How much does H Platform cost?

Agents API Free, Builder $20 a month, Startup $200 a month, Enterprise by quote; Models API per token.

Does H Platform support MCP and tool calling?

Full under the Agentic Index verification standard. H Platform publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: A documented REST API (agents, environments, sessions, skills, vaults, schedules), the hai-agents Python and TypeScript SDKs and CLI, and agents run over MCP; the Models API serves Holo models with open weights. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can H Platform be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. H Platform publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: The Agents API runs from an EU or a US base URL, agents can run in the customer's own browser or desktop, Holo models can be self hosted, and the enterprise offering lists regional data residency, zero retention, on premise and sovereign cl. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does H Platform give you tracing and observability into agent runs?

Full under the Agentic Index verification standard. H Platform publishes public evidence of tracing, observability and audit logging into agent runs, so a team can see what an agent did and why. Evidence basis: Each session keeps a complete paginated event record of what the agent observed and did, with full logs and session replay of every action, and enterprise exports are audit ready. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

H Platform

Q: What are the best alternatives to H Platform?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to H Platform among browser and computer-use agents are Airtop, Autotab, Axiom.ai, Automat AI. Each is graded on the same public evidence, and no vendor pays for placement.

Also known as: Runner H, H Company, HoloTab

Visit site

Browser / computer-use agentindependentVerified 2026-09-27

Entry priceFree tier; Agents API Builder from $20 a monthFull pricing detail

H Company's computer use agents: the H Platform Agents API runs agents in the browser and on desktops on its Holo models, with HoloTab and HoloDesktop.

H Company, a Paris AI lab, builds computer use agents on its own Holo vision language models. Runner H, its first flagship agent, is no longer presented as a product: its page now redirects to a newsroom post, and the company sells H Platform instead. The Agents API runs managed agents that see the screen, locate interface elements and act in browsers and on desktops, in H's hosted environments or in the customer's own browser or desktop, with the Holo model of the customer's choice from H's family.

Developers define agents with environments, skills, instructions and subagents, give them custom tools and vault credentials, and run them in sessions that can be watched, steered, paused and resumed, scheduled on a cron, or started from the API, the hai-agents Python and TypeScript SDKs, a CLI, MCP clients and n8n. Every session keeps a complete event record and replay. The API runs from EU or US endpoints, and the enterprise offering adds on premise and sovereign cloud deployment, regional data residency, zero retention, SOC 2 Type II and ISO 27001. HoloTab, a Chrome extension, HoloDesktop, an on device CLI, and open Holo weights are free to try.

The pages read do not document roles or SSO, a memory layer or an evaluation harness, and the agent and skill catalog in the docs loads client side without named entries.

Vendor details

Canonical URL

https://hcompany.ai

Company status

independent

Use cases & customers

In practice

A finance team faces slow, error prone onboarding. Runner H pre fills multi step verification forms across portals, handles document uploads, and completes the workflow autonomously by seeing and clicking each interface element, freeing analysts for higher value review.

A recruiter needs candidates sourced and logged. From a single natural language prompt, Runner H aggregates resumes from the web, navigates the applicant tracking system, and updates the customer relationship management records without any brittle scripts to maintain.

A quality assurance team must test an e-commerce funnel across payment methods. Tester H converts plain English test scenarios into executable checks, simulates real user actions, and adapts automatically when the interface changes, cutting testing maintenance.

Sources & related URLs

Research sources

https://hcompany.ai/agents-api https://hcompany.ai/enterprise https://hcompany.ai/pricing https://hub.hcompany.ai/llms.txt https://hub.hcompany.ai/agents-api/observe-and-steer https://hub.hcompany.ai/agents-api/schedules/overview https://hub.hcompany.ai/agents-api/agents/create

