Kimi‑Dev logo

Kimi‑Dev

Kimi‑Dev AI Agent
Rating:
Rate it!

Overview

Open‑source coding LLM optimized for automated debugging and issue resolution tasks.

Kimi‑Dev (72B) is an open‑source coding language model by Moonshot AI, fine‑tuned via reinforcement learning to autonomously fix bugs and write tests, achieving state‑of‑the‑art SWE‑bench performance.

Autonomy level

84%

Reasoning: Kimi-Dev demonstrates high autonomy through its specialized coding capabilities including bug fixing, code generation, and unit test creation without requiring step-by-step user guidance. Its 128k-token memory capacity and reinforcement learning architecture enable independent handling of complex software engineering tasks, though it remains depend...

Comparisons


Custom Comparisons

Some of the use cases of Kimi‑Dev:

  • Automating code fixes and writing unit tests
  • Handling complex software engineering tasks across repositories
  • Deploying high‑performance open‑source LLMs via vLLM or Transformers
  • Researchers exploring RL‑based coding model training

Loading Community Opinions...

Pricing model:

Code access:

Popularity level: 36%

Kimi‑Dev Video:

Did you find this page useful?

Not useful
Could be better
Neutral
Useful
Loved it!