DSH Plugin HubDSH 插件市场
plastic-labs/honcho 预览 preview

plastic-labs/honcho

Plugin插件 ⭐ 7,451 AGPL-3.0 Memory & Knowledge记忆与知识库Models & Routing模型与路由

Memory library for building stateful agents

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

Honcho is open-source reasoning-first memory infrastructure built for stateful AI agents that track changing entities over time. It stores conversations and events, runs background reasoning to update entity representations, and lets developers query context, search results, or natural language insights for any LLM or agent framework. It supports integration with multiple popular coding agent platforms including DSH, Claude Code, Cursor, OpenCode, and Hermes, and works with any MCP-compatible client. Users can choose between the official managed service at api.honcho.dev, a local deployment via the CLI, or full self-hosting of the FastAPI backend.

The standard Honcho workflow follows four clear steps that fit into any existing agent development pipeline. First, developers store conversations, events, documents, or tool traces as messages attached to a specific session in a Honcho workspace. Next, Honcho processes the queued data in the background to update its representations of tracked peers, projects, and ideas. After processing, developers query for relevant context or insights before injecting the results directly into an LLM prompt or agent workflow. This tool serves both development teams building agentic products and individual users who want to add persistent memory to their coding agents.

This repository hosts the core FastAPI server logic for Honcho, with separate official SDKs for Python and TypeScript available via PyPI and npm respectively. A dedicated CLI tool is also published to PyPI, and new users can get a local stack running by installing the CLI and running honcho start --setup to complete initial configuration. The entire project is licensed under the AGPL-3.0 open-source license, and self-hosters can deploy using Docker Compose or a local development environment. All external pull requests must link to a maintainer-approved issue, and the project does not operate a public bug bounty program.

Honcho是一套面向智能体的推理优先持久化记忆基础设施，核心能力是存储对话与事件后，在后台自动推理更新用户、项目、想法等实体的长期表征，支持开发者从中查询会话上下文、混合搜索结果或自然语言洞察。它可集成到多种编码智能体平台中，除DeepSeek Harness外，还兼容Claude Code、Cursor、OpenCode、Hermes等常见智能体客户端，支持MCP协议接入，提供官方托管、本地运行、自托管三种部署选项。

典型工作流分为四个标准步骤，开发者首先将对话、事件、文档或工具调用痕迹存储到Honcho的对应会话中，再由Honcho在后台异步处理队列更新各类实体的表征，随后通过自然语言查询接口或低延迟静态表征端点获取所需上下文，最后将结果注入到任意LLM调用或自定义智能体框架中。它主要面向需要为智能体添加长期状态记忆的开发团队，也适合想要给自己常用的编码智能体添加持久化记忆的个人用户。

本项目采用AGPL-3.0开源许可，核心服务基于FastAPI构建，提供Python和TypeScript官方SDK，同时提供可通过PyPI安装的命令行工具，本地运行可直接安装CLI后执行honcho start --setup完成初始化。自托管可使用Docker Compose或本地开发环境部署，贡献代码需提交关联了维护者批准标签议题的拉取请求，项目不提供漏洞赏金计划。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：honcho（plastic-labs/honcho）
仓库：https://github.com/plastic-labs/honcho
本站详情页：https://www.yhbd.top/plugins/plastic-labs-honcho/
本站登记：类型 plugin · 归类 多平台兼容工具（非 DSH 原生） · 许可证 AGPL-3.0 · ⭐ 7451 · 最近提交 2026-10-02 · 主语言 Python · 未检测到 DSH 插件清单

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单：可能只是打了 dsh-plugin 话题，安装方式要现场确认
  • Not DSH-native: a multi-platform tool that may require Node / Electron or another runtime first非 DSH 原生，是多平台兼容工具：可能要先装 Node / Electron 等运行时
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add @honcho-ai/dsh-honcho

把 plastic-labs/honcho 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

33.5 KB · 缓存于 2026-10-01 22:09:23 · 33.5 KB
Honcho

Static Badge PyPI version NPM version CLI Discord

Honcho is memory infrastructure for building stateful agents that understand changing people, agents, groups, projects, and ideas over time.

Store messages and events, let Honcho reason in the background, then query peer representations, session context, search results, or natural-language insights from any model or framework. Use it managed at api.honcho.dev, run a local stack with honcho start, or self-host the FastAPI server yourself.

Using Honcho as your memory system will earn your agents higher retention, more trust, and help you build data moats to out-compete incumbents.

Honcho has defined the Pareto Frontier of Agent Memory. Watch the video, check out our evals page, and read the blog post for more detail.

Contents

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 plastic-labs/honcho 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev skill 下一个 Next dsh-routing-suite →