Developer docs
API playgroundTry for free, no card

Search company profiles

Runebook

Full company profile

uuid003wxfb

Namestring
Runebook
Legal namestring
Runebook
Websiteurl
runebook.ai
Company typeenum
Private
Founded yearstring
-
Descriptiontext

Runebook was a small, stealth-stage software company (1–10 employees) that built Tome, a local LLM client with native Model Context Protocol (MCP) support. The product enabled developers and AI practitioners to run large language models locally on their own hardware while leveraging MCP to build and interact with AI agents, targeting concerns around data privacy, deployment control, and ease-of-use for agentic workflows. The company positioned itself as "a small but nimble group of hackers" building user-friendly interfaces for LLMs.

The founding team consisted of engineers who previously built products at the frontier of DevOps at companies including Heroku, Mezmo, Sentry, and MakerBot. Runebook pursued a product-led, community-driven go-to-market: Tome was distributed open-source via a GitHub repository and as a self-serve download at gettome.app, with community engagement on Discord, Bluesky, and X (Twitter). No pricing, revenue model, or named customers were disclosed, and no enterprise logos or commercial contracts were reported in available sources.

In November 2025, Runebook was acquired by Keycard — an identity and access platform for AI agents — to expand Keycard's ecosystem of SDKs for building and adopting trusted MCP-powered AI agents. The acquisition was announced at the AI Engineer Code Summit. Post-acquisition, Runebook's Tome product (including an extension branded "Tome for Coding Agents") operates within Keycard, and Runebook no longer functions as an independent entity. No funding rounds, investor identities, revenue figures, or cap-table details were disclosed.

Short descriptiontext

Runebook was a stealth-stage software startup that built Tome, a local LLM client with native Model Context Protocol support, targeting developers and AI practitioners who wanted to run LLMs locally with agent capabilities. The company was acquired by Keycard in November 2025.

Operating statusenum
Acquired
Ownership categoryenum
Headcount rangeband
1–10
akta.pro rankint
HeadquartersSan Francisco, United States
HQ citystring
San Francisco
HQ countrystring
United States
HQ regionstring
North America
Markets served

Serves global market

Keyword5 values
local LLM client, MCP AI agents, AI agent interfaces, developer AI tools, Model Context Protocol
Industry1 code
PRIMARYFSAPABAB
Smart Contract Frameworks & SDKs (developer kits, templates, standards)
Financial & Insurance/Blockchain & Web3/Smart Contract Platforms & Developer Tooling (SDKs, APIs, indexing, oracles)
NAICS code1 code
  • Software Publishers5132
SIC code1 code
  • Services-Prepackaged Software7372
Product category
AI Developer Tools
Social media profiles2 records
GTM motion2 records

Each record includes

Type, Description, Source

Revenue model1 record
1Software/Tool
TypeSubscription Recurring
Description

Runebook built Tome as a local LLM client with MCP support. Revenue model not explicitly disclosed in available sources.

runebook.ai
Marketing channels5 records

Each record includes

Title, Type, Stage, Description, Source

Distribution channels2 records

Each record includes

Title, Type, Scope, Target buyer, Description, Source

Cost components4 values
Personnel, Technology or R&D, Marketing or Sales, Operations
GTM typeB2C
B2C
Offering typeSoftware
Software
Brand1 of 2 records shown
1Tome
Description

A local LLM client with magical MCP powers

runebook.ai
+1 more record
Core offering1 text field

Runebook builds Tome, a downloadable local LLM client with native Model Context Protocol (MCP) support that enables users to run large language models on their own machines while building and interacting with AI agents. The product is offered as open-source software via GitHub and a direct-download web app at gettome.app, targeting developers and AI practitioners who want privacy-preserving, locally controlled LLM interfaces.

