Give your AI agents safe access to 10,000+ APIs
Building agents that call real APIs is painful. You end up hardcoding auth, juggling secrets in prompts, and writing glue code for every service. Jentic Mini is a self-hosted, open-source API execution layer that sits between your agent and the outside world. Your agent says what it wants to do. Jentic Mini finds the right API from a catalog of 10,000+, injects credentials at runtime, and brokers the request. Secrets never touch the agent.
Jentic Mini provides an encrypted local vault that stores API keys and OAuth tokens, injecting credentials at runtime so secrets never touch the agent. Supports 10,000+ APIs with toolkit-scoped permissions and per-agent killswitches for instant access revocation.
Jentic Mini includes basic simulate mode for testing agent workflows against production APIs without live execution. Paired with the broader Jentic platform's API Scorecard, developers can assess AI-readiness and validate integrations safely.
Jentic Mini is self-hosted and runs entirely in your own infrastructure as a single Docker instance with FastAPI server and SQLite backend. Apache 2.0 licensed and open source, eliminating vendor lock-in and enabling customization.
Jentic Mini provides access to 1,500+ public APIs and 2,000+ pre-built workflows defined in open standards (OpenAPI, Arazzo). Agents can dynamically discover, search, and execute workflows without hardcoding integration logic.
Jentic Mini uses toolkit-scoped permissions where each agent receives one toolkit key bundling specific credentials and access policies. Admins can instantly revoke any agent's access with a single killswitch without affecting others.