Skip to main content

afterthread

Keep the thread after the conversation ends.

afterthread 是一個 local-first 的個人知識延續工具,用來保存討論結束後最容易 蒸發的架構脈絡:決策、理由、替代方案、取捨、風險與下一步。主要介面是一個由 FastAPI、SQLite 與 React 組成的本機網頁應用;wheel 已內嵌完整前端,只需要一個 afterthread 指令即可啟動。

目前是早期版本,支援 Python 3.14,以及 Linux/macOS。Windows 尚未列入支援 範圍。

安裝與啟動

不需要常駐安裝,直接執行:

uvx afterthread

或安裝成固定指令:

uv tool install afterthread
# 或
pipx install afterthread

啟動後以瀏覽器開啟 http://127.0.0.1:8000。資料預設儲存在 $XDG_DATA_HOME/afterthread;未設定 XDG_DATA_HOME 時使用 ~/.local/share/afterthread。可用 afterthread --data-dir <path> 覆寫。

功能

  • 快速捕捉一個決策、調查主題或擱置工作。
  • 逐步補齊背景、理由、替代方案、後果、風險與下一步。
  • 以狀態、階段、標籤與關鍵字篩選,回顧陳舊或待補齊項目。
  • 選配 OpenAI-compatible LLM,提供結構化的 AI 捕捉、補齊與進度更新。
  • 讓 AI 依 OpenAPI 文件建立可呼叫外部 API 的本機工具。

本產品沒有聊天介面;AI 功能都是針對單一記憶項目的結構化操作。

AI 設定與隱私

手動新增、編輯、刪除、篩選與回顧不需要 LLM。若要啟用 AI 功能,請先執行 afterthread init-env 在資料目錄建立 .env 範本,再編輯以下設定:

OPENAI_BASE_URL=https://your-endpoint.example/v1
OPENAI_API_KEY=your-key-if-required
OPENAI_MODEL=your-model

記憶項目儲存在本機 SQLite;但使用 AI 功能時,正在處理的內容會傳送到你設定的 LLM endpoint。若 endpoint 是遠端服務,內容就會離開本機。

KB 工具安裝器能讓 AI 執行真實 bash 指令,而且沒有容器隔離。只應使用你信任的 OpenAPI 文件與安裝指示;完整威脅模型與設定參考請閱讀 afterthread 文件。

授權

MIT License。Copyright (c) 2026 birdhackor。

Metadata

Release files for afterthread 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for afterthread 0.4.0
File Size Uploaded
afterthread-0.4.0.tar.gz 565.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for afterthread 0.4.0
File Interpreter ABI Platform
afterthread-0.4.0-py3-none-any.whl Python 3 none any Details

Total release size: 1.1 MB

Release files / afterthread-0.4.0.tar.gz

Download URL afterthread-0.4.0.tar.gz
Size 565.7 kB
Tags Source
SHA-256 checksum
How to use checksums
09861b5f6925aaeba0f1cd36c6378e55ff5e8f0f263c23571c0678a446756ada
BLAKE2b-256 checksum
How to use checksums
5a076e466f9e365960bce14818f6ad7b64d54bae825a423bcee459343a138829
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 29, 2026.

Transparency log

Release files / afterthread-0.4.0-py3-none-any.whl

Download URL afterthread-0.4.0-py3-none-any.whl
Size 562.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b7a9ee6095c2bad549f8f91a80b2edc15c3c8f3de86772842cb4746ee380d304
BLAKE2b-256 checksum
How to use checksums
c8ed28bfed6a967adf52d000d3f0d331c4b0f39badfee00f9f897b5f2e226244
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 29, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.4.0 This release

2 release files

0.3.0

2 release files

0.2.0

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page