Differentiator
Functional benefit
Problem solved
Product overview1 text field

Runebook is a software company that built Tome, a local LLM client with native MCP (Model Context Protocol) support. The company was acquired by Keycard in November 2025 to expand Keycard's ecosystem of SDKs for building and adopting trusted MCP-powered AI agents. Runebook was previously focused on building user interfaces for LLMs to empower people, and their primary product, Tome, provides a user-friendly interface for running LLMs locally with enhanced AI agent capabilities through MCP integration.

Product and service1 record
1Tome
CategoryAI Developer Tools
Description

Tome is a downloadable local LLM client with native Model Context Protocol (MCP) support that enables developers and AI practitioners to run large language models on their own machines and build AI agent interfaces with privacy and local control. It is offered as open-source software.

Scale indicator1 record

Each record includes

Type, Value, Description, Source

Partnership1 partner
Strategic tierCoreTypeStrategic or Co-development PartnerAnnounced on2025-11-01
Description

Keycard acquired Runebook in November 2025 to expand its ecosystem of SDKs for building and adopting trusted MCP-powered AI agents. The acquisition was announced at the AI Engineer Code Summit and aims to help companies build and deploy trusted AI agents more securely and easily.

Recent move5 records

Each record includes

Date, Type, Title, Description, Source

Expansion highlight4 records

Each record includes

Type, Description

Peers10 records
1GPT4All
TypeDirect peer
Description

Local LLM chat client with model management and a community ecosystem. Overlaps with Tome on local inference UX and developer/individual user target segment.

TypeEmerging player
Description

Open-source AI coding agent that integrates with MCP servers. Comparable emerging player in the MCP agent tooling space, with a stronger coding-agent vertical but similar developer-led GTM.

3AnythingLLM
TypeDirect peer
Description

Desktop and self-hosted AI application supporting local LLMs, agents, and document interaction. Comparable to Tome in combining local-LLM support with agent/MCP-style extensibility.

TypeDirect peer
Description

Open-source local LLM runtime that lets users run and manage large language models on their own machines. Closest direct competitor to Tome on the 'local LLM client' axis, though Ollama lacks native MCP/agent UX focus.

TypeBroad incumbent
Description

Dominant AI platform whose ChatGPT desktop app and agent tooling could subsume the local LLM client category. Comparable as a broad incumbent shaping developer expectations for LLM interfaces.

TypeEmerging player
Description

Open-source AI code assistant supporting local models and MCP integrations. Targets overlapping developer audience with similar local-first, MCP-friendly positioning.

7LM Studio
TypeDirect peer
Description

Desktop application for running local LLMs with a user-friendly GUI, targeting the same developer/hobbyist persona as Tome. Direct overlap on local inference workflow and developer audience.

TypeEmerging player
Description

Identity and access platform for AI agents that acquired Runebook in November 2025. Now the parent ecosystem in which Tome operates; comparable as the closest adjacent MCP-native SDK provider.

TypeDirect peer
Description

Open-source local AI client and chat interface for running LLMs on-device. Competes directly with Tome in the local-LLM-client category with similar privacy-first positioning.

TypeBroad incumbent
Description

Creator of the Model Context Protocol that Runebook's product is built around. As the protocol steward, Anthropic could natively deliver agentic UX that reduces demand for third-party MCP clients like Tome.

Market position
Strengths4 records

Each record includes

Headline, Details, Source

Weaknesses4 records

Each record includes

Headline, Details, Source

Competitive moat3 records

Each record includes

Type, Details

Key risks5 records

Each record includes

Headline, Details, Source

Key highlights5 records

Each record includes

Headline, Details, Source

Customer concentration

Classification, Details

Segment1 record

Each record includes

Title, Type, Primary, Description, Pain point addressed, Use case, Source

Ideal customer profile1 record

Each record includes

Profile, Firmographic size, Sales motion, Sales cycle length, Buying structure, Purchase trigger, Buyer persona, Geography, Industry vertical, Primary use case, Description, Pain points, Evidence proof points, Target buyer

