varun29ankuS/shodh-memory

Overview

Shodh-memory is a cognitive memory system for AI agents that runs as a single offline binary written in Rust. It learns from usage to strengthen relevant memories and forget irrelevant information over time.

Best for

Best for
Developers building offline AI agents that require adaptive, self-maintaining memory

Use cases

• Adding persistent adaptive memory to autonomous AI agents
• Running a memory store entirely offline without cloud dependencies
• Building lightweight agents that prioritize learned information

Notes

Shodh-memory is a cognitive memory system for AI agents that runs as a single offline binary written in Rust. It learns from usage to strengthen relevant memories and forget irrelevant information over time.

215 stars on GitHub. Last updated 2026-06-01. Licensed Apache-2.0.

Use cases

• Adding persistent adaptive memory to autonomous AI agents
• Running a memory store entirely offline without cloud dependencies
• Building lightweight agents that prioritize learned information

Pros

• Single binary makes deployment simple and self-contained
• Fully offline operation preserves privacy and avoids API costs
• Rust implementation offers good performance and low resource usage

Cons

• Small community and limited stars suggest early-stage adoption
• Less documentation and fewer examples compared to established memory solutions
• Core adaptive forgetting logic may need tuning for specific use cases

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.