Summoner

What Summoner does

Summoner Corp. is a New York-based, Delaware-incorporated developer of coordination infrastructure for AI agents operating across organizational boundaries. Its core technology is the SPLT Protocol (Summoner Protocol for Layered Transactions), a decentralized mesh architecture that enables agents to discover verified counterparts, negotiate under governance policies, and maintain durable, cryptographically signed state via a Decision Graph. The platform exposes self-sovereign Ed25519 agent identity, encrypted routing through untrusted relays, policy hooks applied at state transitions, and adaptive backpressure mechanisms, with SDKs in Python (asyncio) and Rust (Tokio) distributed under Apache 2.0 alongside 50+ agent blueprints.

The product surface comprises the SPLT Protocol, Agent Fleets (framework-agnostic orchestration), the Decision Graph (durable audit ledger), and the Decision Network (reputation-aware discovery), supplemented by three packaged vertical use cases — RouteGuard (fleet telematics), TariffGuard (customs classification), and Patient Handoff (healthcare revenue cycle). Agents run locally on user-controlled nodes and connect to enterprise systems (SAP, Salesforce, HubSpot, Dynamics 365, Shopify, Slack, Twilio, Notion) via relays, operating in Observer, Advisor, or Actor modes.

Summoner employs 3 people (CEO Kevin Ghim, CTO Rémy Tuyéras, and Full Stack Engineer Shubh Gupta) and operates a hybrid go-to-market combining a free, self-serve Builder Edition distributed via GitHub and Discord with a paid 90-day Enterprise Pilot engagement targeting Operations and IT leaders. The company raised $100,000 in August 2025 from Forum Ventures and Right Side Capital Management; revenue is not publicly disclosed.

Name

Summoner

Legal name

Summoner Corp.

Website

https://summoner.org

Company type

Private

Founded year

2025

Operating status

Operating

Headcount range

1–10 employees

Short description

Summoner Corp. builds coordination infrastructure (SPLT Protocol, Decision Graph) that lets enterprises manage AI agents as a scalable workforce across organizational boundaries, serving AI developers and enterprise Operations/IT leaders via an open-source SDK and paid 90-day Enterprise Pilots.

Ownership category

akta.pro rank

Headquarters

HQ city

New York

HQ country

United States

HQ region

North America

Markets served

GTM type

B2B

Offering type

Software

Cost components

Personnel, Technology or R&D, Infrastructure, Marketing or Sales, Operations

Revenue model

1. Enterprise Platform Licensing: Enterprise pilot engagements with dedicated solution engineers, custom success metrics, and priority support SLA. 90-day engagement model for Operations and IT leaders to validate ROI on live production workflows.
2. Open Core / Builder Edition: Free and open source core SDK with Python and Rust runtimes, 50+ agent blueprints, and local relay. Open core model where enterprise features may be proprietary while core protocol remains open.
3. Professional Services: Architectural discovery workshops and white-glove support bundled with enterprise pilot engagements.

Pricing tiers

Go-to-market motion4 records

Distribution channels4 records

Marketing channels7 records

Core offering

Summoner provides coordination infrastructure that lets enterprises manage AI agents as a scalable workforce across organizations. Its core is the SPLT Protocol, a decentralized mesh that enables agents to discover verified counterparts, negotiate under governance policies, and maintain cryptographically signed durable state via the Decision Graph. It ships open-source Python and Rust SDKs under Apache 2.0, plus 50+ Agent Blueprints, and monetizes through a 90-day Enterprise Pilot with dedicated solution engineers.

Product overview

Summoner is a coordination infrastructure platform for the AI workforce, consisting of a core protocol (SPLT) and multiple integrated products. The main platform comprises the SPLT Protocol (decentralized mesh for cross-org agent coordination with durable state), Agent Fleets (framework-agnostic infrastructure supporting Python and Rust runtimes), the Decision Graph (cryptographically signed ledger for negotiations), and the Decision Network (discovery and transaction layer for cross-boundary agent interaction). The platform operates in three modes: Observer (passive monitoring), Advisor (proposing signed solutions), and Actor (autonomous execution). Developer tools include Python SDK (asyncio-based) and Rust SDK (Tokio-based) under Apache 2.0, plus 50+ Agent Blueprints. Enterprise services include a 90-day Enterprise Pilot with dedicated support and a free Builder Edition for developers. Industry-specific use cases include RouteGuard (fleet management), TariffGuard (customs), and Patient Handoff (healthcare revenue cycle).

