AgentIndex icon
AgentIndex
claude-soul logo
claude-soul
★ 92
vs
widemem-ai logo
widemem-ai
★ 49

claude-soul vs widemem-ai

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.; widemem-ai: widemem is an open-source AI memory layer that provides persistent, locally-stored memory with importance scoring, time decay, hierarchical recall, and YMYL prioritization. It resolves conflicts, admits uncertainty, and supports multiple LLM and embedding providers, making it ideal for building AI assistants that remember what matters.

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 →
widemem-ai logo
widemem-aiMemory & Context · ★ 49

Chatbots and conversational AI with persistent, accurate memory

Read widemem-ai full review →
02

Side-by-Side Comparison

Field
claude-soul logoclaude-soul
widemem-ai logowidemem-ai
Category
Memory & Context
Memory & Context
Stars
★ 92
★ 49
License
MIT
NOASSERTION
Install Command
npx claude-soul init --starter
pip install widemem-ai
Updated
4mo ago
4d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
ai, ai-agent, claude
agent-memory, ai, ai-agent
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
widemem-ai logowidemem-ai
01Batch conflict resolution: single LLM call for multiple fact updates
02Importance scoring (1-10) with configurable time decay (exponential, linear, step, none)
03Hierarchical memory: facts roll up into summaries, summaries into themes
04YMYL (Your Money or Your Life) prioritization for health, legal, and financial facts
05Uncertainty and confidence modes: strict, helpful, creative, with pinning and frustration recovery
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
widemem-ai logowidemem-ai
↳Chatbots and conversational AI with persistent, accurate memory
↳Personal assistants that remember user preferences, critical information, and life details
↳Healthcare, legal, or financial applications requiring reliable retention of important facts
FAQ

FAQ

What is the difference between claude-soul and widemem-ai?
Both claude-soul and widemem-ai are in the Memory & Context category. claude-soul has 92 stars, while widemem-ai has 49 stars.
Which is better, claude-soul or widemem-ai?
The best choice depends on your use case. Choose claude-soul if Maintain context and recall previous decisions across Claude Code sessions, and widemem-ai if Chatbots and conversational AI with persistent, accurate memory.
Is claude-soul free or open source?
Yes, claude-soul is open source on GitHub (MIT).
Is widemem-ai free or open source?
Yes, widemem-ai is open source on GitHub (NOASSERTION).
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 widemem-ai →claude-soul details →widemem-ai details →