Provides local-first long-term memory for AI agents using structured JSON or SQLite to maintain context across sessions.
別名 LuizEduPP/Rememb
- スター
- 5
- ツール
- —
- ダウンロード数(30日間)
- 636
- 最新バージョン
- 0.3.5
- 最終コミット
- 2026年11月2日
- ライセンス
- MIT
rememb MCPとは
Provides local-first long-term memory for AI agents using structured JSON or SQLite to maintain context across sessions.
プロジェクトのREADMEから生成された概要
rememb MCP server について
rememb provides a local-first long-term memory solution for AI agents to prevent context loss between different chat sessions. It allows developers and teams to store durable facts, decisions, and project architecture without relying on cloud services or external API keys. The system operates entirely on your local machine using either a structured JSON backend or a SQLite database for larger datasets.
Users can integrate the server into various IDEs and agents like Cursor, Claude, or VS Code using the MCP protocol. The setup process includes installing the package via pip and running the install command to apply memory rules and session hooks. It features eighteen specialized tools for managing memory, including rememb_write, rememb_edit, and rememb_search. A local web interface is also available for supervising memory, inspecting version history, and viewing statistics through a browser-based dashboard.
できること
- 1Maintain project contextAn AI agent can store technical stack details and architectural decisions to avoid repetitive explanations in new sessions.
- 2Retrieve specific informationDevelopers can instruct an agent to find relevant past information using keyword and token matching.
- 3Audit and restore changesYou can inspect the history of memory entries and revert to previous versions if an overwrite was incorrect.
- 4Manage per-project memoryYou can maintain separate memory stores for different code repositories using the project argument.
プロジェクトの README から作成されています。すべてのユースケースは、その引用と照らし合わせて確認されています。
rememb MCPのインストール方法
フォーマット検証日 2026年11月10日Cursor に追加Gooseに追加Claude Codeにrememb MCPをインストール
$ claude mcp add rememb -- uvx remembCursorにrememb MCPをインストール
~/.cursor/mcp.json
{
"mcpServers": {
"rememb": {
"command": "uvx",
"args": [
"rememb"
]
}
}
}VS Codeにrememb MCPをインストール
.vscode/mcp.json
{
"servers": {
"rememb": {
"type": "stdio",
"command": "uvx",
"args": [
"rememb"
]
}
}
}VS Code CLIにrememb MCPをインストール
$ code --add-mcp '{"name":"rememb","type":"stdio","command":"uvx","args":["rememb"]}'Claude Desktopにrememb MCPをインストール
claude_desktop_config.json
{
"mcpServers": {
"rememb": {
"command": "uvx",
"args": [
"rememb"
]
}
}
}Codexにrememb MCPをインストール
$ codex mcp add rememb -- uvx remembCodex config.tomlにrememb MCPをインストール
~/.codex/config.toml
[mcp_servers.rememb] command = "uvx" args = ["rememb"]
Gemini CLIにrememb MCPをインストール
$ gemini mcp add -s user rememb uvx -- remembGemini settings.jsonにrememb MCPをインストール
~/.gemini/settings.json
{
"mcpServers": {
"rememb": {
"command": "uvx",
"args": [
"rememb"
]
}
}
}自動チェック
実行日 2026年11月13日完全なレポート →自動チェックに合格しました。これはセキュリティ監査ではありません。コードを読み、サーバーに必要最小限のアクセス権を与えてください。 チェックの仕組み
- ソースリポジトリがリンクされており、アクセス可能luizedupp/rememb is public and reachablegithub.com/luizedupp/rememb ↗合格
- パッケージがこのリポジトリをソースとして指定rememb names luizedupp/rememb as sourcepypi.org/project/rememb/ ↗合格
- ビルドの来歴 (Sigstore 証明)No build attestation published for this release未チェック
- オープンソースライセンス (OSI)MITspdx.org/licenses/MIT.html ↗合格
- 過去1年以内にコミットまたはリリースありLast commit or release 2026-11-02github.com/luizedupp/rememb ↗合格
- OpenSSF Scorecard未チェック
- パッケージ名が有名なパッケージに酷似していないNo popular package one edit away from rememb合格
- パッケージおよびその依存関係に重大な勧告なし13 resolved dependencies checked; no critical advisoryosv.dev ↗合格
- モデルへの隠れた指示がない0 tool descriptions and the README read; no override phrases, credential paths or hidden characters合格
- 破壊的なツールがラベル付けされている未チェック
- リモートエンドポイントが MCP ハンドシェイクに応答未チェック
README
GitHubで見るOperate AI agents without losing context between sessions. rememb is local-first long-term memory: structured entries, keyword search, versioning, diff, restore, and audit trail — no cloud, no API keys.
