Skip to main content

HeroPen — AI Agent Long-term Memory System

Project description

heropen

给本地大模型 Agent 装上长期记忆。一次 pip install,不用每次从头教。

你的 agent 每次开新会话都要重新交代一遍——项目怎么组织的、习惯用什么工具、之前踩过的坑、写好的配置和 skill。heropen 就是解决这个的:装完以后,agent 自己记得住。

数据 100% 在你自己的机器上,SQLite + 向量搜索,不联网、不上云。

安装

pip install heropen
heropen auto-setup

两行搞定。会装好数据库、自动检测你的 agent(Claude Code / Cursor / Windsurf 等),配好 MCP。

装完重启 agent,它就有记忆了。

如果你用 heropen install 可以走交互式向导手动选择。

快速开始

# 存一条记忆
heropen add "项目用 FastAPI + SQLAlchemy,测试走 pytest"

# 搜索之前记过的
heropen search "项目技术栈"

# 查看状态
heropen status

接入 Agent(MCP 协议)

主流 agent 工具都能接。heropen auto-setup 会自动检测并配置。

也可以手动配,在 agent 的配置里加上:

{
  "mcpServers": {
    "heropen": {
      "command": "heropen",
      "args": ["mcp"]
    }
  }
}

重启 agent,它就有记忆了。

接上 MCP 之后,agent 甚至可以自己在干活过程中自动存和查——遇到一个坑记下来,下次另一个会话里遇到同样问题,自己翻出来。

为什么是 heropen

heropen 免费版 其他方案
记忆条数 不限 通常有限制
搜索次数 不限 按量收费
联网 不需要 必须联网
数据在哪 你的机器 别人的服务器
安装 pip install 一行 搭服务、配环境

免费版就是全部核心,不阉割。

支持

协议

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

heropen-1.4.7.tar.gz (43.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

heropen-1.4.7-py3-none-any.whl (48.9 kB view details)

Uploaded Python 3

File details

Details for the file heropen-1.4.7.tar.gz.

File metadata

  • Download URL: heropen-1.4.7.tar.gz
  • Upload date:
  • Size: 43.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.17 {"installer":{"name":"uv","version":"0.11.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for heropen-1.4.7.tar.gz
Algorithm Hash digest
SHA256 79cfe0fba244ad9fc9ba51566e4b8aaf1af8d174496353aec045086cae4bbcd6
MD5 a7354b31b8d3b5bbd2d0be3af6d413a5
BLAKE2b-256 fdeaf3d673304b93da607b10034893a5e0d4e0d49a3db5b6838f8f2711e0f955

See more details on using hashes here.

File details

Details for the file heropen-1.4.7-py3-none-any.whl.

File metadata

  • Download URL: heropen-1.4.7-py3-none-any.whl
  • Upload date:
  • Size: 48.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.17 {"installer":{"name":"uv","version":"0.11.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for heropen-1.4.7-py3-none-any.whl
Algorithm Hash digest
SHA256 1d8bf693ee083add3cac5ce0e961fd638d037ff685e328f5899481164cf1137d
MD5 fc0cab09843ddac3d3d1cabc60771a11
BLAKE2b-256 c6865cc0eb2fd977aaa45bcbed8911639e6f4709ac92548e54c7eb79666ec124

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page