Agentic Index coverage score

9.0 / 14 capabilities · 64%

Integrations & Tool Calling	Full
Agents can be given custom tools whose results the customer's code returns to the session, beside operating any interface directly; agents also run from n8n and MCP clients. Sourcehub.hcompany.ai/agents-api/custom-toolsread 2026-09-27
Workflow Orchestration	Full
Agents are defined with environments, skills, instructions and subagents, parallelize work across subagents, and run in sessions that can be paused, resumed and scheduled; the enterprise platform orchestrates workflows across systems and switches to computer use for steps without an API. Sourcehub.hcompany.ai/agents-api/multi-agentread 2026-09-27
Knowledge Grounding & RAG	Unable to verify
No retrieval over a maintained store of the customer's knowledge is documented; agents read interfaces and documents at run time and the Models API offers document OCR as a model capability. Sourcehub.hcompany.ai/llms.txtread 2026-09-27
Human Oversight & Guardrails	Partial
A running session can be watched, paused, resumed, steered with messages or forced to answer, and two factor prompts are handed to a person; an approval step before an action commits appears only in an enterprise case description, not as a documented setting. Sourcehub.hcompany.ai/agents-api/observe-and-steerread 2026-09-27
Security, Identity & Governance	Partial
The enterprise page states SOC 2 Type II and ISO 27001 with a Vanta trust center at trust.hcompany.ai, plus vaults for credentials and redaction before data leaves the perimeter; no roles, SSO or other access model is documented. Sourcehcompany.ai/enterpriseread 2026-09-27
Observability & Auditability	Full
Each session keeps a complete paginated event record of what the agent observed and did, with full logs and session replay of every action, and enterprise exports are audit ready. Sourcehub.hcompany.ai/agents-api/observe-and-steerread 2026-09-27
Memory & State Persistence	Unable to verify
Sessions carry their own history and a customer can bring a browser profile, which is browser state; no memory store an agent reads across sessions is documented. Sourcehub.hcompany.ai/agents-api/sessions/overviewread 2026-09-27
Deployment & Data Residency	Full
The Agents API runs from an EU or a US base URL, agents can run in the customer's own browser or desktop, Holo models can be self hosted, and the enterprise offering lists regional data residency, zero retention, on premise and sovereign cloud. Sourcehcompany.ai/enterpriseread 2026-09-27
Prebuilt Agents, Templates & Packs	Partial
The docs render a catalog gallery of H provided agents and skills, but it loads client side and no page names the entries or the jobs they do; the agents-api-demos repository offers examples. Sourcehub.hcompany.ai/agents-api/skills/overviewread 2026-09-27
Triggers & Channel Coverage	Full
Schedules create sessions on a cron expression and can be paused and resumed, beside sessions started from the API, SDKs, CLI, MCP clients, n8n and the platform, with webhooks for notifications. Sourcehub.hcompany.ai/agents-api/schedules/overviewread 2026-09-27
Model Flexibility & Routing	Unable to verify
An agent's model is any Holo model id from H's own family (default holo3-122b-a10b), and no choice of provider is documented. Sourcehub.hcompany.ai/agents-api/agents/createread 2026-09-27
APIs, SDKs & MCP Extensibility	Full
A documented REST API (agents, environments, sessions, skills, vaults, schedules), the hai-agents Python and TypeScript SDKs and CLI, and agents run over MCP; the Models API serves Holo models with open weights. Sourcehub.hcompany.ai/agents-api/api-referenceread 2026-09-27
Testing, Debugging & Optimization	Partial
Sessions and individual events take feedback through the API and replays show where a run failed; no evaluation harness, scored test cases or quality gate for agents is documented, and the QA testing use case tests the customer's application rather than the agent. Sourcehub.hcompany.ai/agents-api/sessions/feedbackread 2026-09-27
Browser & Computer Use	Full
H Platform agents see the screen, locate interface elements and act in the browser and on desktops, in H's hosted environments or in the customer's own browser or desktop, on the Holo computer use models. Sourcehcompany.ai/agents-apiread 2026-09-27

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify 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

Recent platform changes

2026-09-28·Agent capabilityVerified

H released Holo4, its own agentic models in a 27B dense size and a 35B mixture of experts size, on its Models API and as open weights on Hugging Face. One model clicks and types on screens, writes and runs code, and calls MCP or API tools across desktop, web, Android and code sandboxes. H reports 85.2% on OSWorld for the 27B at $0.08 per task, with every benchmark run published.

Bears on: Browser/computer use

View source

2026-07-22·IntegrationsPartially Verified

H Company integrated Linkup's web search API as the default retrieval layer across its computer-use agent stack. This embedded integration replaces the platform's previous search setup, enabling agents to pull real-time web context mid-task with a median latency of 1.5 seconds.

Bears on: Integrations

View source

View all 2 changes for H Platform →Tracked since Jul 2026 · Verified from public vendor sources

Pricing

Free tier; Agents API Builder from $20 a month

Free tier

What is public

hcompany.ai/pricing publishes Agents API session plans (Free $0, Builder $20 a month, Startup $200 a month, Enterprise custom with negotiated markup) with the first $20 or $200 of usage at model cost, per token Models API rates, and free HoloTab, HoloDesktop CLI and open Holo weights. The earlier Runner H wave rollout is withdrawn: Runner H's page now redirects to a newsroom post.

Free / trial

Free Agents API plan; HoloTab extension, HoloDesktop CLI and open weights free

Lowest paid plan

Builder, $20 a month

Key ambiguities

Sessions per plan are approximate and vary with task complexity and the Holo model used.

Agentic Index verified 2026-09-27

Official pricing page

Related vendors

Alternatives to H Platform

The closest documented capability profiles to H Platform among browser and computer-use agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Airtop9.0 / 14Adds documented Model Flexibility & Routing
Autotab8.0 / 14Adds documented Memory & State Persistence
Axiom.ai10.0 / 14Adds documented Model Flexibility & Routing
Automat AI11.5 / 14Adds documented Knowledge Grounding & RAG and Memory & State Persistence, among others
Browser Use11.5 / 14Adds documented Memory & State Persistence and Model Flexibility & Routing
Narada10.5 / 14Adds documented Knowledge Grounding & RAG and Memory & State Persistence

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

Compare H Platform with other vendors →Compare all browser and computer-use agents →See where H Platform ranks →

Data confidence: high

Head to head

H Platform vs Simular