The problem
Teams using agents at real velocity rarely fail because they lack generation. They fail because operating agents every day creates context debt:
- too much re-explaining project facts every session
- too little durable memory outside the chat window
- too little audit trail for why something changed
- too much noise when recalling the right context
Every team or solo developer operating agents professionally hits this wall:
Session 1: "We're using PostgreSQL, auth at src/auth/, prefer async patterns."
Session 2: Agent starts from zero. You explain everything again.
Session 3: Same thing.
Existing solutions often center on hosted memory layers, API keys, or opaque context pipelines. What you actually need is to resume the next session with the minimum correct context and a trail you can inspect.
rememb is built around four memory problems:
- durable facts and decisions instead of session-only chat memory
- keyword search instead of rereading everything (agents judge relevance)
- non-destructive versioning instead of silent overwrites
- local-first audit trail for AI work, not opaque cloud logs
Install
pip install rememb
Quick Start
With MCP (recommended)
1. Install the door, or add the MCP block by hand:
rememb install --apply --project
That writes the MCP server, Memory Rules, and SessionStart / PostToolUse / Stop hooks when the host has them (Cursor and Claude today). Without --apply it only prints the plan. --host limits the target; omit it to write every host rememb install knows (cursor, claude, codex, vscode, copilot, windsurf, continue, gemini, opencode, zed, cline).
Or add this to your IDE's MCP config and paste the rules from MCP_TOOLS.md:
{
"mcpServers": {
"rememb": {
"command": "rememb",
"args": ["mcp"]
}
}
}
Add repeatable --project /path/to/repo args for per-project stores alongside global ~/.rememb. Details: MCP_TOOLS.md.
2. Restart your IDE.
SessionStart injects recent entries, tags, and a short stats block. The agent writes durable memory when something changes, and searches only when targeted recall is needed.
No extra storage setup is required. In MCP mode, rememb auto-initializes ~/.rememb and optional --project stores on first use. Public tools: MCP_TOOLS.md (18 tools).
If you want multiple MCP clients on the same machine to reuse one already-running rememb process, start a persistent local SSE transport:
rememb mcp --transport sse --host 127.0.0.1 --port 8765
This keeps one MCP process alive, so repeated clients can connect through http://127.0.0.1:8765/sse and http://127.0.0.1:8765/messages/.
Do not put --transport sse inside a stdio MCP client config. stdio clients expect JSON-RPC on stdin/stdout; the SSE mode exposes an HTTP endpoint and must be started separately.
Local usage without MCP
rememb # Open the web UI (http://localhost:18181)
rememb --port 9000 # Custom port
How it works
~/.rememb/ ← default store location (MCP and Web UI)
entries.json ← default JSON backend (or entries.db with SQLite)
meta.json ← project metadata
config.json ← limits, sections, storage backend, UI paging
A local store on disk. Your agent can read prior decisions, search by keywords and tokens, update entries without losing history, and restore previous versions without depending on a cloud memory service. Copy ~/.rememb/ anywhere to move the store.
User: "We're using PostgreSQL, auth at src/auth/, async patterns"
Agent: [rememb_write] → Saved
[New session]
SessionStart injects recent + tags + stats (handoff first)
Agent: "I see you're using PostgreSQL with auth at src/auth/..."
Writes, edits, and deletes go through rememb_write, rememb_edit, and rememb_delete. Host hooks also write into actions via rememb hook post-tool / stop. For the full MCP surface, see MCP_TOOLS.md.
Search uses keyword and token matching over entry content and tags. rememb_search returns id, score, tags, date, and a short excerpt (search_excerpt_chars, default 160). Full body is rememb_get / rememb_read on the ids the agent picked, or max_chars=0 on search. The agent applies semantic relevance judgment. No API keys, no cloud, no embedding model download at runtime.
config.json is written during initialization with all supported knobs:
{
"max_content_length": 1000000,
"max_tag_length": 500,
"max_tags_per_entry": 100,
"max_entries": 100000,
"sections": ["project", "actions", "systems", "requests", "user", "context"],
"section_colors": {
"project": "#d84848",
"actions": "#d08020",
"systems": "#d4c430",
"requests": "#40c040",
"user": "#20d4c4",
"context": "#c060f0"
},
"entry_batch_size": 24,
"entry_load_threshold": 6,
"search_excerpt_chars": 160,
"storage_backend": "json"
}
Set storage_backend to sqlite for larger stores. The Web UI and MCP migrate existing JSON entries automatically when you switch backends.
entry_batch_size and entry_load_threshold control pagination in the web UI — how many cards load at once and when to trigger "load more".
