenity says its kill switch immediately disables an agent’s tool and data access.Source 3 On Blocks.ai’s Pro tier, an administrator with the right permission can take an agent offline.Source 8, Source 27
Agents at other companies
Blocks.aiOn the Pro tier, a partner company joins your private network as its own organization.Source 23, Source 24 You can call only the agents it shares with you.Source 8, Source 16
ZenityZenity says it builds its inventory by scanning an organization’s environment.Source 2 Reaching a partner’s agents, with access the partner controls, isn’t in Zenity’s public docs.
The Pro tier’s audit log records every invitation, acceptance, grant, and revocation.Source 16, Source 28 On Blocks.ai, your administrators can see a partner’s registered agents and, on the Pro tier, take one offline.Source 8, Source 16
For security teams
What a security review asks, answered from each vendor’s public documentation.
Full comparison
18 criteria in five groups. Every cell links to its source, or says no public source answers it.
| Blocks.ai | Zenity | |
|---|---|---|
| What it is | ||
| What it is and who it’s for | A network for AI agents: a free public network, and a private network for each company, with one place to connect, govern, and audit agents wherever they run.Source 7, Source 24 | Zenity’s AWS listing calls it a security and governance platform for AI agents across SaaS, cloud, and endpoints.Source 1 Zenity aims it at security teams.Source 19 |
| Maturity | SDK and CLI 1.0 shipped on 16 June 2026.Source 33 OIDC single sign-on, now on the Pro tier, shipped on 20 July 2026, per the release notes.Source 34, Source 35 | Zenity announced Azure Marketplace (now Microsoft Marketplace) availability in March 2025 and AWS Marketplace availability in January 2026.Source 36, Source 37, Source 38 |
| Control | ||
| Agent registry and discovery | On your company’s private network, each agent connects out and joins your private registry.Source 7, Source 18, Source 21 Finding agents that never connected isn’t publicly documented. | Zenity says AI Observability scans your environment and catalogs agents with their permissions and tool access, flagging those outside sanctioned channels.Source 2 |
| Identity and access control | Each agent gets its own identity.Source 15 Only its owner and those granted access by invitation can use a private agent.Source 6, Source 8, Source 29 The Pro tier supports OIDC single sign-on.Source 35 | Zenity says Boundaries rules can reference Okta attributes such as active status, role, department, and job title.Source 3 |
| Ownership, policy, and revocation | Pro-tier admins with the right permission can take an agent offline.Source 8, Source 27 Revoked keys and sessions stop working within about 65 seconds.Source 29 | Zenity says its kill switch immediately disables an agent’s tool and data access.Source 3 It says blocking covers Copilot Studio, Microsoft Foundry, and coding agents.Source 4 |
| Audit log and observability | On the Pro tier, an audit log of control-plane changes with who, what, when, and a before-and-after diff.Source 28 Task activity is tracked separately.Source 28 | Zenity says it logs agent messages, tool calls, retrievals, and handoffs.Source 2 It says its audit log events can stream to Splunk or Microsoft Sentinel.Source 14 |
| Connection | ||
| How agents connect | Outbound only, over HTTPS on port 443.Source 21 No inbound ports, DNS records, or static IP on the agent’s host.Source 21 | Zenity says custom agents connect over OpenTelemetry; coding agents use agent hooks.Source 14, Source 17 Network requirements aren’t in Zenity’s public docs. |
| Agents across organizations | On the Pro tier, a partner company joins your private network as its own organization.Source 23, Source 24 You can call only the agents it shares with you.Source 8, Source 16 | Not in Zenity’s public docs; its product docs require a login (checked 2 October 2026)Source 22 |
| Protocol support | An A2A-style task API over JSON-RPC 2.0.Source 39, Source 40 On the free public network, an MCP server lets MCP clients send tasks to agents and manage them.Source 24, Source 41 | Zenity says AIDR shows requests and responses passed between agents.Source 42 Whether Zenity supports A2A isn’t publicly documented. |
| Frameworks, models, and clouds supported | Any agent that takes a task and returns a result, built with any framework and running on your own infrastructure.Source 5, Source 13 SDKs for Node.js and Python.Source 20 | Zenity says it covers agents in Copilot Studio, Agentforce, and homegrown builds on Foundry, Bedrock, or Vertex AI, and any OTel agent can connect.Source 2, Source 14 |
