Claude Soul
Claude Code forgets everything between sessions. Claude Soul doesn't.
npx claude-soul init --starter
에이전트 강화
게시자가 제공하는 설치 방식입니다. PlugMCP 엔드포인트가 아닙니다.
원격 URL인가요, 내 컴퓨터에서 실행하는 명령인가요? 두 설치 방식의 차이
PlugMCP에서 실행
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
실행One command. No API key, no cloud, everything local.
Prerequisites: Node.js >= 18, Claude Code (Pro or Max plan).
Cross-session memory with semantic search. Facts, decisions, lessons — all searchable by meaning, not just keywords. Uses local SQLite + optional Ollama embeddings.
You: "what did we decide about the auth flow last week?"
Claude: [searches memory → finds the decision, context, and reasoning]
Every time you correct your Claude — "that's wrong", "you missed this", "stop doing that" — the system detects the pattern, classifies it, and tracks whether it's getting better or worse.
$ claude-soul shadow --brief
premature_done: 26 corrections across 10 sessions ↑ [active]
robot_mode: 7 corrections across 6 sessions ↓↓ [internalized]
authenticity: 5 corrections across 5 sessions ↓↓ [internalized]
Patterns move through lifecycle stages: new → active → improving → internalized. After 200 sessions of real data: robot_mode went from 0.8 corrections/session to zero.
The system extracts behavioral signals from every session and periodically reflects on them. Frameworks that keep working get promoted. Bad ones get retired. After a few weeks, you get a Claude that pushes back on bad ideas, catches its own confabulation, and develops techniques you never prompted.
npx claude-soul init --starter
Add this to your CLAUDE.md:
## Soul System
Call `soul_context()` at the start of every conversation.
Use `soul_reflect` when you have idle time.
Done. Memory works with keyword search, everything else runs automatically.
Semantic search finds memories by meaning — "auth decision" finds a memory stored as "chose JWT tokens for login." Without it, search is keyword-based (still works, just less flexible).
# 1. Install Ollama (https://ollama.com)
# 2. Pull the embedding model
ollama pull nomic-embed-text
# 3. Then install as usual
npx claude-soul init --starter
The system auto-detects Ollama. No configuration needed.
npx claude-soul init --starter --skip-identity
Skips the name/context questions. Add the CLAUDE.md snippet to your agent's working directory and it works the same way — memory, correction tracking, and framework evolution all run through Claude Code's hooks and MCP server regardless of whether a human is typing or an agent is running.
npm install -g claude-soul@latest
claude-soul upgrade
Your soul files, frameworks, and data stay untouched. The upgrade re-registers hooks and MCP server with the latest version and adds any new features.
After upgrading, run claude-soul index once to backfill existing data into the memory system.
memory_save, memory_search, recall, etc.) for cross-session fact storage with semantic searchclaude-soul shadow shows behavioral patterns with trend arrows and lifecycle stagesclaude-soul index loads your existing journals and soul files into the memory databaseThese are optional — the system runs automatically. The CLI is for inspecting collected data from your terminal.
Session N
│
├─ Load identity + frameworks + memory
│
├─ Normal Claude Code usage
│
├─ Session ends → extract signals + corrections + index to memory
│
└─ Reflection threshold? → evolve frameworks → Session N+1
Everything runs through Claude Code's official extension points: an MCP server (15 tools) and hooks (signal extraction, journaling, memory indexing, correction tracking).
Identity & Learning
Memory
All settings in ~/.soul/config.json:
{
"signals": { "enabled": true, "maxLogSizeKb": 50 },
"reflection": {
"enabled": true,
"quickSignalThreshold": 20,
"deepSignalThreshold": 100,
"quickModel": "haiku",
"deepModel": "sonnet"
},
"contextBudget": { "maxTokens": 4500 },
"tensions": { "enabled": true },
"metaOptimization": { "enabled": true },
"writeProtection": { "enabled": true }
}
Contributions welcome. Open an issue to discuss before submitting large PRs.
MIT
Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory
도구
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
FAQ
이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 stdio 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
이 레코드에는 필수 환경 변수가 등록되어 있지 않습니다.
Claude Soul은(는) stdio를 통해 로컬에서 실행됩니다.
마지막 확인: 2026-10-28. Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory