# Jentic One

> Jentic One is a self-hosted, open-source execution layer letting AI agents securely call real APIs without handling credentials.

- **Category:** AI Agents
- **Licence:** Apache-2.0
- **Latest version:** v0.44.0
- **Open source:** oss
- **Languages:** Typescript, Go, Python
- **Platforms:** Docker, Docker Compose, Helm, AWS, Build from Source, Systemd
- **Tags:** Mcp, Security, OAuth, Openapi, Ai Agents, Claude, Audit, Api Gateway, Openclaw, Permissions, Self Hosted, Codex, Agentic, Cursor, Agent Infrastructure, Openapi3, Policy, Least Privilege, Credential Manager, Arazzo, Agent Security, Credential Broker

## Description

Jentic One is a self-hosted platform that sits between AI agents and external APIs. Instead of giving agents API keys directly, operators register APIs and store credentials once in Jentic One. Agents then make calls through the Jentic Broker, which checks permissions, injects the appropriate credential at execution time, and records every request. The system deploys as two peer services — an App (control plane with UI, registry, auth, and admin) and a Broker (data plane that injects credentials) — backed by PostgreSQL or SQLite. It integrates with coding agents like Claude Code, Codex, and Cursor via a local MCP server or CLI, and supports OIDC for single sign-on. The project is in public beta (0.x releases) with schemas and CLI commands subject to change.

## Links

- [Homepage](https://github.com/jentic/jentic-one)
- [Website](https://jentic.com)
- [Docker](ghcr.io/jentic/jentic-one-app)
- [Documentation](https://docs.jentic.com)
- [GitHub Repository](https://github.com/jentic/jentic-one)
- [Discord Community](https://discord.gg/TdbWXZsUSm)
- [GitHub Discussions](https://github.com/jentic/jentic-one/discussions)
- [Twitter/X](https://x.com/jenticai)
- [LinkedIn](https://www.linkedin.com/company/jentic)
- [YouTube](https://youtube.com/@JenticAI)

---
Source: https://selfhost.directory/project/jentic-one