Technology focused
Yes
API detail
Has APIbool
No

Docs URL, Description

AI capability2 records

Each record includes

Type, Description, Source

AI maturity
App detail

Has app

Feature1 record

Each record includes

Title, Differentiator, Description, Source

Core technology
Revenue estimate
Valuation estimate
Number of profiles
No data
No data
Funding overview

Funding stage, Last funding date, Total funding USD

Funding rounds

Each record includes

Round, Amount USD, Date, Pre money valuation, Total investors, Investors, News

Investors

Each record includes

Name, Type, Date of entry, Rounds participated, Website

Funding detail is available on the Subscription and Enterprise plan.Contact sales →

M&A

Each record includes

Name, Acquisition type, Announced date, Completed date, Status, Website, News

Investment

Each record includes

Name, Round, Announced date, Lead investor, Website, News

M&A and investment is available on the Subscription and Enterprise plan.Contact sales →

Runebook

AI Developer Toolsrunebook.ai

Runebook was a stealth-stage software startup that built Tome, a local LLM client with native Model Context Protocol support, targeting developers and AI practitioners who wanted to run LLMs locally with agent capabilities. The company was acquired by Keycard in November 2025.

What Runebook does

Runebook was a small, stealth-stage software company (1–10 employees) that built Tome, a local LLM client with native Model Context Protocol (MCP) support. The product enabled developers and AI practitioners to run large language models locally on their own hardware while leveraging MCP to build and interact with AI agents, targeting concerns around data privacy, deployment control, and ease-of-use for agentic workflows. The company positioned itself as "a small but nimble group of hackers" building user-friendly interfaces for LLMs.

The founding team consisted of engineers who previously built products at the frontier of DevOps at companies including Heroku, Mezmo, Sentry, and MakerBot. Runebook pursued a product-led, community-driven go-to-market: Tome was distributed open-source via a GitHub repository and as a self-serve download at gettome.app, with community engagement on Discord, Bluesky, and X (Twitter). No pricing, revenue model, or named customers were disclosed, and no enterprise logos or commercial contracts were reported in available sources.

In November 2025, Runebook was acquired by Keycard — an identity and access platform for AI agents — to expand Keycard's ecosystem of SDKs for building and adopting trusted MCP-powered AI agents. The acquisition was announced at the AI Engineer Code Summit. Post-acquisition, Runebook's Tome product (including an extension branded "Tome for Coding Agents") operates within Keycard, and Runebook no longer functions as an independent entity. No funding rounds, investor identities, revenue figures, or cap-table details were disclosed.

Runebook firmographics

Firmographics
Name
Runebook
Legal name
Runebook
Website
https://runebook.ai
Company type
Private
Operating status
Acquired
Headcount range
1–10 employees
Short description
Runebook was a stealth-stage software startup that built Tome, a local LLM client with native Model Context Protocol support, targeting developers and AI practitioners who wanted to run LLMs locally with agent capabilities. The company was acquired by Keycard in November 2025.
Ownership category
akta.pro rank

Runebook industry classification

Industry
Product category
AI Developer Tools
NAICS
Software Publishers (5132)
SIC
Services-Prepackaged Software (7372)
akta.pro industry
PRIMARYFSAPABAB
Smart Contract Frameworks & SDKs (developer kits, templates, standards)
Financial & Insurance/Blockchain & Web3/Smart Contract Platforms & Developer Tooling (SDKs, APIs, indexing, oracles)

Keywords

  • Local LLM client
  • MCP AI agents
  • AI agent interfaces
  • Developer AI tools
  • Model Context Protocol

Where Runebook is headquartered

Location

Headquarters

HQ city
San Francisco
HQ country
United States
HQ region
North America

Markets served

Runebook business model

Business model
GTM type
B2C
Offering type
Software
Cost components
Personnel, Technology or R&D, Marketing or Sales, Operations

Revenue model

  1. Software/Tool: Runebook built Tome as a local LLM client with MCP support. Revenue model not explicitly disclosed in available sources.