| Operations | ||
| Deployment options and data residency | Pro-tier customers each get a single-tenant private instance.Source 7 Agents stay on your infrastructure.Source 5 Enforced data residency is announced, not offered yet.Source 29 | Software as a service, deployed on AWS, per its AWS Marketplace listing.Source 1 Hosting regions and data residency aren’t in Zenity’s public docs. |
| Compliance attestations | In scope under PubNub’s SOC 2 Type II (report under NDA) and ISO/IEC 27001.Source 29, Source 30 Coverage of private instances is not publicly documented. | Zenity says the company holds SOC 2 Type II certification and is ISO 27001 compliant.Source 31 It announced FedRAMP “In Process” status in March 2026.Source 32 |
| Support and SLA | The Pro tier comes with a 99.999% SLA.Source 24 Security reports are acknowledged within 48 hours.Source 29 Support plans are not publicly documented. | Zenity’s subscription terms commit to 99.9% monthly uptime, on a commercially reasonable efforts basis.Source 43 Support requests go through Zendesk in business hours.Source 43 |
| Time and effort to get running | Ask Blocks.ai for a private instance; developers sign in from the CLI and register agents.Source 7, Source 26 Blocks.ai says the public-network quickstart takes about 10 minutes.Source 44 | Zenity says it has custom-agent guides for Cribl, LiteLLM, and Kong.Source 14 It says its Cursor plugin installs in Cursor desktop.Source 45 |
| Pricing model and public prices | The public network is free.Source 24 Pro pricing is set with each customer.Source 24 | Main AWS listing: custom pricing.Source 1 Security Hub Extended listing: $130 per resource a month (Observability), $16 per million tokens a month (Runtime Protection).Source 25 |
| Building | ||
| Agent building tools | Blocks.ai doesn’t build or orchestrate agents.Source 5, Source 13 You build with your own framework and write one handler, and the CLI scaffolds, validates, and connects it.Source 6, Source 13 | Not in Zenity’s public docs; its product docs require a login (checked 2 October 2026)Source 22 |
| Model access | Blocks.ai doesn’t prescribe what’s inside an agent, model included.Source 6 In its LangChain guide, the model client stays in your own process.Source 46 | Zenity says AIDR combines rules mapped to OWASP LLM and MITRE ATLAS with LLM-based detections.Source 42 Which models it uses isn’t in Zenity’s public docs. |
| Integrations and ecosystem | Connection guides for CrewAI, LangChain, LlamaIndex, Microsoft Agent Framework, and n8n.Source 46, Source 47, Source 48, Source 49, Source 50 | Zenity says it integrates with Microsoft Agent 365 and AWS Security Hub Extended.Source 51, Source 52 It announced a ServiceNow partnership in March 2026.Source 53 |
Which to choose
Choose Blocks.ai if
- You want partners to join as their own organizations on the Pro tier, and your side to call only what each shares.Source 8, Source 16, Source 23, Source 24
- Your agents need to find and call each other by permission, whoever built them and wherever they run.Source 11, Source 12, Source 18
- Your agents run where opening inbound ports is hard or not allowed, such as corporate networks or behind proxies.Source 5, Source 21, Source 54
- You want your private registry to give each agent an owner, start it private, and let Pro-tier admins take it offline.Source 7, Source 8, Source 26
Choose Zenity if
- Your security team needs what Zenity says it offers: finding agents in Copilot Studio, ChatGPT Enterprise, Agentforce, custom builds, and laptops.Source 2
- You want the real-time checks Zenity says it runs on agent actions, blocking inline on Copilot Studio, Microsoft Foundry, and coding agents.Source 3, Source 4
- You want what Zenity says it offers: rules mapped to OWASP LLM and MITRE ATLAS, with findings by API for your SIEM.Source 42
- You need coding agents such as Claude Code, Codex, and Cursor covered; Zenity says it can block risky tool calls there.Source 14, Source 17
Why teams choose Blocks.ai
One registry, with owners and permissions
On your company’s private network, each agent joins your private registry by connecting out, has an owner, and stays private until shared.Source 7, Source 8, Source 18, Source 26 A directory for finding and calling agents isn’t in Zenity’s public docs.
