Context7
Up-to-date docs for AI agents
제작자가 쓴 설명(영어 원문)
Session checkpoint & recovery for Claude Code: resume, search, tag, and export recorded sessions.
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.
CLAUDE_REPLAY_DB필요한 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": {
"claude-replay": {
"command": "uvx",
"args": [
"claude-replay",
"mcp"
],
"env": {
"CLAUDE_REPLAY_DB": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add claude-replay --env CLAUDE_REPLAY_DB=your-value -- uvx claude-replay mcp실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"claude-replay": {
"command": "uvx",
"args": [
"claude-replay",
"mcp"
],
"env": {
"CLAUDE_REPLAY_DB": "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": {
"claude-replay": {
"type": "stdio",
"command": "uvx",
"args": [
"claude-replay",
"mcp"
],
"env": {
"CLAUDE_REPLAY_DB": "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.
CLAUDE_REPLAY_DB env이 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 constripacity 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.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
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(0.4.3)은 3개월 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.
The observability layer for Claude Code sessions — search, analytics, and visualization across every project.
Claude Code's --resume/--continue and /rewind recover *the session you're in*. Claude Replay does the part they don't: it hooks passively into every session, records what happened to a local SQLite store, and makes every past session — across every project — searchable, comparable, measurable, and exportable. Full-text search, per-session insight metrics, death-cause classification (*why* a session ended), session diffing, a web dashboard, and a terminal UI — none of which Claude Code has natively.
Claude Code session
| hooks (PreToolUse · PostToolUse · Stop) | v ~/.claude-replay/sessions.db ← events + checkpoints | +----+--------------------+ | | | MCP tools Dashboard TUI (resume) :8766 (browse)
Passive hooks write. MCP tools, the web dashboard, and the terminal UI read. Nothing leaves your machine.
Claude Replay is additive — it layers on top of the built-ins, it doesn't replace them.
| You want to… | Use |
|---|---|
| Resume / continue the current session | Native claude --continue, --resume |
| Undo file + conversation changes in a session | Native /rewind |
| Search every past session by content, tool, or outcome | Replay search |
| See *why* a session ended + per-session metrics | Replay status / replay_insights |
| Compare two runs side by side | Replay diff |
| Visualize a session timeline / browse all projects | Replay dashboard + TUI |
| Export a session as HTML / JSON / Markdown | Replay export --format |
Think of native resume/rewind as *recovery*, and Replay as *observability* over your whole history.
Passive hooks write to SQLite. MCP tools read from SQLite. Dashboard + TUI visualize SQLite. That's the whole system.
| Layer | File | Role |
|---|---|---|
| Store | claude_replay/store.py | All DB access — sessions, events, checkpoints |
| Hooks | claude_replay/hooks.py | Record tool calls + auto-checkpoint, dispatched by claude-replay hook |
| Recovery | claude_replay/resume.py | Generate a resume brief from a session |
| Export | claude_replay/export.py | Render a session as a self-contained HTML trace |
| Server | claude_replay/server.py | Starlette app — MCP SSE + JSON API + static dashboard |
| TUI | claude_replay/tui.py + tui_client.py | Textual session browser over the JSON API |
| CLI | claude_replay/cli.py | Every subcommand |
Port 8766 deliberately one above Claude Bridge's 8765, so the two siblings can run side by side without colliding.
pip install claude-replay
Or from a clone if you'd like to hack on it:
git clone https://github.com/constripacity/Claude-Replay.git
cd Claude-Replay pip install -e .[dev] # editable install with test/lint deps pip install -e .[tui] # add the terminal UI deps (textual, httpx)
If
pip install -efails on your environment (a known hatchling editable-install quirk on some setups), install the deps directly instead:
pip install mcp starlette uvicorn anyio textual httpx.
This wires Replay into Claude Code by merging three hooks into ~/.claude/settings.json. It's idempotent and leaves any other tools' hooks untouched.
claude-replay install
✓ Installed Claude Replay hooks into ~/.claude/settings.json
PreToolUse → claude-replay hook pre-tool PostToolUse → claude-replay hook post-tool Stop → claude-replay hook stop
From now on, every Claude Code session is recorded automatically. Remove the hooks any time with claude-replay uninstall (it removes only Replay's hooks).
Confirm it's actually wired up — the one check that matters:
claude-replay doctor
Claude Replay — doctor
✓ Hooks installed: PreToolUse / PostToolUse / Stop are in settings.json ✓ Hook command on PATH: claude-replay → …/claude-replay ✓ Database: ~/.claude-replay/sessions.db ✓ Sessions recorded: 3 sessions; most recent 5m ago
All good — Replay is installed and recording. ✓
If doctor warns that claude-replay isn't on PATH, the hooks can't run and nothing is recorded — put your install directory on PATH and re-run it.
claude-replay serve # defaults: 127.0.0.1:8766
claude-replay serve --port 9000 # custom port claude-replay serve --host 0.0.0.0 # bind all interfaces
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Claude Replay — Session checkpoint & recovery server Version: 0.4.1 DB: ~/.claude-replay/sessions.db http://localhost:8766/ ← Dashboard http://localhost:8766/sse ← MCP config http://localhost:8766/api/state ← JSON state http://localhost:8766/status ← Health check ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
So a running Claude Code session can call replay_resume, replay_checkpoint, etc. directly. Two ways:
SSE (alongside the dashboard — needs claude-replay serve running):
claude mcp add --transport sse -s user claude-replay http://localhost:8766/sse
stdio (no server process — the client launches Replay on demand):
claude mcp add -s user claude-replay -- claude-replay mcp
Verify with claude mcp list claude-replay should show ✓ Connected. Inside an already-running session, type /mcp to re-handshake.
