CodePrep ships open-source AI mock interviewer

// 59d agoOPENSOURCE RELEASE

CodePrep ships open-source AI mock interviewer

ANNOUNCEMENT PRODUCT GITHUB PRODUCT HUNT

CodePrep is an open-source Python app that simulates coding interviews with an AI interviewer, built-in code execution, voice mode, and structured feedback. It ships 132+ real-world problems and keeps sessions, history, and code local, with OpenAI handling only the messages and code you send.

// ANALYSIS

CodePrep’s real strength is the feedback loop, not the problem count. It makes candidates explain, code, get pushed back on, and receive a debrief that feels much closer to a real screen than a LeetCode clone.

–Voice mode trains the communication layer most prep tools ignore.
–The scenario-based problem library is better practice for real interviews than random puzzle grinding.
–Open source and local-first storage make the tool easier to audit, tweak, or self-host.
–The tradeoff is real: it still needs a paid OpenAI API key, and the runtime is Python-only.

// TAGS

codeprepopen-sourceai-codingllmspeechtesting

DISCOVERED

59d ago

2026-03-29

PUBLISHED

59d ago

2026-03-29

RELEVANCE

8/ 10

AUTHOR

[REDACTED]

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE58m ago

Grok Build widens access, adds subagents

xAI’s Grok Build is an early-beta terminal coding agent with plan-review-approve flows, parallel subagents, worktree isolation, and support for plugins, hooks, skills, and MCP. The latest improvements make it feel less like a demo and more like xAI’s bid to compete seriously in the AI coding CLI race.

MODEL1h ago

Krea 2 lands on Replicate

Krea 2 is now available on Replicate, giving developers access to Krea's style-first image model outside the Krea app. It emphasizes aesthetic diversity, style control, and reference-driven creative workflows.

MODEL1h ago

ElevenLabs launches Music v2 for creators

ElevenLabs has released Music v2, a new music generation model that improves vocals, instrumentation, arrangement, and multilingual output. The model supports longer, section-by-section composition, inpainting to regenerate specific parts of a track, and more complex shifts within a song without losing coherence. It powers ElevenMusic and ElevenCreative now, with ElevenAPI access coming soon, and is trained on licensed data for commercial use.