Jentic
Jentic is an AI infrastructure company building the agentic knowledge layer for APIs. Founded in late 2024 and backed by $4.5M in pre-seed funding, Jentic enables enterprises to confidently manage, scale, and govern AI agent initiatives in a unified platform built on open standards. The platform provides secure execution, managed authentication, unified permissions, and observability for AI agents accessing 1,500+ public APIs and 2,000+ agent-ready workflows. Jentic's bet is that AI agents need a standards-based control plane built on OpenAPI plus Arazzo workflows plus MCP, rather than ad-hoc tool wiring inside every agent framework. The platform ships the Jentic Public APIs catalog, the Arazzo Engine (workflow runner), the Standard Agent (a composable ReWOO-style reasoning agent), the Jentic Mini self-hosted execution layer, a hosted Remote MCP server at api.jentic.com/mcp, and the Jentic API AI-Readiness Framework (JAIRF) for scoring API readiness for agents.
6 APIs
0 Features
AI AgentsArazzoOpenAPIMCPWorkflowsIntegrationsAgent RuntimeStandard AgentJust In Time ToolingCredential VaultAgent GovernanceObservabilityAPI AI Readiness
The Jentic API is the hosted agent control plane. It exposes a small, stable surface that lets any agent dynamically discover, load, and execute API operations and Arazzo workfl...
The Jentic Remote MCP Server is the hosted Model Context Protocol endpoint that exposes the Jentic catalog to MCP-capable clients (Claude Desktop, ChatGPT, Cursor, Windsurf, VS ...
Open-source Python engine that executes Arazzo workflow specifications alongside OpenAPI operation definitions. Powers the Jentic platform's workflow execution and is also insta...
Open-source composable reasoning agent framework that plans, acts, and recovers from failures, preconfigured with Jentic tools and a ReWOO reasoning loop. Primary entry point is...
Free, open-source, self-hosted API execution layer that sits between an agent and the outside world. The agent says what it wants to do and Jentic Mini handles the how: finding ...
Technical specification for evaluating how interpretable, operable, and trustworthy an API is for AI systems and autonomous agents. Defines the signals, dimensions, scoring mode...
aid: jentic
url: https://raw.githubusercontent.com/api-evangelist/jentic/refs/heads/main/apis.yml
name: Jentic
description: >-
Jentic is an AI infrastructure company building the agentic knowledge layer for APIs. Founded in late 2024 and backed
by $4.5M in pre-seed funding, Jentic enables enterprises to confidently manage, scale, and govern AI agent initiatives
in a unified platform built on open standards. The platform provides secure execution, managed authentication, unified
permissions, and observability for AI agents accessing 1,500+ public APIs and 2,000+ agent-ready workflows. Jentic's
bet is that AI agents need a standards-based control plane built on OpenAPI plus Arazzo workflows plus MCP, rather
than ad-hoc tool wiring inside every agent framework. The platform ships the Jentic Public APIs catalog, the Arazzo
Engine (workflow runner), the Standard Agent (a composable ReWOO-style reasoning agent), the Jentic Mini self-hosted
execution layer, a hosted Remote MCP server at api.jentic.com/mcp, and the Jentic API AI-Readiness Framework (JAIRF)
for scoring API readiness for agents.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
type: Index
access: 3rd-Party
position: Consumer
created: '2026-01-02'
modified: '2026-05-19'
tags:
- AI Agents
- Arazzo
- OpenAPI
- MCP
- Workflows
- Integrations
- Agent Runtime
- Standard Agent
- Just In Time Tooling
- Credential Vault
- Agent Governance
- Observability
- API AI Readiness
segments:
- AI Agents
- Workflows
- Integrations
- MCP
- Agent Infrastructure
specificationVersion: '0.19'
apis:
- aid: jentic:jentic-api
name: Jentic API
humanURL: https://docs.jentic.com/reference/public-apis/
baseURL: https://api.jentic.com/api/v1
description: >-
The Jentic API is the hosted agent control plane. It exposes a small, stable surface that lets any agent
dynamically discover, load, and execute API operations and Arazzo workflows from the Jentic catalog.