Go-to-market motion2 records

Distribution channels2 records

Marketing channels5 records

Runebook product offering

Product offering

Core offering

Runebook builds Tome, a downloadable local LLM client with native Model Context Protocol (MCP) support that enables users to run large language models on their own machines while building and interacting with AI agents. The product is offered as open-source software via GitHub and a direct-download web app at gettome.app, targeting developers and AI practitioners who want privacy-preserving, locally controlled LLM interfaces.

Product overview

Runebook is a software company that built Tome, a local LLM client with native MCP (Model Context Protocol) support. The company was acquired by Keycard in November 2025 to expand Keycard's ecosystem of SDKs for building and adopting trusted MCP-powered AI agents. Runebook was previously focused on building user interfaces for LLMs to empower people, and their primary product, Tome, provides a user-friendly interface for running LLMs locally with enhanced AI agent capabilities through MCP integration.

Differentiator

Problem solved

Functional benefit

Brands

  • Tome: A local LLM client with magical MCP powers
  • Tome for Coding Agents

Products and services

  • Tome Tome is a downloadable local LLM client with native Model Context Protocol (MCP) support that enables developers and AI practitioners to run large language models on their own machines and build AI agent interfaces with privacy and local control. It is offered as open-source software.

Companies that use Runebook

Customer profile

Segments1 record

Ideal customer profiles1 record

Runebook technology and API

Technology

Technology focussed Yes

API detail

Has API
No
API docs
API detail

Core technology

AI maturity

App detail

AI capability2 records

Feature1 record

Runebook partnerships and signals

Strategic signal

Partnerships

One partnership is on record.

  • KeycardcoreStrategic or Co-development Partner · 1 November 2025Keycard acquired Runebook in November 2025 to expand its ecosystem of SDKs for building and adopting trusted MCP-powered AI agents. The acquisition was announced at the AI Engineer Code Summit and aims to help companies build and deploy trusted AI agents more securely and easily.

Scale indicators1 record

Recent moves5 records

Expansion highlights4 records

Runebook competitors and assessment

Company assessment

Direct peers

  • GPT4All: Local LLM chat client with model management and a community ecosystem. Overlaps with Tome on local inference UX and developer/individual user target segment.
  • AnythingLLM: Desktop and self-hosted AI application supporting local LLMs, agents, and document interaction. Comparable to Tome in combining local-LLM support with agent/MCP-style extensibility.
  • Ollama: Open-source local LLM runtime that lets users run and manage large language models on their own machines. Closest direct competitor to Tome on the 'local LLM client' axis, though Ollama lacks native MCP/agent UX focus.
  • LM Studio: Desktop application for running local LLMs with a user-friendly GUI, targeting the same developer/hobbyist persona as Tome. Direct overlap on local inference workflow and developer audience.
  • Jan AI: Open-source local AI client and chat interface for running LLMs on-device. Competes directly with Tome in the local-LLM-client category with similar privacy-first positioning.

Emerging players

  • Cline: Open-source AI coding agent that integrates with MCP servers. Comparable emerging player in the MCP agent tooling space, with a stronger coding-agent vertical but similar developer-led GTM.
  • Continue: Open-source AI code assistant supporting local models and MCP integrations. Targets overlapping developer audience with similar local-first, MCP-friendly positioning.
  • Keycard: Identity and access platform for AI agents that acquired Runebook in November 2025. Now the parent ecosystem in which Tome operates; comparable as the closest adjacent MCP-native SDK provider.

Broad incumbents

  • OpenAI: Dominant AI platform whose ChatGPT desktop app and agent tooling could subsume the local LLM client category. Comparable as a broad incumbent shaping developer expectations for LLM interfaces.
  • Anthropic: Creator of the Model Context Protocol that Runebook's product is built around. As the protocol steward, Anthropic could natively deliver agentic UX that reduces demand for third-party MCP clients like Tome.