# What's the state of the last session?
claude-replay status
claude-replay resume claude-replay resume
claude-replay tui # needs claude-replay serve running
claude-replay export # → ~/.claude-replay/exports/ .html
Paste the resume output into a fresh Claude Code session and it picks up where the dead one left off objective, what was done, what's next, and which files were touched.
Every connected Claude Code session gets these ten tools:
| Tool | Description |
|---|---|
replay_status | Current session summary objective, status, how it ended, event/checkpoint counts, last activity |
replay_checkpoint | Force a checkpoint of the current session now, with an optional note |
replay_resume | Generate a structured resume brief for a session (default: most recent) |
replay_sessions | List recent sessions with status, model, duration, checkpoint count |
replay_insights | Per-session metrics: how it ended, duration, tool calls, error rate, files touched, top tools |
replay_stats | Cross-session analytics: tool calls, error rate, why sessions end, tool mix, per-project rollups |
replay_search | Full-text search across sessions with filters (tool, cause, date, project), ranked by match count |
replay_diff | Compare two sessions: metric deltas + which files each touched |
replay_tag | Name a session and add/remove tags for later retrieval |
replay_export | Render a session as a self-contained trace (html / json / md) and return the path |
| Command | What it does | ||
|---|---|---|---|
claude-replay install | Merge Replay's hooks into ~/.claude/settings.json (idempotent) | ||
claude-replay uninstall | Remove only Replay's hooks | ||
claude-replay status | Current/last session at a glance, with insight metrics | ||
claude-replay sessions [--limit N] | List recent sessions (with names + tags) | ||
claude-replay search [--tool T] [--cause C] [--since 7d] [--project P] | Full-text search with filters (omit query to browse by filter) | ||
claude-replay diff | Compare two sessions side by side | ||
claude-replay resume [session_id] | Print a resume brief (default: most recent) | ||
| `claude-replay export [session_id] [--output DIR] [--format html\ | json\ | md]` | Render a trace |
claude-replay tag [session_id] [--name N] [--add a,b] [--remove c] [--clear] | Name or tag a session | ||
claude-replay prune [--older-than 30d] [--yes] | Delete sessions with no recent activity (destructive) | ||
claude-replay serve [--host H] [--port P] | Start the MCP + dashboard server (port 8766) | ||
claude-replay mcp | Serve the MCP tools over stdio (for uvx claude-replay mcp / MCP clients) | ||
claude-replay tui [--url URL] | Launch the terminal session browser | ||
claude-replay reset [--yes] | Delete all recorded sessions (destructive) | ||
claude-replay hook | Internal — invoked by Claude Code's hooks |
Web dashboard (claude-replay serve, then open http://localhost:8766/) a vanilla-JS view that polls every 2 s: session list (with how-it-ended badge + tags), a live search box, per-session timeline, and one-click "Copy Resume Brief" / "Export HTML". No CDN, no build step.
Terminal UI (claude-replay tui) a Textual browser in the same dark theme. A session sidebar, a live event feed, and a detail inspector showing how the session ended, its tags, the latest checkpoint, and files touched. Keys:
↑↓ navigate Tab switch panel Space pause
r resume (copies the brief to your clipboard) e export HTML trace ? help q quit
The TUI talks to the server over HTTP start claude-replay serve first (defaults to http://127.0.0.1:8766; point elsewhere with --url).
| Env var | Default | Purpose |
|---|---|---|
CLAUDE_REPLAY_DB | ~/.claude-replay/sessions.db | SQLite store location |
CLAUDE_SESSION_ID / CLAUDE_CODE_SESSION_ID | — | Session identity (Claude Code sets this in the hook payload); falls back to these env vars, then to a hash of the project dir |
CLAUDE_REPLAY_CORS_ORIGIN | localhost only | Comma-separated extra CORS origins for the server |
CLAUDE_REPLAY_NO_DASHBOARD | — | Set to disable the static dashboard mount (MCP/JSON only) |
The hook path is offline-first by design: it makes no network calls and completes in well under 50 ms just the one SQLite write. Large tool payloads are truncated at 8 KB per event so the DB stays lean.
pip install -e .[dev] # or install deps directly (see install note)
python -m pytest # full suite ruff check .
Tests use an isolated tmp_path SQLite database (the fresh_db fixture) — they never touch your real ~/.claude-replay/sessions.db. See CONTRIBUTING.md for the scope and the coding rules.
MIT see LICENSE.
Sibling to Claude Bridge. Built under the Constripacity banner.