Authentication uses an agent-scoped API key (X-JENTIC-API-KEY). The canonical flow is search to load to execute:
search the catalog by natural language, load the schema and auth requirements for the returned operation or
workflow UUIDs, and execute with managed server-side credential injection. Operation UUIDs are prefixed op_ and
workflow UUIDs are prefixed wf_, and both are accepted by the execute endpoint.
tags:
- AI Agents
- Arazzo
- OpenAPI
- Workflows
- Integrations
- MCP
- Agent Runtime
properties:
- url: https://jentic.com/
type: Website
- url: https://docs.jentic.com/
type: Documentation
- url: https://docs.jentic.com/getting-started/quickstart/
type: GettingStarted
- url: https://docs.jentic.com/reference/public-apis/
type: APIReference
- url: https://app.jentic.com/sign-up
type: SignUp
- url: https://app.jentic.com/
type: Console
- url: https://api.jentic.com/api/v1
type: BaseURL
- url: openapi/jentic-openapi.yml
type: OpenAPI
- url: rules/jentic-rules.yml
type: SpectralRules
- url: json-schema/jentic-operation-schema.json
type: JSONSchema
- url: json-schema/jentic-agent-schema.json
type: JSONSchema
- url: json-schema/jentic-workflow-schema.json
type: JSONSchema
- url: json-structure/jentic-operation-structure.json
type: JSONStructure
- url: examples/jentic-search-example.json
type: Example
- url: examples/jentic-load-example.json
type: Example
- url: examples/jentic-execute-example.json
type: Example
- url: examples/jentic-register-example.json
type: Example
properties_authentication:
- name: API Key
scheme: apiKey
in: header
header: X-JENTIC-API-KEY
notes: >-
Agent-scoped API key obtained from the Jentic dashboard (app.jentic.com) by creating an agent and clicking
Generate API Key. The key authorizes that agent to call only the APIs and workflows permitted in its scope.
Anonymous register endpoint can also mint a low-rate-limit key. Set as JENTIC_AGENT_API_KEY env var when using
the SDK or MCP server.
properties_features:
- name: Just In Time Tooling (JITT)
description: >-
Tools are loaded on demand instead of being preloaded into every agent prompt, keeping the context window
small, reducing hallucination, and letting a single agent reach 1,500+ APIs without context bloat.
- name: Arazzo Workflow Execution
description: >-
Multi-step deterministic recipes defined in the OpenAPI Arazzo specification. Workflows are executed
server-side by the Arazzo Engine with parameter chaining, conditional steps, and authentication resolution.
- name: Managed Credential Vault
description: >-
Upstream API credentials live in the Jentic server-side vault and are injected at execution time. Agents never
see secrets, which eliminates the classic anti-pattern of secrets in prompts or tool definitions.
- name: Catalog Search
description: >-
Semantic, natural-language search over the public API catalog and the Arazzo workflow library. Returns ranked
UUIDs that can be fed directly to load and execute.
- name: Agent Scoping
description: >-
Each agent is created with an explicit allow list of APIs and workflows. The API key inherits that scope, so
the same SDK call cannot accidentally reach an unauthorized integration.
- name: Observability
description: >-
Every execution emits an execution_id and audit-grade telemetry, giving enterprises a unified view of agent
fleet behavior across all upstream APIs.
- name: Open Standards
description: >-
Built on OpenAPI 3.x, the OpenAPI Arazzo workflow specification, and Model Context Protocol. No proprietary
tool format, so the same catalog works for Cursor, Claude Desktop, ChatGPT, Windsurf, VS Code, and custom
Python or TypeScript agents.
- name: MCP First
description: >-
A hosted Remote MCP server at https://api.jentic.com/mcp exposes search_apis, load_execution_info, execute,
and list_credentials to any MCP-capable client with OAuth or API key auth.
properties_useCases:
- name: Sandbox To Production Agents
description: >-
Build an agent against the Agentic Sandbox, validate behavior without connecting to live systems, then promote
to production against the same Arazzo workflows.
- name: Multi API Agent Workflows
description: >-
Compose multi-vendor workflows like "create a Linear ticket, notify Slack, log to Notion" without writing N
integration adapters per agent.
- name: Governed AI Automation
description: >-
Centralize permissions, credentials, and audit so business teams can ship agents under existing IAM and
security controls.
- name: Coding Assistant Tools
description: >-
Expose 1,500+ APIs to Cursor, Claude Desktop, Windsurf, and VS Code via the Jentic Remote MCP so developers
get real API actions inside their IDE.
- name: API AI Readiness Evaluation
description: >-
Score an API against the Jentic API AI-Readiness Framework (JAIRF) to know how well it will work with
autonomous agents.
properties_integrations:
- name: 1500+ Public APIs Catalog
description: >-
Curated, AI-ready descriptions for 1,500+ public SaaS APIs maintained in the jentic-public-apis open-source
repository.
- name: 2000+ Agent Ready Workflows
description: Pre-built Arazzo workflows covering common business automations across the catalog.
- name: Claude Desktop
description: Remote MCP integration via OAuth.
- name: ChatGPT
description: Remote MCP integration via OAuth.