Market position

Strengths4 records

Weaknesses4 records

Competitive moat3 records

Key risks5 records

Key highlights5 records

Customer concentration

Runebook social profiles

Digital presence

Runebook financial estimates

Financial estimate

Revenue estimate

Valuation estimate

Runebook leadership team

Management profile

Number of profiles

Runebook funding detail

Funding detail

Funding overview

Funding rounds

Investors

Funding detail is available on the Subscription and Enterprise plan.Contact sales →

Runebook M&A and investment

M&A and investment

M&A

Investments

M&A and investment is available on the Subscription and Enterprise plan.Contact sales →

Frequently asked questions about Runebook

What does Runebook do?

Runebook builds Tome, a downloadable local LLM client with native Model Context Protocol (MCP) support that enables users to run large language models on their own machines while building and interacting with AI agents. The product is offered as open-source software via GitHub and a direct-download web app at gettome.app, targeting developers and AI practitioners who want privacy-preserving, locally controlled LLM interfaces.

Is Runebook a public or private company?

Runebook is a private company. It is classified as corporate owned and is currently acquired.

When was Runebook founded?

Runebook was founded in -1. It employs 1 to 10 people.

Where is Runebook based?

Runebook is headquartered in San Francisco, United States, in the North America region.

How does Runebook make money?

One revenue line is on record: software/Tool.

Who are Runebook's main competitors?

Direct peers on record are GPT4All, AnythingLLM, Ollama, LM Studio and Jan AI. Emerging players are Cline, Continue and Keycard. Broad incumbents are OpenAI and Anthropic.

Does Runebook have an API?

No public API is recorded for Runebook.

What industry is Runebook in?

Runebook's product category is AI Developer Tools. Its primary akta.pro industry code is FSAPABAB, Smart Contract Frameworks & SDKs (developer kits, templates, standards). Its NAICS code is 5132 and its SIC code is 7372.

Unlock the full company data

50 free credits on sign-up, no credit card required.

Contact sales
Live signals
CB InsightsThese startups are building the security layer for AI agentsThree startups—Hush Security, Geordie AI, and Keycard—are emerging in the AI agent security market, with Hush signing a Kyndryl partnership and taking a Series A led by Akamai, Geordie AI reporting deployments across 30 environments, and Keycard acquiring Runebook and Anchor.dev. Keycard is expected to raise its next funding round within three months.SalesTech StarKeycard Acquires Runebook to Make It Easy for Enterprises to Build and Adopt Trusted, MCP-Powered AI AgentsKeycard, the provider of an identity and access platform for AI agents, has acquired Runebook to expand its ecosystem of SDKs enabling enterprises to build and adopt trusted MCP-powered AI agents without deep expertise in identity or security. The acquisition combines Runebook's experience building developer products with Keycard's platform capabilities for AI agent identification and distributed policy enforcement. MCP is emerging as the standard for AI agents connecting with data and systems, though building and deploying MCP-based tools into production remains challenging due to security concerns.SiliconANGLEAI agent identity startup Keycard acquires Runebook to empower MCP connectivity - SiliconANGLEKeycard Labs acquired Runebook to enhance its AI agent identity platform with Model Context Protocol connectivity. Runebook builds text and voice-enabled AI agents and a desktop LLM client, and Keycard will use its expertise to expand its drop-in SDKs and one-click installation capabilities.GlobeNewswireKeycard Acquires Runebook to Make It Easy for Enterprises to Build and Adopt Trusted, MCP-Powered AI AgentsKeycard, the provider of an identity and access platform for AI agents, announced the acquisition of stealth startup Runebook at the AI Engineer Code Summit on November 20, 2025. The acquisition expands Keycard's ecosystem of SDKs that enable enterprises to build and adopt trusted MCP-powered AI agents without requiring deep identity or security expertise. Runebook's team, which previously built developer products for companies like Heroku and Sentry, will join Keycard, with co-founder Peter Cho becoming Head of Product at Keycard.