返回 2026-08-18 编辑版
发现与解读中文优先 · EN 原文AI 产品

Subham Kundu 发布:GitNexus 给 Coding Agent 提供代码库知识图谱

今天我们推出@akonlabs支持@ycombinator我们建造GitNexus,您的存储库的开源知识图。编码代理查询它以准确获取任务所需的符号、调用路径、依赖项的上下文,而不是四处查找并将一半代码库填充到上下文窗口中。上下文是编码代理的瓶颈。更大的窗户还没有解决这个问题。代理的购买者为每个token支付更多费用以获得更差的代码,并且代理本身没有他们正在编辑的存储库的地图。我们正在解决这个问题。在DeepSWE,与相同的代理GitNexus与没有相比: 1. 37% → 68.4% 的任务通过 2. 每次修复成本减半 3. 在最困难的任务上,差距增加了三倍多 一个堆栈:知识图谱、编码代理、自动化PR审查。托管、自托管或气隙式。 45kGitHub星星。每周 65,000 次 npm 下载。 10+ 企业部署。注册:https://app.akonlabs.com

查看英文原文

Today we're launching @akonlabs backed by @ycombinator We build GitNexus, an open-source knowledge graph for your repository. Coding agents query it to get exactly the context a task needs symbols, call paths, dependencies instead of grepping around and stuffing half your codebase into a context window. Context is the bottleneck for coding agents. Bigger windows haven't fixed it. Buyers of agents are paying more per token to get worse code, and the agents themselves have no map of the repo they're editing. We're fixing this. On DeepSWE, the same agent with GitNexus vs. without: 1. 37% → 68.4% of tasks passed 2. Half the cost per fix 3. On the hardest tasks, the gap more than triples One stack: knowledge graph, coding agent, automated PR review. Managed, self-hosted, or air-gapped. 45k GitHub stars. 65k weekly npm downloads. 10+ enterprise deployments. Sign up at: https://app.akonlabs.com

Today we're launching @akonlabs backed by @ycombinator We build GitNexus, an open-source knowledge graph for your repository. Coding agents query it to get exactly the context a task needs symbols, call paths, dependencies instead of grepping around and stuffing half your codebase into a context window. Context is the bottleneck for coding agents. Bigger windows haven't fixed it. Buyers of agents are paying more per token to get worse code, and the agents themselves have no map of the repo they're editing. We're fixing this. On DeepSWE, the same agent with GitNexus vs. without: 1. 37% → 68.4% of tasks passed 2. Half the cost per fix 3. On the hardest tasks, the gap more than triples One stack: knowledge graph, coding agent, automated PR review. Managed, self-hosted, or air-gapped. 45k GitHub stars. 65k weekly npm downloads. 10+ enterprise deployments. Sign up at: https://app.akonlabs.com

上下文不再只靠加长窗口:知识图、压缩层和结构化区域开始各自承重

为什么值得看

上下文工程正在从提示技巧变成独立基础设施。团队需要分别回答模型该看什么、重复输出怎样压缩、token 花在哪里,以及长期任务如何保持结构,而不是只购买更大的窗口。

最强反方

GitNexus 的任务通过率与成本改善、Codag 的约 3 倍 token 降幅和组织采用数均来自发布方;Leviath 是作者提交的项目页。现有材料证明产品方向活跃,不能形成统一效果排名。

原始出现与传播对照

1 条出现 · 本次 AIHOT 未精确命中

发现与解读

今天我们推出@akonlabs支持@ycombinator我们建造GitNexus,您的存储库的开源知识图。

今天我们推出@akonlabs支持@ycombinator我们建造GitNexus,您的存储库的开源知识图。编码代理查询它以准确获取任务所需的符号、调用路径、依赖项的上下文,而不是四处查找并将一半代码库填充到上下文窗口中。上下文是编码代理的瓶颈。更大的窗户还没有解决这个问题。代理的购买者为每个token支付更多费用以获得更差的代码,并且代理本身没有他们正在编辑的存储库的地图。我们正在解决这个问题。在DeepSWE,与相同的代理GitNexus与没有相比: 1. 37% → 68.4% 的任务通过 2. 每次修复成本减半 3. 在最困难的任务上,差距增加了三倍多 一个堆栈:知识图谱、编码代理、自动化PR审查。托管、自托管或气隙式。 45kGitHub星星。

查看英文原文

Today we're launching @akonlabs backed by @ycombinator We build GitNexus, an open-source knowledge graph for your repository. Coding agents query it to get exactly the context a task needs symbols, call paths, dependencies instead of grepping around and stuffing half your codebase into a context window. Context is the bottleneck for coding agents. Bigger windows haven't fixed it. Buyers of agents are paying more per token to get worse code, and the agents themselves have no map of the repo they're editing. We're fixing this. On DeepSWE, the same agent with GitNexus vs. without: 1. 37% → 68.4% of tasks passed 2. Half the cost per fix 3. On the hardest tasks, the gap more than triples One stack: knowledge graph, coding agent, automated PR review. Managed, self-hosted, or air-gapped. 45k GitHub stars. 65k weekly npm downloads. 10+ enterprise deployments. Sign up at: https://app.akonlabs.com

Today we're launching @akonlabs backed by @ycombinator We build GitNexus, an open-source knowledge graph for your repository. Coding agents query it to get exactly the context a task needs symbols, call paths, dependencies instead of grepping around and stuffing half your codebase into a context window. Context is the bottleneck for coding agents. Bigger windows haven't fixed it. Buyers of agents are paying more per token to get worse code, and the agents themselves have no map of the repo they're editing. We're fixing this. On DeepSWE, the same agent with GitNexus vs. without: 1. 37% → 68.4% of tasks passed 2. Half the cost per fix 3. On the hardest tasks, the gap more than triples One stack: knowledge graph, coding agent, automated PR review. Managed, self-hosted, or air-gapped. 45k GitHub stars. 65k weekly npm downloads. 10+ enterprise deployments. Sign up at: https://app.akonlabs.com

直接发布标题Subham Kundu@subhamCenrax打开该层出处 ↗

Today we're launching @akonlabs backed by @ycombinator We build GitNexus, an open-source knowledge graph for your repository. Coding agents query it to get exactly the context a task needs symbols, call paths, dependencies instead of grepping around and stuffing half your codebase into a context window. Context is the bottleneck for coding agents. Bigger windows haven't fixed it. Buyers of agents are paying more per token to get worse code, and the agents themselves have no map of the repo they're editing. We're fixing this. On DeepSWE, the same agent with GitNexus vs. without: 1. 37% → 68.4% of tasks passed 2. Half the cost per fix 3. On the hardest tasks, the gap more than triples One stack: knowledge graph, coding agent, automated PR review. Managed, self-hosted, or air-gapped. 45k GitHub stars. 65k weekly npm downloads. 10+ enterprise deployments. Sign up at: https://app.akonlabs.com

来源
X @ycombinator · x-ycombinator
证据角色
x_project_network
时间状态
known
用户判决
未判
查看该来源原文raw/x-ycombinator.json456f7ad15e343498ae9ba68155f36302654d2db5ffc7c9ab0dc22168995f2ead
Cluster IDevt_13b1a9afa5effad5dc890c32精确去重依据canonical_url事件状态未判