- name: Cursor
description: Remote MCP integration via OAuth or API key.
- name: Windsurf
description: Remote MCP integration via OAuth or API key.
- name: VS Code
description: Local MCP server integration.
- name: Anthropic / OpenAI / Google Models
description: >-
Tool definitions can be generated in either anthropic or openai format via AgentToolManager. Standard Agent
ships ReWOO-style planning compatible with Claude, GPT-4 class, and Gemini models.
properties_solutions:
- name: Enterprise Agentic Sandbox
description: >-
Closed environment for capturing and validating agent behavior before connecting to live systems. Enterprise
tier.
- name: API Scorecard
description: Automated assessment for API AI-readiness.
- name: Jentic Mini
description: Free self-hosted execution layer for agents that prefer to keep execution inside their own VPC.
- name: Arazzo UI / Editor
description: Visual workflow building and editing surface.
- name: VPC / On Premises Deployment
description: Enterprise tier; deploy the execution layer in customer infrastructure.
properties_plans:
- url: plans/jentic-plans-pricing.yml
type: PlansPricing
properties_rateLimits:
- url: rate-limits/jentic-rate-limits.yml
type: RateLimits
properties_finops:
- url: finops/jentic-finops.yml
type: FinOps
properties_sdks:
- name: Jentic Python SDK
url: https://pypi.org/project/jentic/
repository: https://github.com/jentic/jentic-sdks
language: Python
install: pip install jentic
notes: >-
Provides the Jentic client class plus SearchRequest, LoadRequest, ExecutionRequest. AgentToolManager generates
tool definitions in anthropic or openai format.
- name: Jentic TypeScript SDK
language: TypeScript
notes: Listed as "not yet available" on docs.jentic.com.
- name: Arazzo Runner CLI
repository: https://github.com/jentic/arazzo-engine
install: pip install arazzo-runner
language: Python
notes: >-
CLI plus Python API for executing Arazzo workflows directly. Commands include execute-workflow,
list-workflows, show-env-mappings.
- name: Jentic Mini
repository: https://github.com/jentic/jentic-mini
language: Python
notes: Self-hosted API execution layer.
- name: Standard Agent
repository: https://github.com/jentic/standard-agent
language: Python
notes: >-
Composable ReWOO reasoning agent preconfigured with Jentic tools. Primary class ReWOOAgent. Requires Python
3.11+.
- name: Jentic OpenAPI Tools
repository: https://github.com/jentic/jentic-openapi-tools
language: Python
- name: Jentic Arazzo Tools
repository: https://github.com/jentic/jentic-arazzo-tools
language: TypeScript
- aid: jentic:jentic-mcp
name: Jentic Remote MCP Server
humanURL: https://docs.jentic.com/guides/mcp/remote-mcp/
baseURL: https://api.jentic.com/mcp
description: >-
The Jentic Remote MCP Server is the hosted Model Context Protocol endpoint that exposes the Jentic catalog to
MCP-capable clients (Claude Desktop, ChatGPT, Cursor, Windsurf, VS Code). It speaks the same search / load /
execute pattern as the Jentic API, but packaged as MCP tools. Supports OAuth 2.0 with PKCE and dynamic client
registration, with an API key fallback for Cursor and Windsurf.
tags:
- MCP
- AI Agents
- OAuth
- Remote MCP
properties:
- url: https://docs.jentic.com/guides/mcp/
type: Documentation
- url: https://docs.jentic.com/guides/mcp/remote-mcp/
type: GettingStarted
- url: https://api.jentic.com/mcp
type: BaseURL
properties_authentication:
- name: OAuth 2.0
scheme: oauth2
notes: >-
Recommended. PKCE supported. Automatic token refresh. Dynamic client registration. Used by Claude Desktop,
ChatGPT, Cursor, Windsurf.
- name: API Key
scheme: apiKey
notes: Fallback for Cursor and Windsurf. Uses an agent-scoped Jentic API key (JENTIC_AGENT_API_KEY).
properties_features:
- name: search_apis Tool
description: Lists matching APIs and workflows for a natural language query.
- name: load_execution_info Tool
description: Returns the schema and auth requirements for a chosen operation.
- name: execute Tool
description: Executes an operation or workflow with managed credentials.
- name: list_credentials Resource
description: Lists the agent's available upstream credentials.
- aid: jentic:arazzo-engine
name: Arazzo Engine
humanURL: https://github.com/jentic/arazzo-engine
description: >-
Open-source Python engine that executes Arazzo workflow specifications alongside OpenAPI operation definitions.
