choihyunsus/soul
Soul: The Persistent Memory Layer for Multi-Agent Systems. High-performance session orchestration with SQLite-based KV-Cache for MCP. Give your AI agents a soul that never forgets.
This tool gives AI agents a reliable, persistent memory so they don't forget past conversations or tasks. It takes an agent's work history and project context as input and provides a continuously updated, shared memory that agents can access across sessions. Software developers who build or manage multi-agent AI systems, such as those used for code assistance or complex workflows, will find this project essential.
Use this if you are a developer building AI agents and need them to consistently remember previous interactions, share context seamlessly, and hand off work to each other without losing progress.
Not ideal if you are an end-user simply chatting with a single AI model and don't require complex multi-agent orchestration or persistent memory beyond a single conversation thread.
Stars
60
Forks
7
Language
TypeScript
License
—
Category
Last pushed
Mar 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/choihyunsus/soul"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
kayba-ai/agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
MemMachine/MemMachine
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory...
knowns-dev/knowns
The memory layer for AI-native development — giving AI persistent understanding of your software...
rexdivakar/HippocampAI
HippocampAI — Autonomous Memory Engine for LLM Agents
Dicklesworthstone/cass_memory_system
Procedural memory for AI coding agents: transforms scattered session history into persistent,...