Afterpaths

Name: Afterpaths
Author: burnssa

作者：burnssa版本 0.2.5i★ –i在你的电脑上运行

注册名称io.github.burnssa/afterpaths

安装

概览

作者提供的说明（英文原文）

Session memory for AI coding agents. Search past sessions, extract rules, and track what works.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 搜索与 AI 记忆
你需要填写：ANTHROPIC_API_KEY, OPENAI_API_KEY

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： ANTHROPIC_API_KEY, OPENAI_API_KEY

标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。

你需要

PyPI已安装 Python 的 uv（用于 uvx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "afterpaths": {
      "command": "uvx",
      "args": [
        "afterpaths",
        "afterpaths-mcp"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add afterpaths --env ANTHROPIC_API_KEY=your-value --env OPENAI_API_KEY=your-value -- uvx afterpaths afterpaths-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "afterpaths": {
      "command": "uvx",
      "args": [
        "afterpaths",
        "afterpaths-mcp"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "afterpaths": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "afterpaths",
        "afterpaths-mcp"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

ANTHROPIC_API_KEY 机密 env
Anthropic API key for session summarization and rule extraction. Not required for search, list, show, or rules tools.
OPENAI_API_KEY 机密 env
OpenAI API key (alternative to Anthropic) for summarization.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 burnssa 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

星标数多于此分类中其他 7248 个服务器的 0%
发布到注册中心的时间比此分类中其他 7248 个服务器的 11% 更新
基础检查结果等于或优于此分类中其他 7248 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Afterpaths 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

你需要填写：ANTHROPIC_API_KEY, OPENAI_API_KEY

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（0.2.5）于6个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它？

同一分类中有：Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者：upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT今天更新

安装

Codebase Memory

作者：DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT20天前更新

安装

Exa

作者：exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT上个月更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Afterpaths

Smarter with every session, automatically.

Extract rules from what worked. Track what didn't. Find the best models for your stack.

You're running Claude Code, Cursor and Codex, but which model actually works best for your stack? What approaches lead to breakthroughs vs. expensive dead ends? How do you stop your agents from making the same mistakes?

Afterpaths gives you a single view across all your AI coding tools: compare what's working, capture discoveries as rules, and guide your agent team away from costly diversions.

What you're seeing:

`ap audit` — Overview of your sessions, models used, and rule status
`ap show 5 --raw` — Raw session transcript (the messy JSONL data, made readable)
`ap show 5` — LLM-generated summary extracting discoveries, dead ends, and decisions
`head .claude/rules/gotchas.md` — Rules automatically extracted and ready for Claude's next session

The Problem

You're managing multiple agents - retaining critical context and learning from sessions is painful:

Repeated mistakes — Your agents hit the same gotchas. Three weeks later, same dead end, same wasted tokens.
No cross-tool visibility — Is Opus actually better than Sonnet for your codebase? Is Cursor outperforming Claude Code? You're guessing.
Rules are tedious — After a costly diversion, the last thing you want is to write a CLAUDE.md rule. So you don't. And the knowledge evaporates.
Sessions vanish — Session content is obscurely logged and hard to extract. Then it's often auto-deleted after 30 days. That breakthrough architecture decision? Context gone.

Afterpaths captures sessions across tools, surfaces what's working, and generates rules automatically—so your agents learn from every session, and you retain all your rich session context.

How It Works

Your Sessions                      Afterpaths

─────────────── ────────────────────────────────────

Claude Code ──► ap log ──► Browse sessions across IDEs Cursor ap stats ──► Analytics: tokens, activity, errors Codex ap summarize──► Session summaries (what happened) ap rules ──► Rule files (what to remember) ap search ──► Find past discussions & discoveries │ ▼ .claude/rules/ · .cursor/rules/ │ ▼ Your next session is smarter

Quick Start

pip install afterpaths

Navigate to your project (rules are project-specific)

cd ~/code/your-project

Run audit to see what you have

ap audit

The audit shows your sessions across all tools, model performance, and whether you have rules set up. No API key needed.

From there, the recommended flow:

# 1. Browse sessions and find significant work

ap log

2. Summarize important sessions (requires API key)

export ANTHROPIC_API_KEY="sk-ant-..." ap summarize 1

3. Extract rules from summaries → .claude/rules/

ap rules

4. Search across past sessions

ap search "database schema" ap search "auth" --deep # also search raw transcripts

5. Track ongoing performance

ap stats ap stats --daily

Tip: ap is the short alias for afterpaths. Both work identically.

All commands support --json for structured output (e.g., ap log --json, ap show 1 --json, ap search "query" --json).

See docs/commands.md for the full command reference and recipes.

From Session to Rules

Real example: A bug causing 76 missing sessions became a rule that prevents the same mistake.

While building afterpaths, sessions for a project weren't showing up. The path (let's call it) /Users/Code/foo_bar was being decoded as /Users/Code/foo/bar. After investigation, we discovered Claude Code uses lossy path encoding—both / and _ become -.

The summary captured the discovery:

## Discoveries

Claude Code's path encoding is lossy: Project paths in ~/.claude/projects/ are encoded by replacing / with -, but underscores are ALSO converted to hyphens. Three different paths encode identically:
/Users/Code/foo_bar → -Users-Code-foo-bar
/Users/Code/foo-bar → -Users-Code-foo-bar
/Users/Code/foo/bar → -Users-Code-foo-bar

`ap rules` extracted it into `.claude/rules/gotchas.md`:

- **Claude Code lossy path encoding**: Claude Code encodes project paths by

replacing both / and _ with -, making them indistinguishable when decoding. When decoding, try underscore variants alongside hyphen variants at each greedy step, preferring longer segments (single directories) over nested paths. _Source: 91b1ffbc_

Next time Claude works on path decoding in this codebase, it already knows about the lossy encoding—no need to rediscover it.

