Agentic Index
HOL Guard vs Knostic (2026)
HOL Guard last verified ·Knostic last verified
HOL Guard is an open source control that runs on each developer's machine and pauses risky agent actions for a person to approve, while Knostic's Kirin is a managed service that enforces a security team's policy across coding assistants and their MCP connections. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Both check what a coding agent is about to do before it happens, both stop destructive commands, secret reads and unapproved MCP servers, and both are free for a small team.
HOL Guard connects to fifteen coding agents, Claude Code, Codex, Cursor, GitHub Copilot CLI, Cline, Gemini CLI, OpenCode and Kimi Code among them, through native hooks, MCP proxies and launch wrappers. Each action is allowed, paused for approval or blocked, and an approval carries a scope and a short expiry. Package installs are checked against supply chain advisories, and every decision writes a receipt. Policies are text files with built in tests, and they can run in observe mode before they enforce. The core is open source under Apache 2.0, works offline and sends nothing off the machine unless Guard Cloud is connected.
Kirin works inside Cursor, Claude Code, GitHub Copilot and Windsurf. It blocks risky prompts, destructive commands and unsafe MCP servers, redacts secrets and personal data in the IDE, and holds MCP connections to an allowed list with alerts when a connection drifts. Its policies block or allow, with no step that asks a person to approve. Knostic also maps what Microsoft 365 Copilot exposes and rates MCP servers and agent skills in its AgentMesh catalog. The service runs on AWS, and Knostic reports SOC 2 Type 2.
HOL Guard is free on one machine, with Guard Cloud plans at $4.99 a month for Solo, $15 for Pro and $30 a seat for Team, which adds shared policy, roles and evidence exports. Kirin is free for up to five users, Team is $15 a user a month with role based access and audit logs, and Enterprise is quoted with single sign on and SIEM and Slack integrations.
Choose HOL Guard for an open source guard on every machine that covers many agents and lets developers approve the ambiguous calls. Choose Kirin for a managed control with SOC 2, secret redaction inside the IDE and single sign on on its Enterprise plan.
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. HOL Guard and Knostic are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,168 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose HOL Guard if
- Your developers run several coding agents, such as Claude Code, Codex, Cline, OpenCode or Kimi Code, and you want one control across all of them.
- Ambiguous actions should pause for a developer to approve, with each approval scoped to one artifact or wider and set to expire.
- The guard should run on each machine, keep working offline and send nothing to a vendor unless you connect the cloud.
- You want policies as text files with tests that gate CI, plus an observe mode before anything is enforced.
- Package installs by agents should be checked against supply chain advisories before they run.
Choose Knostic if
- Your security team needs a vendor with a SOC 2 Type 2 report and single sign on on the Enterprise plan.
- Secrets and personal data should be redacted inside the IDE before an assistant sees them.
- You want an inventory of every MCP server in use, an allowed list and alerts when a connection drifts.
- Security events should flow into your SIEM and Slack.
- You are also rolling out Microsoft 365 Copilot and want to see which business topics it exposes.
| Feature | H HOL Guard |
K Knostic |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
HOL GuardIntegrations & Tool Calling Guard connects to fifteen coding agents, among them Claude Code, Codex, Cursor, GitHub Copilot CLI, Cline, Gemini CLI, OpenCode, Hermes and Kimi Code. It reaches them through native hooks such as PreToolUse and PermissionRequest, managed MCP proxies that route a server's tool calls through Guard, and launch wrappers. How deep it goes depends on the events each agent exposes. On the Team plan, Guard Cloud connects to Slack, Jira, PagerDuty, GitHub, email and HTTPS webhooks, and review actions can be taken from Slack. SourceHOL, github.com/hashgraph-online/hol-guard harness support matrix and hol.org/guard/featuresread 2026-11-17 |
||
|
KnosticIntegrations & Tool Calling Kirin integrates into Cursor, Claude Code, GitHub Copilot and Windsurf, with Codex and JetBrains listed as coming, to block risky prompts, MCP connections and extensions inline. The Enterprise plan adds SIEM and Slack integrations, and Kirin is built to extend existing DLP, DSPM, Purview and SIEM investments into AI workflows. The Copilot work covers Microsoft 365 Copilot and Glean, with remediation through permissions and labels. SourceKnostic, getkirin.com, /pricing, /features and /enterpriseread 2026-10-06 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
HOL GuardWorkflow Orchestration Every action takes one fixed path: a hook or wrapper catches it, a bundled Rust runtime checks it against policy, Guard allows, asks or blocks, and a receipt is written. Guard Cloud adds a routing studio where a team builds multistep graphs of triggers, enrichment, conditions, rate limits and delivery steps, tests them on a sample event and publishes them, with failed deliveries retried through an outbox. Routing only delivers notifications and records, and it never approves, blocks or changes what runs on a machine. Guard does not coordinate the agents it protects. SourceHOL, hol.org/guard/docs/guard/routing.md and the Guard architecture guideread 2026-11-17 |
