展示HN：Decispher – 为编码智能体提供持久的工程上下文和记忆
你好，HN，
我是Ali，正在开发Decispher。
我们正在解决的问题是，编码代理反复发现工程组织内部已经存在的上下文信息。
一个开发者在开发某个功能时，可以结合之前的PR、Jira工单、Slack讨论、所有权边界、架构决策以及他们自己的经验。编码代理通常从一个提示和一个代码库开始，然后花费代币去搜索相同的上下文——或者完全错过它。
Decispher是一个为工程代理提供上下文和记忆的层。
它目前有三个部分：
1) 上下文引擎
工程上下文通常分散在不同的系统中。Decispher连接来自工程平台的记录，并将相关片段组合成代理可以检索的上下文单元，以便完成任务。
例如，关于某个组件的上下文可能包括之前的PR、相关问题、架构决策、所有权信息和实施历史。
我们还构建了Branch Story，它记录AI编码会话，并将其执行转化为PR上的结构化交接：
提示 → 计划 → 行动 → 结果。
2) 记忆层
记忆层在用户、团队和项目级别存储持久的上下文。
这包括工作偏好和工程惯例。团队还可以创建可重用的记忆集，例如前端、支付后端或项目特定的记忆集，并根据任务注入相关的记忆。
在LongMemEval中，我们当前的系统达到了：
a) 使用GPT-4.1-mini作为提取器和阅读器，在oracle分割上达到89%的准确率
b) 在LongMemEval -S数据集上达到81%（使用前沿模型时为89%）
c) 中位数代币减少38倍
我很乐意分享更多关于我们如何测量检索质量和代币减少的细节。
3) 工作代理
Decispher还拥有一个自主工作代理，在执行任务时使用上下文引擎和记忆层。
它可以从Jira和Slack等来源获取工作，检索相关的上下文和所有权信息，并在可用上下文不足时向相关人员询问，而不是猜测。这些答案随后可以作为未来工作的上下文。
上下文引擎、记忆层和工作代理可以独立使用。
设置
npx decispher init
这将连接一个代码库并配置代理集成。
npx decispher link
这将你的decispher账户链接到你的代码库。
Decispher与MCP兼容的代理一起工作，并为Claude、Codex、Grok Build和Cursor提供特定集成。我们还有一个VS Code/OpenVSX扩展，用于查看上下文和编写交接。
注意：
a) 上下文引擎不克隆源代码；它通过GitHub API读取和写入。
b) 工作代理使用一个隔离的沙箱，除了通过允许的代理外没有网络出口。
c) 工作沙箱在运行后被销毁。
d) 原始消息和文本在静止状态下被加密并自动清除。会话在合并后7天或最后活动后30天被清除，保留时间可配置。
我们还有一个MIT许可的开源项目，名为Decision Guardian，用于在PR上展示ADR上下文。
上下文引擎现在可以使用。记忆层和工作代理正在逐步推出。
我特别希望得到反馈，我们也在寻找设计合作伙伴。
欢迎提问。
Ali
这是我之前Show HN帖子的后续：
[https://news.ycombinator.com/item?id=48762112](https://news.ycombinator.com/item?id=48762112)
自那以来的主要新增功能包括记忆层、LongMemEval结果、工作代理沙箱和用于AI生成PR工作的Branch Story。
查看原文
Hello HN,<p>I'm Ali, building Decispher.<p>The problem we're working on is that coding agents repeatedly rediscover context that already exists inside an engineering organization.<p>A developer working on a feature can combine information from previous PRs, Jira tickets, Slack discussions, ownership boundaries, architectural decisions and their own experience. Coding agents usually start with a prompt and a repository, then spend tokens searching for that same context—or miss it entirely.<p>Decispher is a context and memory layer for engineering agents.<p>It currently has three parts:<p>1) Context Engine<p>Engineering context is usually fragmented across systems. Decispher connects records from engineering platforms and combines related fragments into context units that agents can retrieve for a task.<p>For example, context around a component might include previous PRs, related issues, architectural decisions, ownership information and implementation history.<p>We also built Branch Story, which records an AI coding session and turns its execution into a structured handoff on the PR:<p>Prompt → plan → actions → result.<p>2) Memory Plane<p>The Memory Plane stores persistent context at the user, team and project levels.<p>This includes working preferences and engineering conventions. Teams can also create reusable memory sets for example frontend, payments-backend, or project-specific sets and inject the relevant memory based on the task.<p>On LongMemEval, our current system reaches:<p>a) 89% accuracy on the oracle split using GPT-4.1-mini as extractor and reader
b) 81% on LongMemEval -S dataset (89% with frontier models)
c) 38× median token reduction<p>I'm happy to share more details about how we measure retrieval quality and token reduction.<p>3) Worker Agent<p>Decispher also has an autonomous worker agent that uses the Context Engine and Memory Plane while working on a task.<p>It can take work from sources such as Jira and Slack, retrieve relevant context and ownership information, and ask the humans involved when the available context is insufficient instead of guessing. Those answers can then become available as context for future work.<p>The Context Engine, Memory Plane and Worker Agent can be used independently.<p>Setup<p>npx decispher init<p>This connects a repository and configures the agent integration.<p>npx decispher link<p>This links your decispher account to your repo.<p>Decispher works with MCP compatible agents, with specific integrations for Claude, Codex, Grok Build and Cursor. We also have a VS Code/OpenVSX extension for viewing context and writing handoffs.<p>Notes:<p>a) The Context Engine does not clone source code; it reads and writes through the GitHub API.
b) The Worker Agent uses an isolated sandbox with no network route out except through an allowlisted proxy.
c) Worker sandboxes are destroyed after a run.
d) Raw messages and text are encrypted at rest and automatically purged. Sessions are currently purged 7 days after merge or 30 days after last activity, with configurable retention.<p>We also have an MIT-licensed open-source project called Decision Guardian for surfacing ADR context on PRs.<p>The Context Engine is available now. Memory and the Worker Agent are rolling out gradually.<p>I'm especially interested in feedback and we are also looking for design partners.<p>Happy to answer.<p>Ali<p>This is a follow-up to my previous Show HN post:<p><a href="https://news.ycombinator.com/item?id=48762112">https://news.ycombinator.com/item?id=48762112</a><p>The major additions since then are the Memory Plane, LongMemEval results, Worker Agent sandboxing and Branch Story for AI-generated work on PRs.