Aman Kumar
An OpenAI-compatible gateway operator specializing in LLM API gateway architecture and caching optimization practices.
Timeline (last 90 days)
A team of four—Aman Kumar, Rishu, Abhishek and Ayan—participated in the Graph Hacks hackathon co-hosted by WeMakeDevs and FalkorDB, chose the 'Agent Memory and Coordination' track, and built the RecallAI prototype in four days.
The author tested Mastra custom endpoint behavior against a local mock service under @mastra/core 1.78.0 + Node 20.19.2.
The author splits tests into two groups: the vast majority are unit tests (the client is replaced with a fake, runs in milliseconds, and does not touch the network) and a very small number of live smoke tests (actually access the endpoint, are skipped by default, and only check the response shape).
Original author Aman Kumar built an OpenAI-compatible API gateway.
All Facts (4)
The author tested Mastra custom endpoint behavior against a local mock service under @mastra/core 1.78.0 + Node 20.19.2.
50%UnverifiedThe author splits tests into two groups: the vast majority are unit tests (the client is replaced with a fake, runs in milliseconds, and does not touch the network) and a very small number of live smoke tests (actually access the endpoint, are skipped by default, and only check the response shape).
50%UnverifiedOriginal author Aman Kumar built an OpenAI-compatible API gateway.
50%UnverifiedA team of four—Aman Kumar, Rishu, Abhishek and Ayan—participated in the Graph Hacks hackathon co-hosted by WeMakeDevs and FalkorDB, chose the 'Agent Memory and Coordination' track, and built the RecallAI prototype in four days.
50%