Differentiator

Problem solved

Functional benefit

Products and services

• Summoner SPLT Protocol A programmable protocol for cross-organizational agent coordination. Unlike MCP (connects agents to tools) and A2A (connects agents to agents), SPLT coordinates agents across trust boundaries with durable state, portable identity, and encrypted routing. The server is an untrusted relay that maintains the pipe without seeing message contents. For AI/agent architects and enterprise engineering teams.
• Agent Fleets Framework-agnostic infrastructure for agents that execute across systems and organizations. Agents run locally on user-controlled edge nodes and connect via relays. Supports Python asyncio and Rust (Tokio) runtimes with a single config flag to toggle between them. For AI/agent architects and developers building coordinated agent fleets.
• Decision Graph A cryptographically signed ledger of every cross-company negotiation. Decisions become durable state, accessible to all parties, and audit-ready forever. Transforms ephemeral agent actions into a permanent, shared state machine. For enterprise compliance, audit, and governance stakeholders.
• Decision Network A network layer where fleets discover and transact with external agents across organizational boundaries. Supports reputation-aware peer discovery based on verified history and capabilities via the Relay network. For enterprises coordinating with suppliers, partners, and customers.
• Python SDK Python SDK (asyncio-based) for building network-coordinated agents. Agents are defined by subclassing SummonerClient with decorator-based send/receive handlers. Fully typed payloads, async-native, Apache 2.0 licensed. For AI/agent developers building on the Summoner protocol.
• Rust SDK Rust SDK (Tokio-based) for high-concurrency production environments. Provides advanced traffic shaping, resource optimization controls, and adaptive backpressure mechanisms. Toggle with Python via single config flag. Apache 2.0 licensed. For production engineering teams requiring high-throughput agent runtimes.
• Agent Blueprints 50+ pre-built agent templates available on GitHub (summoner-agents). Enables developers to quickly scaffold and deploy coordinated agent fleets without starting from scratch. For AI/agent developers accelerating build cycles.
• RouteGuard Fleet management use case where agents monitor live telematics against agreed routes. If a truck deviates, the agent creates a signed 'Variance Event' and notifies the carrier instantly. Claims $300k+ saved per 100 trucks in fuel and penalty recovery. For fleet operators and logistics teams.
• TariffGuard (Dynamic Customs) Supply chain customs use case where agents cross-reference goods against changing government databases and calculate landed cost before shipping. Claims 90% accuracy in classification and ±2% landed cost precision. For supply chain operations, importers, and customs brokers.
• Patient Handoff (Revenue Cycle) Healthcare & life sciences use case where agents negotiate the 'Handoff Packet' to confirm insurance auth and medical necessity before patient arrival. Claims 40% fewer denials and 60% faster specialist referrals. For healthcare providers, payers, and revenue cycle operations teams.
• Enterprise Pilot 90-day guided engagement for Operations & IT Leaders. Includes architectural discovery workshop, dedicated solution engineer, custom success metrics & ROI tracking, and priority support SLA. Pricing not publicly disclosed. For enterprise Operations and IT decision-makers.

Quantifiable outcome

• Reduces coordination costs by $300k+ per 100 trucks through automated telematics monitoring and variance event creation
• +2 more outcomes

Segments5 records

Ideal customer profiles2 records

Technology focussed Yes

API detail

Has API

Yes

API docs

API detail

Core technology

AI maturity

App detail

Integration8 records

AI capability7 records

Feature10 records

Scale indicators5 records

Recent moves5 records

Expansion highlights5 records

Broad incumbents

• Celigo: Celigo is a leading iPaaS platform for enterprise system integration and workflow automation. Both address cross-system coordination, though Celigo focuses on traditional SaaS integrations rather than AI agent coordination.
• Temporal Technologies: Temporal is an established durable execution platform widely used for microservices orchestration. Its durable state machine concept parallels Summoner's Decision Graph, though Temporal is not agent-specific.
• Workato: Workato is an enterprise automation and integration platform used for cross-system workflow orchestration. It addresses similar enterprise coordination pain points but is not designed for autonomous AI agent negotiation.

Direct peers

• Google Agent-to-Agent (A2A) Protocol: Google's A2A protocol enables direct agent-to-agent communication across organizational boundaries. Summoner explicitly differentiates SPLT Protocol against A2A by adding durable state, cryptographic identity, and policy enforcement.
• Anthropic Model Context Protocol (MCP): MCP is Anthropic's open protocol for connecting AI agents to tools and data sources. Summoner explicitly positions SPLT Protocol as complementing MCP — handling cross-org trust boundaries that MCP does not address.
• Microsoft AutoGen: AutoGen is Microsoft's open-source framework for building multi-agent AI systems. Summoner explicitly integrates with AutoGen and competes for the same agent orchestration and cross-system coordination use cases.
• LangChain: LangChain is the leading AI agent framework with extensive tooling for building LLM-powered agents. Summoner explicitly integrates with LangChain and positions itself as the coordination layer that complements LangChain's agent reasoning capabilities.
• CrewAI: CrewAI is a multi-agent orchestration framework for building collaborative AI agent crews. Summoner explicitly supports CrewAI integration and competes for the same developer mindshare on agent coordination architecture.

Emerging players

• Inngest: Inngest provides durable execution and event-driven orchestration for AI agents and serverless functions. Both companies focus on durable state and step functions for AI workflows, with overlapping use cases in long-running agent processes.
• Restate: Restate is a durable execution framework for building reliable distributed applications and AI agent workflows. It shares Summoner's emphasis on durable state and resilient coordination, with comparable developer-tool positioning.

Market position

Weaknesses5 records

Competitive moat4 records

Key risks6 records

Key highlights6 records

Customer concentration

• Xx.com/SummonerNetwork
• GitHubgithub.com/Summoner-Network
• LinkedInlinkedin.com/company/summoner-network

Revenue estimate

Valuation estimate

Number of profiles

Profiles3 records

Funding overview

Funding rounds1 record

Investors2 records

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

M&A

Investments

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

Frequently asked questions about Summoner