Claude Soul
Claude Code forgets everything between sessions. Claude Soul doesn't.
Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
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.
เปิดnpx claude-soul init --starter
One 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
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Claude Soul ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-28 Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory