Temporal Cortex
Open scheduling infrastructure that gives any AI agent reliable calendar scheduling over MCP, A2A, and REST, with atomic booking and deterministic time logic.
Temporal Cortex is open scheduling infrastructure that gives any AI agent reliable scheduling across calendars. It provides 18 tools across 5 layers over MCP, A2A, and REST protocols, with deterministic temporal computation from its Truth Engine, cross provider availability merging, and atomic booking using a two phase commit to prevent double bookings. It connects Google Calendar, Outlook, and iCloud and integrates with agent frameworks such as LangGraph, CrewAI, and the OpenAI Agents SDK. The managed platform adds multi agent coordination with distributed locking, usage metering and a dashboard, caller based booking policies, and a content firewall that detects prompt injection and strips zero width Unicode. Tool responses are returned in a token optimized format to reduce agent token costs. Temporal Cortex ships an open source core under permissive licensing with a free managed platform, and its Agent Skills work across Claude, Cursor, and more than 20 other agent platforms.
Vendor details
Canonical URL
https://temporal-cortex.com
Category
Agent infrastructure
Funding status
Pre seed. Backed by Stellar Development Foundation and Draper University.
Company status
private
Use cases & customers
Primary use cases
Target customers
Integrations
Connects Google Calendar, Outlook, and iCloud, and integrates with agent frameworks including LangGraph, CrewAI, and the OpenAI Agents SDK, exposing 18 tools over MCP, A2A, and REST.
Sources & related URLs
Related / legacy domains
Capability coverage
6.5 / 14 capabilities · 46%
| Integrations & Tool CallingConnects Google, Outlook, and iCloud calendars, exposes 18 tools, and integrates with LangGraph, CrewAI, and the OpenAI Agents SDK (temporal-cortex.com, github.com). | Full |
|---|---|
| Workflow OrchestrationRoutes a scheduling workflow across 5 layers from time resolution to availability to booking, with multi agent coordination, though orchestration is scheduling specific (github.com, temporal-cortex.com). | Partial |
| Knowledge Grounding & RAGNot a knowledge grounding or RAG product (temporal-cortex.com). | Unable to verify |
| Human Oversight & GuardrailsCaller based policies enforce booking rules per agent such as max duration and allowed hours; these are guardrails rather than human approval loops (github.com). | Partial |
| Security, Identity & GovernanceA content firewall detects prompt injection and strips zero width Unicode, and OAuth token refresh is handled server side; no SOC 2 or enterprise identity is documented (github.com). | Partial |
| Observability & AuditabilityA usage dashboard and metering track tool calls per agent and team, connected calendars, and billing (github.com). | Full |
| Memory & State PersistenceDistributed locking is transient coordination to prevent double bookings, not agent memory or state persistence (github.com). | Unable to verify |
| Deployment & Data ResidencyShips an open source self host server with zero infrastructure alongside a free managed platform (temporal-cortex.com, github.com). | Full |
| Prebuilt Agents / Templates / PacksAgent Skills and focused sub skills provide prebuilt scheduling capabilities across more than 20 agent platforms (github.com). | Partial |
| Triggers & Channel CoverageSupports autonomous scheduling over MCP, A2A, REST, and email, plus an Open Scheduling network for publicly queryable availability (github.com, temporal-cortex.com). | Partial |
| Model Flexibility & RoutingModel agnostic infrastructure that works with any agent but does not itself route or select models (temporal-cortex.com). | Unable to verify |
| APIs / SDKs / MCP ExtensibilityExposes an MCP server, A2A, a REST API, an npm package, and framework SDK integrations (github.com, temporal-cortex.com). | Full |
| Testing, Debugging & OptimizationBenchmarks are published as marketing content; no user facing testing or evaluation tooling is documented (temporal-cortex.com). | Unable to verify |
| Browser / Computer-useBrowser is listed as a delivery protocol, not browser automation or computer use (github.com). | Unable to verify |
Recent platform changes
No recent material changes tracked yet.
Pricing
Free. Temporal Cortex ships an open source core for self hosting and a free managed platform; no paid tier is publicly priced.
Usage metering on the managed platform tracks tool calls per agent and team; no published rate.
Included quota
Open source is unlimited when self hosted; the managed platform is currently free.
Cost watchouts
Usage metering and billing infrastructure exist on the managed platform, so paid usage tiers may be introduced; self hosting adds standard infrastructure and OAuth app maintenance.
Variable cost rationale
The core is deterministic computation rather than model inference, self hosting adds only minor infrastructure, and the managed platform is currently free, so cost does not scale materially with usage today.
Overage / add-ons
Not public.
Sales call required
No — self-serve available
Free / trial
Free open source self host and a free managed platform.
Lowest paid plan
Not public.
Key ambiguities
The managed platform exposes billing and usage metering, but no paid tier or rate is published.
Related vendors
- Acrab — Singapore compute infrastructure company building a full stack…
- AgentOps — Agent observability and reliability platform with broad model and…
- Agno — High-performance agent runtime and framework (formerly Phidata) with…
- AIsa — Unified resource and payment gateway for AI agents that lets them…
- AlphaBitCore — AI control plane that governs how models, agents, tools, and…
- Anchor Browser — Cloud hosted browser infrastructure that lets AI agents operate real…