||
|
KnosticWorkflow Orchestration The product runs a fixed pipeline over the customer's AI tools and agents, discovering, monitoring, enforcing and remediating, with the same policies applied to agents built in house, SaaS agents and MCP driven agents. Knostic does not orchestrate the customer's agents, and customers cannot build a flow of their own. SourceKnostic, knostic.ai/ai-agent-security-solutionread 2026-10-06 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
HOL GuardTriggers & Channel Coverage Checks start on the agent's own events, with no prompt from a person. Hooks fire before each tool call and on permission requests, and on Copilot CLI, Kimi Code, Z Code, Devin, Cline and Pi they also fire when a prompt is submitted, so shell commands, file reads, MCP calls and package installs are evaluated before they execute. Launch interception reviews new or changed MCP servers, plugins, skills and hooks before an agent starts. Guard Cloud flags MCP and skill drift and sends digests and matched advisories, and routing workflows start on synced events such as a new triage item. SourceHOL, harness support matrix and hol.org/guard/features; github.com/hashgraph-online/hol-guard/blob/main/docs/guard/harness-support.mdread 2026-11-17 |
||
|
KnosticTriggers & Channel Coverage Kirin enforces inline on each prompt, MCP connection and extension before execution and keeps scanning projects continuously, and MCP posture management flags policy drift and misconfiguration as they occur, with no user prompt needed. SourceKnostic, getkirin.com, /features and knostic.ai/mcp-security-posture-management-solutionread 2026-10-06 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
HOL GuardKnowledge Grounding & RAG An inventory of the plugins, skills, hooks and MCP servers on each machine is kept and can be exported as an AI bill of materials in JSON. Package installs are checked against supply chain intelligence, and HOL's Security Hub publishes advisories, CVEs, threat campaigns and monthly reports as RSS and JSON feeds, with premium feeds on Pro. HOL also runs a public plugin registry and a plugin security dataset. All of this is reference data that informs Guard's decisions, and there is no retrieval store over the customer's own knowledge for agents to draw on. SourceHOL, github.com/hashgraph-online/hol-guard and hol.org/guard/llms.txtread 2026-11-17 |
||
|
KnosticKnowledge Grounding & RAG An up to date list of the customer's allowed MCP servers is kept, with every connection validated in real time, alongside a map of which business topics, such as HR, finance and legal, Copilot exposes. AgentMesh is Knostic's own catalog, which scans every MCP server, agent skill and extension for prompt injection, malicious behavior and supply chain risk. Knostic describes no retrieval structure that the agents draw on. SourceKnostic, knostic.ai/mcp-security-posture-management-solution and /copilot-readiness-assessmentread 2026-10-06 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
HOL GuardMemory & State Persistence An always allow decision is saved against a command's hash and holds until someone removes it or the command changes. Paid plans sync this decision memory across sessions and devices, and Team shares reviewed policy decisions across a workspace. Guard applies these as rules the next time a matching action arrives. There is no memory layer for the agents Guard watches, and Guard runs no agent of its own that carries context from one run to the next. SourceHOL, hol.org/guard/docs/guard/approval-center-and-audit.md and hol.org/guard/featuresread 2026-11-17 |
||
|
KnosticMemory & State Persistence Policies, inventories and allowed lists are settings that shape enforcement. Knostic describes no memory for the customer's agents or for an agent of its own. SourceKnostic, knostic.ai/ai-agent-security-solution and getkirin.com; knostic.airead 2026-10-06 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
HOL GuardHuman Oversight & Guardrails Ambiguous actions pause for a person. A held request can be resolved in the agent's own dialog where one exists, in a local approval center on the developer's machine, or from the terminal, and each approval takes a scope that runs from one artifact up to a publisher, workspace, agent or everything. One time approvals expire after 5 or 15 minutes, a timeout never counts as approval, and an optional password gate protects broad allows and history clears. On Codex, approving in the browser resumes the same thread. Team plans add a shared review queue with assignment. SourceHOL, hol.org/guard/docs/guard/approval-center-and-audit.md and harness support matrixread 2026-11-17 |
||
|
KnosticHuman Oversight & Guardrails Policies on the customer's coding agents block destructive commands and risky prompts and connections, redact secrets and PII, gate exec and file read operations, and enforce least privilege access, OAuth based agent authentication and an allowed MCP server list, with policy groups on the Enterprise plan. These policies block or allow. Knostic names no step that asks a person to approve an agent action before it commits. SourceKnostic, knostic.ai/ai-agent-security-solution, /mcp-security-posture-management-solution and getkirin.com/pricingread 2026-10-06 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
