Greptile 发布 v5 审查 Agent,为每个 PR 启动子 Agent 混用开源与前沿模型
Greptile 的 v5 会在每个 PR 上开一堆子 Agent,开源模型和前沿模型一起跑,互相补盲区,审查更快更便宜,写代码的可以看看。
AI 代码审查公司 Greptile 推出 v5 Agent,在每个 PR 上自动生成多个子 Agent 并行执行首次代码审查。v5 将开源模型与前沿模型搭配使用,避免单一模型的盲区决定审查结果。Together AI 为其中开源模型提供推理支持,使审查返回速度更快、成本更低。
greptile wants to validate every piece of software on the planet
as more code gets written by ai, the first review pass needs to be independent + fast. greptile’s v5 agent spins up sub-agents on every pr, pairing open + frontier models so one model’s blind spots don’t decide what gets caught
together ai powers part of the inference behind those open models, helping reviews come back faster and at lower cost
watch how @greptile does it