Sankhya-AI/Dhee
Memory layer for AI agent orchestrators with adaptive forgetting, stronger retrieval.
This helps AI agents go beyond simple recall to genuinely learn and adapt, making them more effective at complex, multi-session tasks. It takes an agent's raw observations and actions, processes them into actionable insights, and provides context-aware guidance. Any professional who relies on AI assistants for tasks like coding, customer support, or data analysis would find this useful.
Use this if your AI agent needs to remember user preferences across sessions, learn from past successes and failures, proactively warn you about performance issues, or recall intentions based on current context.
Not ideal if you only need a basic keyword or vector search for static information, or if your agent's tasks are simple and don't require learning or long-term memory.
Stars
16
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Sankhya-AI/Dhee"
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,...