AgentIndex icon
AgentIndex
claude-soul logo
claude-soul
★ 92
vs
kimi-code-mcp logo
kimi-code-mcp
★ 61

claude-soul vs kimi-code-mcp

claude-soul: Claude Soul gives Claude Code persistent memory across sessions, automatically tracks user corrections with lifecycle stages, and develops improved behavioral frameworks over time. It runs entirely locally using SQLite, integrates via MCP server and hooks, and requires no cloud or API keys.; kimi-code-mcp: This MCP server integrates Kimi Code (K2.5) with Claude Code, allowing Claude to delegate bulk code reading and analysis to Kimi while focusing on decision-making and code editing. It reduces Claude token consumption by using Kimi's 256K context for cheap, deep code understanding. The tool supports code analysis, querying, session management, and can be configured for different levels of output detail.

01

TL;DR

claude-soul logo
claude-soulMemory & Context · ★ 92

Maintain context and recall previous decisions across Claude Code sessions

Read claude-soul full review →
kimi-code-mcp logo
kimi-code-mcpDev Tooling · ★ 61

Analyze codebase architecture: Kimi reads all files, Claude acts on the report

Read kimi-code-mcp full review →
02

Side-by-Side Comparison

Field
claude-soul logoclaude-soul
kimi-code-mcp logokimi-code-mcp
Category
Memory & Context
Dev Tooling
Stars
★ 92
★ 61
License
MIT
MIT
Install Command
npx claude-soul init --starter
curl -L code.kimi.com/install.sh | bash && npm install -g kimi-mcp-server
Updated
4mo ago
1w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
ai, ai-agent, claude
ai-agent, ai-coding-assistant, claude-code
03

Features

claude-soul logoclaude-soul
01Cross-session memory with semantic search (local SQLite + optional Ollama embeddings)
02Automatic correction tracking with lifecycle stages (new → active → improving → internalized)
03Self-evolving judgment and framework optimization through reflection cycles
04Shadow analysis CLI to inspect behavioral patterns with trends
05Fully local, no cloud, no API key, no telemetry
kimi-code-mcp logokimi-code-mcp
01Delegates bulk code reading to Kimi for token savings
02256K context for deep codebase understanding
03Provides structured analysis (architecture, security, dependencies)
04Resume sessions with retained context
05Configurable output detail levels (summary/normal/detailed)
04

Use Cases

claude-soul logoclaude-soul
↳Maintain context and recall previous decisions across Claude Code sessions
↳Track and internalize corrections to improve Claude's behavior over time
↳Allow Claude to autonomously develop and refine working frameworks based on repeated successful patterns
kimi-code-mcp logokimi-code-mcp
↳Analyze codebase architecture: Kimi reads all files, Claude acts on the report
↳Scan for security vulnerabilities: Kimi audits, Claude cross-examines
↳Dependency mapping and refactoring planning: Kimi builds graph, Claude plans changes
FAQ

FAQ

What is the difference between claude-soul and kimi-code-mcp?
Both claude-soul and kimi-code-mcp are in the Memory & Context category. claude-soul has 92 stars, while kimi-code-mcp has 61 stars.
Which is better, claude-soul or kimi-code-mcp?
The best choice depends on your use case. Choose claude-soul if Maintain context and recall previous decisions across Claude Code sessions, and kimi-code-mcp if Analyze codebase architecture: Kimi reads all files, Claude acts on the report.
Is claude-soul free or open source?
Yes, claude-soul is open source on GitHub (MIT).
Is kimi-code-mcp free or open source?
Yes, kimi-code-mcp is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to claude-soul →Alternatives to kimi-code-mcp →claude-soul details →kimi-code-mcp details →