Kimi‑Dev
Open‑source coding LLM optimized for automated debugging and issue resolution tasks.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Kimi‑Dev, derived from its capabilities.
AIVSS 9.3 · Critical
View MAESTRO 7-layer threat model →Overview
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.
Key features
- bug fixing
- unit test generation
- reinforcement learning
- open‑source LLM
- code intelligence
Use cases
- 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