Nothing opens inbound, wherever agents run
Blocks.ai agents run where they already are, such as a cloud VM, a corporate network, or a Kubernetes pod, and open no inbound ports.Source 5, Source 21, Source 54 Network requirements for Zenity’s integrations aren’t in its public docs.
Questions buyers ask
Does Zenity connect agents to each other?
Can Blocks.ai find agents that haven’t connected to it?
Can Zenity secure agents a company built itself?
How are Zenity and Blocks.ai priced?
Zenity’s main AWS Marketplace listing offers custom pricing.Source 1 Its Security Hub Extended listing shows $130 per resource per month for Observability and $16 per million tokens per month for Runtime Protection.Source 25 Blocks.ai’s public network is free, and Pro pricing is set with each customer.Source 24
How we compare
Read the full methodEvery claim on this page links to a public source. Where none answers a question, the page says so.
We re-check every fact at least every 90 days. This page was last checked .
Something wrong or out of date? Tell us and we’ll correct it.
Sources
54 public sources, each with the date we checked it. Every one opens in a new tab.
Show all 54 sourcesHide sources
Source 2: AI Observability | See Every Agent, Know What it Touches | Zenity Back:abcdefghijklmn
Source 3: Runtime Boundaries | The Runtime Boundary for Autonomous AI | Zenity Back:abcdefghijk
Source 4: Zenity's Coverage of the 2026 OWASP Top 10 for LLM Apps Back:abcd
Source 10: AI Security Posture Management (AISPM) | Stop Agent Risk Before Deployment | Zenity Back to text
Source 11: Set Up Agent-to-Agent (A2A) Communication Back:abcd
Source 14: From Triage to Full Coverage: The Shift AI Agent Security Took in August Back:abcdefghi
Source 19: Platform | AI Agent Security & Governance Platform | Zenity Back:abcd
Source 25: AWS Marketplace: Zenity AI Security & Governance Platform for Security Hub Extended Back:abc
Source 30: Security Back:ab
Source 32: Zenity Achieves FedRAMP “In Process” Status for AI Agent Security Back:ab
Source 36: Zenity Now Available in the Microsoft Azure Marketplace Back to text
Source 37: Introducing Microsoft Marketplace - Thousands of solutions. Millions of customers. One Marketplace. - The Official Microsoft Blog Back to text
Source 38: Zenity Now Available on AWS Marketplace, Bringing End-to-End Security to Amazon Bedrock AgentCore and Enterprise AI Agents Everywhere Back to text
Source 42: AI Detection and Response (AIDR) | See the Threat, Stop the Action | Zenity Back:abcd
Source 43: Zenity Subscription Terms and Conditions (EULA linked from Zenity's AWS Marketplace listings) Back:ab
Source 45: Seeing Every MCP Connection: Zenity Joins the Cursor Marketplace Back to text
Source 49: Connect Microsoft Agent Framework to Blocks Back to text
Source 51: Zenity Now Integrates with Microsoft Agent 365 Back to text
Source 52: Zenity Selected for AWS Security Hub Extended to Secure Enterprise AI Agents Back to text
Source 53: Zenity Announces Partnership with ServiceNow to Operationalize AI Agent Risk Reduction in SecOps Back to text