HOL GuardSecurity, Identity & Governance Team workspaces carry members, roles and role based access, service principals for automation and API access, and named owners for machines, policies and cases. A managed restrictive control set lets an organization lock settings that local remembered decisions cannot loosen. Cloud commands use signed capabilities that are bound to one device or workspace, limited to exact operations and set to expire, and headless machines pair through an OAuth device code. HOL states no single sign on, no SOC 2 report, ISO certificate or trust center, and makes no compliance claims for Guard. SourceHOL, hol.org/guard/features, local vs cloud guide and hol.org/guard/methodology/product-factsread 2026-11-17 |
||
|
KnosticSecurity, Identity & Governance Kirin's Team plan adds role based access control and audit logs, and its Enterprise plan adds enterprise SSO. Multi factor authentication is among the product security controls. Knostic reports SOC 2 Type 2 and GDPR compliance, and its trust center offers a pentest report. Role based training is part of Knostic's own security program. SourceKnostic, getkirin.com/pricing and security.knostic.airead 2026-10-06 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
HOL GuardObservability & Auditability Every evaluation writes a local receipt with the reason, the policy action and the approval source. The audit trail keeps the pending request, its changed fields, the artifact that triggered it, the decision and the scope it was saved at. A policy check shows the effect, the winning rule and every candidate rule, so a block can be traced to its cause. Guard Cloud adds searchable history across sessions and machines, incident summaries and evidence exports, and Team adds cases with an audit history of admin and review actions. History runs 7 days on the free plan and 30, 180 or 365 days in the cloud by plan. SourceHOL, approval center and audit guide, policy as code guide and hol.org/pricing.md; hol.org/guard/docs/guard/approval-center-and-audit.mdread 2026-11-17 |
||
|
KnosticObservability & Auditability Knostic says it tracks "every agentic action" and keeps logs for compliance and incident response. MCP posture management logs connections, blocks and drift events for review. Kirin gives centralized audit of security events and actions across the customer's agents, with audit logs and a unified dashboard on Team and compliance ready reporting on Enterprise. Knostic describes no record at the level of each step or tool call. SourceKnostic, knostic.ai/ai-agent-security-solution, /mcp-security-posture-management-solution and getkirin.com/pricingread 2026-10-06 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
HOL GuardDeployment & Data Residency The core runtime runs on the developer's own computer, installs without an account and keeps enforcing with no internet connection or while the cloud is down. History stays in a folder on the machine, nothing leaves it by default and file contents are never sent. Desktop builds cover macOS 13 or later on Apple silicon, Windows x64 and Linux x86_64, and the open source core can be self hosted. Guard Cloud is optional and receives receipts, redacted summaries and a fleet posture summary once a machine is paired. Its hosting region is not stated. SourceHOL, hol.org/guard and the local vs cloud guideread 2026-11-17 |
||
|
KnosticDeployment & Data Residency The infrastructure runs on Amazon Web Services, with Cloudflare, Descope, Sentry and Groundcover among Knostic's subprocessors. No hosting region is published, and Knostic names no customer environment or data residency option. SourceKnostic, security.knostic.airead 2026-10-06 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
HOL GuardPrebuilt Agents, Templates & Packs Starter policies ship with the product, a package firewall starter among them, along with policy presets and reviewed recipes that carry exact matchers, tests and downloadable hashes. Command rules come from an extension registry where core protections stay on and outside contributions need an explicit opt in, and the routing studio offers workflow templates. These are policy content for Guard itself, and HOL offers no prebuilt agents. SourceHOL, policy as code guide, github.com/hashgraph-online/hol-guard and hol.org/guard/llms.txt; hol.org/guard/docs/guard/policy-as-code.mdread 2026-11-17 |
||
|
KnosticPrebuilt Agents, Templates & Packs OpenAnt, the oversharing tester and a prompts library are free standalone utilities, and Knostic names no prebuilt agents, templates or packs. Kirin's Free plan covers teams of up to five with policy controls and MCP, extension and rules scanning, before Team at $15 a user a month and a custom Enterprise plan. SourceKnostic, getkirin.com/pricing and knostic.ai/copilot-readiness-assessment; knostic.airead 2026-10-06 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
