ctx-memory
ctx-memory
LLM 코딩 에이전트(Claude Code, Codex, Gemini CLI, OpenCode)를 위한 영구 메모리입니다.
새 세션을 시작할 때 에이전트는 이미 지난번에 작업한 내용(내린 결정, 수정한 파일, 발생한 오류, 학습한 규칙 등)을 알고 있습니다. 클라우드도 없고, 텔레메트리도 없습니다. 모든 데이터는 ~/.ctx-memory/store.db의 로컬 SQLite 데이터베이스에 저장됩니다.
작동 방식
Session starts
│
Shell wrapper intercepts 'claude' (or codex/gemini/opencode)
│
MCP server starts alongside — injects prior context, exposes memory tools
│
During session: hooks fire on every tool call, messages buffered
│
Session ends (clean exit / Ctrl-C / crash)
│
Layer 1 → Layer 2 → Layer 3 pipeline runs
│
├── Layer 1: extract weighted messages, events, decisions, errors, keywords
├── Layer 2: compress to ≤500-token digest, store in DB
└── Layer 3: merge digest into project memory doc (markdown)
Next session: agent reads prior context automaticallyRelated MCP server: remem
설치
npm install -g ctx-memory
ctx-memory setup설정 마법사:
설치된 도구(
claude,codex,gemini,opencode)를 감지합니다.통합할 도구를 선택하라는 메시지를 표시합니다.
각 도구에 대한 후크 설정을 작성합니다.
~/.ctx-memory/bin/에 래퍼 심볼릭 링크를 생성합니다.~/.bashrc/~/.zshrc를 통해~/.ctx-memory/bin을 PATH에 추가합니다.
셸을 다시 시작하거나 source ~/.bashrc를 실행한 후, 평소처럼 도구를 사용하세요. 메모리는 자동으로 관리됩니다.
명령어
ctx-memory setup # interactive setup wizard
ctx-memory status # show configuration and stats
ctx-memory projects list # list all projects
ctx-memory projects show <name> # print full memory doc for a project
ctx-memory projects forget <name> # reset memory (keeps sessions)
ctx-memory projects forget <name> --hard # delete all sessions + dataMCP 서버
MCP 서버는 각 도구 세션과 함께 사이드카로 실행되며 6가지 도구를 제공합니다.
도구 | 설명 |
| 세션 종료 시 처리를 위해 대화 메시지를 버퍼링합니다 |
| 도구 호출 이벤트(파일 편집, bash 명령 등)를 기록합니다 |
| 의미론적 유사성 또는 키워드로 과거 세션을 검색합니다 |
| 전체 프로젝트 메모리 문서를 반환합니다 |
| 목표와 결과가 포함된 최근 세션 목록을 표시합니다 |
| 세션을 마무리하고 1단계 → 2단계 → 3단계 파이프라인을 실행합니다 |
Claude Code와 함께 MCP 서버를 독립적으로 사용하려면 ~/.claude/settings.json에 다음을 추가하세요:
{
"mcpServers": {
"ctx-memory": {
"command": "node",
"args": ["/path/to/ctx-memory/dist/src/mcp/index.js"]
}
}
}아키텍처
src/
cli/ — setup wizard, status, projects commands
db/ — SQLite schema + CRUD (projects, sessions, events, digests, memory)
layer1/ — pure message/event processing → weighted Layer1Output
layer2/ — digest compression to ≤500 tokens → Layer2Digest
layer3/ — merge digest into ProjectMemory markdown
mcp/ — MCP server (handlers + stdio entry point)
wrapper/ — shell wrapper (intercepts tool invocation, manages session lifecycle)
hooks/ — hook config writers for Claude / Gemini / OpenCode주요 제약 사항:
모든 1/2/3단계 함수는 순수 함수입니다(I/O 없음, 예외 발생 없음).
요약은 500토큰 미만으로 유지됩니다.
벡터 검색은
sqlite-vec(384차원)을 통해all-MiniLM-L6-v2임베딩을 사용합니다.단일 SQLite DB, WAL 모드, 외래 키 활성화.
개발
npm run build # tsc → dist/
npm run dev # tsc --watch
npm run test:run # vitest (single-shot, 476+ tests)
npm test # vitest (watch mode)DB 경로는 기본적으로 ~/.ctx-memory/store.db입니다. CTX_MEMORY_DB_PATH로 재정의할 수 있습니다.
라이선스
MIT
Available Tools
6 toolsend_sessionC
Signal session end — runs Layer 1→2→3 pipeline, stores digest, updates project memory.
Inputs: outcome (required), project_id (required), session_id (required), exit_code.
get_project_memoryC
Return the full project memory document (architecture, conventions, recent work, known issues).
Inputs: project_id.
list_sessionsC
List recent sessions for a project with their goals and outcomes.
Inputs: limit, project_id.
search_contextB
Search past sessions for context relevant to a query. Uses embedding similarity, falls back to keyword search.
Inputs: query (required), limit, project_id.
store_eventC
Record a tool call event (file edit, bash command, etc.) for the current session.
Inputs: tool (required), session_id (required), args, result, +1 more.
store_messageC
Buffer a conversation message for session-end processing.
Inputs: role (required), index (required), content (required), session_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: session lifecycle (end_session), memory retrieval (get_project_memory, list_sessions, search_context), and data recording (store_event, store_message). No overlap in functionality.
All tool names follow a consistent verb_noun pattern using snake_case, e.g., end_session, get_project_memory, store_event. The naming is predictable and uniform.
With 6 tools, the server covers core memory management operations without bloat. The count is well-scoped for the domain of session context and project memory.
The tool surface covers the full typical lifecycle: recording events/messages, searching and retrieving context, listing sessions, and finalizing sessions with memory updates. No obvious gaps.
Maintenance
Related MCP Connectors
Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Persistent memory for AI agents — shared .brain across Claude Code, Cursor & Codex
Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.
Related MCP Servers
- AlicenseBqualityBmaintenancePersistent, local memory for AI coding agents that learns how you work, not just what you said. Supports Claude Code, Codex CLI, Cursor, and any MCP client.79115 PyPI75MIT
- AlicenseAqualityAmaintenanceLocal-first persistent memory for Claude Code and OpenAI Codex CLI. A single Rust binary captures, distills, searches, and injects project memory across sessions via hooks, MCP, CLI, and localhost REST.1533MIT
- FlicenseNot gradedqualityCmaintenancePersistent, self-curating memory for coding agents. It enables local, zero-cost context recall through MCP tools with hybrid retrieval and autonomous consolidation.-
- FlicenseNot gradedqualityBmaintenancePersistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.1-