Section names are normalized to lowercase, duplicates are ignored after normalization, and removing a section with existing entries automatically migrates those entries to uncategorized. meta.json is kept in sync with the current effective section list.
Older stores may still contain legacy embedding-related config keys; they are dropped the next time configuration is loaded or saved.
Memory sections
| Section | What to store |
|---|---|
project |
Tech stack, architecture, goals |
actions |
What was done, decisions made |
systems |
Services, modules, integrations |
requests |
User preferences, recurring asks |
user |
Name, style, expertise, preferences |
context |
Anything else relevant |
Web UI
rememb includes a local web interface for supervision — browse memory, inspect history, and tune runtime settings. The SPA has no create/edit/delete controls. The HTTP API still has write, delete, and restore routes.
rememb # Open the web UI (http://localhost:18181)
rememb --host 0.0.0.0 # Bind to all interfaces
rememb --port 9000 # Custom port
rememb --no-browser # Start server without opening the browser
Overview with entry totals and recent memory activity.
Stats with totals, section breakdown, date range, and recent entries.
Settings for limits, storage backend, section colors, and maintenance actions.
Skills browser for bundled agent skills included with rememb.
Views:
- Overview — entry totals, deleted count, store size, and recent memory
- Memory — browse, keyword search, filter by section, sort, and include deleted entries
- Stats — totals, backend, section bars, oldest/newest timestamps, and recent entries
- Settings — edit limits, storage backend, section colors, consolidate duplicates, and save runtime config
- Skills — browse bundled agent skills (61 skills shipped in the package)
Entry inspection from the UI includes version history and side-by-side diff. Entry mutations and restore are MCP (rememb_write, rememb_edit, rememb_delete, rememb_restore) or the HTTP API, not SPA controls.
CLI
rememb # Open the web UI (http://localhost:18181)
rememb --host 0.0.0.0 --port 18181 --no-browser # Custom bind, no auto-open
rememb mcp # Start MCP server over stdio
rememb mcp --transport sse --host 127.0.0.1 --port 8765 # One persistent local MCP process
rememb hook session-start # Inject recent + tags + stats
rememb hook post-tool # Write a PostToolUse event from stdin
rememb hook stop # Write a Stop/handoff entry from stdin
rememb install # Show MCP + rules + hooks plan
rememb install --apply --project # Write them for the current directory
rememb --version, -v # Show version
rememb --help, -h # Show help
Compatibility
The current compatibility surface is tracked explicitly in COMPATIBILITY.md.
Short version:
- Python 3.11 to 3.14 are covered by CI
- CLI contract and MCP tool schema (18 tools) have automated test coverage
- stdio MCP is the primary documented integration path
- SSE MCP is documented and partially tested at the route level
- release automation and Trusted Publishing are documented in RELEASE.md
Design
- Local first — plain JSON or SQLite on disk
- Portable — copy
~/.rememb/anywhere, it works - Agnostic — any agent, any IDE (MCP or CLI)
- No lock-in — no servers, no API keys, no accounts
Core capabilities:
- structured memory with sections and tags
- keyword search with agent-side relevance judgment (
rememb_searchis an index: id, score, excerpt; full body via get/read) - host door: SessionStart injects recent + tags + stats; PostToolUse / Stop write into
actions; Stop tagshandoffso the next host sees it first rememb installwrites MCP, Memory Rules, and hooks (hooks for Cursor and Claude)- non-destructive versioning, diff, restore, and soft delete
- duplicate consolidation (exact content) and store stats
- config and maintenance via Web UI (settings and consolidate; entry mutations via MCP or HTTP API)
- 61 bundled agent skills via Web UI and MCP
Contributing
git clone https://github.com/LuizEduPP/Rememb
cd Rememb
pip install -e ".[dev]"
PRs welcome. Issues welcome. Stars welcome. 🌟
License
MIT
rememb MCPのよくある質問
rememb MCPをClaude Codeに追加するには
ターミナルでclaude mcp add rememb -- uvx remembを実行します。すべてのプロジェクトで利用するには--scope userを追加します。
rememb MCPをCursorに追加するには
~/.cursor/mcp.jsonを開き、上記のインストールセクションに示すCursor設定を使ってmcpServersの下にサーバーを追加します。
Does rememb require an internet connection or API keys?
No, it is a local-first solution that requires no cloud services or API keys.
How can I use rememb with my IDE?
You can install it using the command 'rememb install --apply --project' to automatically configure MCP, Memory Rules, and hooks for supported hosts like Cursor and Claude.
Can I manage my memory entries through a visual interface?
Yes, rememb includes a local web UI for browsing memory, inspecting history, and tuning settings.
What storage formats are supported?
It supports a default JSON backend and can be switched to SQLite for larger stores.