HOL GuardModel Flexibility & Routing Allow, ask and block decisions come from a policy engine, and no model takes part in enforcement. A model appears in one place, a Guard Cloud routing step that sends an investigation event through the customer's own OpenRouter account and records the answer. The customer sets the model on that step, with a free OpenRouter model as the default and paid models billed by OpenRouter. The answer never changes a Guard decision. SourceHOL, hol.org/guard/docs/guard/integrations/openrouter.mdread 2026-11-17 |
||
|
KnosticModel Flexibility & Routing Knostic governs third party assistants and agents, such as the coding assistants Kirin protects and Microsoft 365 Copilot, and offers no model choice or routing of its own. SourceKnostic, knostic.ai and getkirin.comread 2026-10-06 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
HOL GuardAPIs, SDKs & MCP Extensibility The core is open source under Apache 2.0 on GitHub, written in Python with a Rust runtime and published on PyPI. Policies are text files in a published GuardPolicy format that is still in alpha, and the command line covers status, approvals, receipts, inventory, policy tests and pairing. Team plans add service principals for API access, and HOL lists an OAuth protected MCP endpoint for workspace and receipt tools. No API reference or tool list for Guard Cloud is published. SourceHOL, github.com/hashgraph-online/hol-guard, hol.org/llms.txt and hol.org/guard/featuresread 2026-11-17 |
||
|
KnosticAPIs, SDKs & MCP Extensibility AgentMesh offers API access by tier, with capped calls for free signed in users and on Premium at $15 a user a month, which includes a Kirin license, and unlimited calls on Pro at $850 a user a month. OpenAnt is an open source tool. Kirin offers open API integration, but no API reference or SDK for building on the Knostic platform is published. SourceKnostic, knostic.ai/blog/introducing-agentmesh-access-tiers and getkirin.com/featuresread 2026-10-06 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
HOL GuardTesting, Debugging & Optimization Policy changes can be tested before they take effect. Test cases live in the policy file, each describing an event and the effect expected, and the test command reports pass, fail or ambiguous, with exit codes that gate a CI pipeline and a diff check against the live policy. New policies can run in observe mode, recording decisions on real agent activity without stopping anything, before they move to enforce. Imports preview by default, and a saved export rolls a policy back. The companion Plugin Scanner also runs as a GitHub Action quality gate on agent plugins. SourceHOL, hol.org/guard/docs/guard/policy-as-code.mdread 2026-11-17 |
||
|
KnosticTesting, Debugging & Optimization The Copilot Readiness Assessment maps which business topics the customer's Copilot exposes, finds the permission gaps behind them against each user's need to know, and recommends changes to file and URL permissions. Knostic delivers it as an independent assessment of the deployed assistant that complements Microsoft's own tools, and there is no harness for the customer to run. A free LLM oversharing tester is also offered. SourceKnostic, knostic.ai/copilot-readiness-assessmentread 2026-10-06 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
HOL GuardBrowser & Computer Use Guard watches what the customer's coding agents do, such as shell commands, file reads, package installs and MCP calls, and it drives no browser, desktop or remote computer itself. Browser actions an agent takes through MCP can be approved for 15 minutes, 1 hour or 5 hours at a time, and the agent doing the browsing is the customer's own. SourceHOL, hol.org/guard/docs/guard/approval-center-and-audit.mdread 2026-11-17 |
||
|
KnosticBrowser & Computer Use Kirin runs as a background service in the IDE, and the agents it watches are the customer's coding assistants. Knostic describes no browser or computer use. SourceKnostic, getkirin.com; knostic.airead 2026-10-06 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | H HOL Guard |
K Knostic |
|---|---|---|
|
Entry price Lowest public entry point |
Free on one machine. Solo is $4.99 a month, Pro $15 a month and Team $30 a seat a month, with Enterprise by contract. | Kirin free for 1 to 5 users; Team $15 per user a month; Enterprise and the agent security platform quoted |
|
Pricing confidence How public the numbers are |
Public, exact | Public, partial |
|
Billing Primary billing axis |
Solo and Pro are billed per user and Team per seat, monthly or annually. | Kirin and AgentMesh are billed per user per month. |
|
Variable cost Workload / overage exposure |
Low variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
Free tierTrial
|
Free tierTrial
|
|
Buying motion Self-serve vs sales call |
Mixed | Mixed |
|
Pricing verified When this pricing was last checked |
HOL Guard is built by HOL DAO LLC, which also runs a plugin registry, an agent registry and a set of open standards, and its core runtime is open source under Apache 2.0. HOL does not state its funding. Knostic is an independent company based in Herndon, Virginia, led by CEO Gadi Evron and CTO Sounil Yu, and backed by investors including Pitango, DNX Ventures and Shield Capital.
More comparisons with HOL Guard or Knostic
Other matchups in security and SOC agents
Not the pairing you were after? These compare a different set of security and SOC agents on the same 14 capabilities.