Powers the Jentic platform's workflow execution and is also installable standalone as arazzo-runner for direct use
in agents and automation. Handles authentication resolution (API key, OAuth 2.0, basic, bearer), dynamic server
URL resolution, parameter chaining between steps, and blob storage for large binary payloads.
tags:
- Arazzo
- OpenAPI
- Workflows
- Open Source
properties:
- url: https://github.com/jentic/arazzo-engine
type: SourceCode
- url: https://docs.jentic.com/getting-started/arazzo-runner/
type: Documentation
- url: https://pypi.org/project/arazzo-runner/
type: PythonPackage
- aid: jentic:standard-agent
name: Jentic Standard Agent
humanURL: https://github.com/jentic/standard-agent
description: >-
Open-source composable reasoning agent framework that plans, acts, and recovers from failures, preconfigured with
Jentic tools and a ReWOO reasoning loop. Primary entry point is the ReWOOAgent Python class. Bring-your-own LLM
(Anthropic, OpenAI, Google). Demonstrates how to build an agent that uses Jentic's just-in-time tooling without
committing to a specific agent framework.
tags:
- Agent Framework
- ReWOO
- Open Source
- Python
properties:
- url: https://github.com/jentic/standard-agent
type: SourceCode
- url: https://docs.jentic.com/getting-started/standard-agent/
type: Documentation
- aid: jentic:jentic-mini
name: Jentic Mini
humanURL: https://github.com/jentic/jentic-mini
description: >-
Free, open-source, self-hosted API execution layer that sits between an agent and the outside world. The agent
says what it wants to do and Jentic Mini handles the how: finding the right API, injecting credentials at runtime,
and brokering the request. Intended for teams that want Jentic's execution model without sending traffic through
the hosted Jentic API.
tags:
- Self Hosted
- Open Source
- Agent Runtime
properties:
- url: https://github.com/jentic/jentic-mini
type: SourceCode
- aid: jentic:jairf
name: Jentic API AI-Readiness Framework (JAIRF)
humanURL: https://github.com/jentic/api-ai-readiness-framework
description: >-
Technical specification for evaluating how interpretable, operable, and trustworthy an API is for AI systems and
autonomous agents. Defines the signals, dimensions, scoring model, and normalization rules used by the Jentic API
Scorecard product. Apache 2.0.
tags:
- Specification
- API AI Readiness
- Open Source
properties:
- url: https://github.com/jentic/api-ai-readiness-framework
type: SourceCode
common:
- url: https://jentic.com/
name: Jentic
type: Website
- url: https://jentic.com/blog
name: Jentic Blog
type: Blog
- url: https://docs.jentic.com/
name: Jentic Documentation
type: Documentation
- url: https://jentic.com/pricing
name: Jentic Pricing
type: Pricing
- url: https://app.jentic.com/sign-up
name: Jentic Sign Up
type: SignUp
- url: https://app.jentic.com/
name: Jentic Console
type: Console
- url: https://jentic.com/contact
name: Jentic Contact
type: Contact
- url: https://jentic.com/company
name: About Jentic
type: About
- url: https://github.com/jentic
name: Jentic GitHub Organization
type: GitHubOrganization
- url: https://jentic.com/privacy
name: Jentic Privacy Policy
type: PrivacyPolicy
- url: https://jentic.com/terms
name: Jentic Terms of Service
type: TermsOfService
- url: https://www.linkedin.com/company/jentic
name: Jentic LinkedIn
type: LinkedIn
- url: https://youtube.com/@JenticAI
name: Jentic YouTube
type: YouTube
- url: https://docs.jentic.com/community/support/
name: Jentic Support
type: Support
- url: https://docs.jentic.com/community/faq/
name: Jentic FAQ
type: FAQ
- url: https://docs.jentic.com/community/security/
name: Jentic Security
type: Security
- url: https://docs.jentic.com/community/contributing/
name: Jentic Contributing
type: Contributing
- url: https://jentic.com/blog/press
name: Jentic Press
type: Press
- url: https://jentic.com/blog/feed.xml
name: Jentic Blog RSS Feed
type: BlogFeed
- url: https://pypi.org/project/jentic/
name: Jentic Python Package
type: PythonPackage
- url: https://pypi.org/project/arazzo-runner/
name: Arazzo Runner Python Package
type: PythonPackage
- url: vocabulary/jentic-vocabulary.yml
type: Vocabulary
- url: json-ld/jentic-context.jsonld
type: JSONLD
- url: json-schema/jentic-operation-schema.json
type: JSONSchema
- url: json-schema/jentic-agent-schema.json
type: JSONSchema
- url: json-schema/jentic-workflow-schema.json
type: JSONSchema
- name: Agent Skills
url: https://github.com/jentic/jentic-skills
type: AgentSkill
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com