Context7
Up-to-date docs for AI agents
제작자가 쓴 설명(영어 원문)
Session memory for AI coding agents. Search past sessions, extract rules, and track what works.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
ANTHROPIC_API_KEY, OPENAI_API_KEY비밀로 표시된 값은 내 계정의 열쇠예요. 절대 다른 사람과 공유하거나 채팅에 붙여 넣지 마세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"afterpaths": {
"command": "uvx",
"args": [
"afterpaths",
"afterpaths-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add afterpaths --env ANTHROPIC_API_KEY=your-value --env OPENAI_API_KEY=your-value -- uvx afterpaths afterpaths-mcp실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"afterpaths": {
"command": "uvx",
"args": [
"afterpaths",
"afterpaths-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"afterpaths": {
"type": "stdio",
"command": "uvx",
"args": [
"afterpaths",
"afterpaths-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
레지스트리 이름이 GitHub 계정 burnssa 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요
내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요
내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
입력해야 할 값: ANTHROPIC_API_KEY, OPENAI_API_KEY
내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.2.5)은 6개월 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Python (uv)도 있어야 해요.
같은 카테고리에는: Context7, Codebase Memory, Exa
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
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:
You're managing multiple agents - retaining critical context and learning from sessions is painful:
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.
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
pip install afterpaths
cd ~/code/your-project
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
export ANTHROPIC_API_KEY="sk-ant-..." ap summarize 1
ap rules
ap search "database schema" ap search "auth" --deep # also search raw transcripts
ap stats ap stats --daily
Tip:
apis the short alias forafterpaths. 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.
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/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.
| 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/ |
| 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.
| Tool | Status | Location |
|---|---|---|
| Claude Code | ✅ Ready | ~/.claude/projects/*.jsonl |
| Cursor | ⚠️ Partial | ~/Library/Application Support/Cursor/User/workspaceStorage/ |
| Codex CLI | ✅ Ready | ~/.codex/ |
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.
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]
claude mcp add afterpaths -- afterpaths-mcp
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.
.afterpaths/ excluded by defaultyour-project/
├── .afterpaths/ # Summaries (gitignored) │ ├── summaries/ │ └── meta.json ├── .claude/ │ └── rules/ # Generated rules (commit these!) │ ├── dead-ends.md │ ├── gotchas.md │ └── patterns.md └── src/
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)
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.
ap search)--json flag)MIT
*Manage your AI coding agents. Learn what works. Stop repeating mistakes.*