Why Afterpaths

Without	With Afterpaths
Discover gotcha, forget to document it	`ap summarize` captures it with full context
Hit the same issue 3 weeks later	Rule in `.claude/rules/` prevents it
No idea what's working	`ap stats` shows tokens, sessions, error rates
Sessions scattered across IDEs	`ap log` unified view across Claude + Cursor
Learnings siloed per tool	Rules sync to `.claude/rules/` and `.cursor/rules/`

What Gets Extracted

Category	What it captures	Example
Dead Ends	Approaches that failed	"Don't use X because Y"
Decisions	Architectural choices	"We chose Redis over Postgres because..."
Gotchas	Non-obvious warnings	"Watch out for X when doing Y"
Patterns	Techniques that worked	"For X, use pattern Y"

Each rule includes source session references so you can trace back to the original context.

Supported Tools

Tool	Status	Location
Claude Code	✅ Ready	`~/.claude/projects/*.jsonl`
Cursor	⚠️ Partial	`~/Library/Application Support/Cursor/User/workspaceStorage/`
Codex CLI	✅ Ready	`~/.codex/`

Known Limitations

Cursor sessions: the adapter reads several known chat/composer formats from state.vscdb (including workbench.panel.aichat.view.aichat.chatdata, composer.composerData, and allComposers), but Cursor changes its storage schema often and some sessions will return Entries: 0 even when the state.vscdb file is present. When this happens, ap show --raw and the afterpaths_show_session MCP tool emit a warning rather than silently returning empty. The raw file is untouched — if you need that session, opening state.vscdb directly with sqlite3 will still work.

Tool provenance features (ap show --artifacts, commit tracing, file activity) only cover sessions whose entries the adapter can read.

MCP Server

Afterpaths includes an MCP server that puts session history directly into your agent's tool list. Instead of relying on agents to discover the CLI, the MCP server makes session search, summaries, and rules available as native tools.

# Install with MCP support

pip install afterpaths[mcp]

Add to Claude Code

claude mcp add afterpaths -- afterpaths-mcp

Or run directly

python -m afterpaths.mcp_server

Tools exposed:

Tool	Description
`afterpaths_list_sessions`	List recent sessions for context recovery
`afterpaths_show_session`	Read session summaries and transcripts
`afterpaths_show_artifacts`	Show artifacts ledger: files written/edited with provenance
`afterpaths_summarize`	Generate summaries for sessions
`afterpaths_search`	Search across past sessions (auto-escalates to transcripts on 0 summary hits)
`afterpaths_get_rules`	Get extracted rules (dead ends, decisions, etc.)

Once configured, agents can ask "have we seen this before?" or "what were the dead ends?" and get answers from your session history.

Privacy

All local — Summaries and rules stay in your project
Your API key — Uses your Anthropic/OpenAI key
Read-only — Never modifies your source code
Gitignored — .afterpaths/ excluded by default

Storage

your-project/

├── .afterpaths/ # Summaries (gitignored) │ ├── summaries/ │ └── meta.json ├── .claude/ │ └── rules/ # Generated rules (commit these!) │ ├── dead-ends.md │ ├── gotchas.md │ └── patterns.md └── src/

Hand-edited notes in rule files

Each rule file is split into a manual section (preserved across ap rules runs) and an auto section (regenerated each run):

# Gotchas: Things to Watch For

_Add project-specific notes here — preserved across ap rules runs._

Auto-generated by afterpaths distill | Updated: 2026-04-21 12:00

Sources: 3 session(s)

Rules

Some extracted rule: ... _Source: abc12345_

Put hand-curated rules or project-specific reminders between the manual:start / manual:end markers — they'll survive every ap rules run. Content *outside* those markers (and outside the recognized boilerplate) blocks the run as a safety check. Pass --force to overwrite anyway, or wrap the content in manual markers to preserve it.

If you're upgrading from an earlier version and your rule files contain only auto-generated content, markers are inserted automatically on the next ap rules run with an empty manual section — no action required.

Roadmap

Claude Code session parsing
Cursor session support
Session analytics (tokens, errors, daily trends)
LLM summarization
Automatic rule extraction
Multi-target export (Claude, Cursor)
Codex CLI support
Cross-session search (ap search)
JSON output (--json flag)
MCP server for agent integration
Semantic search across sessions
Benchmarking and productivity insights

License

MIT

*Manage your AI coding agents. Learn what works. Stop repeating mistakes.*

Afterpaths

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

需要你填写的值

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“搜索与 AI 记忆”中的其他服务器比较i

常见问题

替代选择

Context7

Codebase Memory

Exa

作者的 README

Afterpaths

The Problem

How It Works

Quick Start

Navigate to your project (rules are project-specific)

Run audit to see what you have

2. Summarize important sessions (requires API key)

3. Extract rules from summaries → .claude/rules/

4. Search across past sessions

5. Track ongoing performance

From Session to Rules

Why Afterpaths

What Gets Extracted

Supported Tools

Known Limitations

MCP Server

Add to Claude Code

Or run directly

Privacy

Storage

Hand-edited notes in rule files

Rules

Roadmap

License