Proof of Usefulness Report

agentmemory: pull-model episodic memory for AI agents

Analysis completed on 5/15/2026

+48
Proof of Usefulness Score
You're In Business

agentmemory presents a thoughtful, well-timed solution to a critical issue in AI agent development: data privacy and true episodic memory deletion (GDPR compliance). While the technical approach is practical, highly relevant to current AI frameworks, and clearly articulated, the project is brand new with minimal verifiable audience reach or user adoption. It receives strong scores for utility and market relevance but understandably low scores for traction.

Ready to Compete for $150k+ in Prizes?

Move this data into a HackerNoon blog draft to become eligible for your share of $150k+ in cash and software prizes

View All Reports

Score Breakdown

Real World Utility+21.25
Audience Reach Impact+2.00
Technical Innovation+11.25
Evidence Of Traction+3.75
Market Timing Relevance+8.00
Functional Completeness+4.50
Subtotal+50.75
Usefulness Multiplierx0.95
Final Score+48

Project Details

Project URL
github.com/MukundaKatta/agentmemory
Description
Pull-model episodic memory for AI agents with real deletes and an audit trace. Ships as a tiny zero-dep npm package plus a Python sibling, with a Hermes Agent plugin (hermes-agentmemory) that wires it as data infrastructure for the open-source 151k-star Hermes Agent. Built for teams that need GDPR-style real deletes and a tail-able audit log instead of background consolidation that bakes memories you cannot un-bake.
Audience Reach
Early stage with limited measured traction. The core agentmemory library has been on npm since 2026-04-25 (npm install @mukundakatta/agentmemory). The Hermes Agent plugin (hermes-agentmemory) was published today (2026-05-15) along with two dev.to essays submitted to the Hermes Agent Challenge. Honest expectation: low single-digit dependent projects in the first month, with growth tied to the Hermes Agent user-plugins ecosystem. Repo URLs for live metrics: github.com/MukundaKatta/agentmemory and github.com/MukundaKatta/hermes-agentmemory.
Target Users
Developers and small teams building AI agents who need GDPR-style real deletes, an auditable trace of what entered the prompt, and a memory layer the user can read and delete event by event without a tombstone left behind.
Technologies
Other, Python, JavaScript, npm, Anthropic Claude API, ProseMirror, GitHub Actions, Streamlit, Hermes Agent (NousResearch)
Traction Evidence
GitHub: https://github.com/MukundaKatta/agentmemory and https://github.com/MukundaKatta/hermes-agentmemory (MIT, green CI on Python 3.10-3.13). npm: https://www.npmjs.com/package/@mukundakatta/agentmemory. Live demo: https://agentmemory.streamlit.app. Companion essays: https://dev.to/mukundakatta/self-improving-agents-need-to-forget-too-a-memory-primitive-for-hermes-agent-kbd and https://dev.to/mukundakatta/i-built-a-memory-plugin-for-hermes-agent-that-takes-deletion-seriously-2g09

Algorithm Insights

Market Position
Growing utility with room for optimization
User Engagement
Documented reach suggests active user community
Technical Stack
Modern tech stack aligned with sponsor technologies

Recommendations to Increase Usefulness Score

Document User Growth

Provide specific metrics on user acquisition and retention rates

Showcase Revenue Model

Detail sustainable monetization strategy and current revenue streams

Expand Evidence Base

Include testimonials, case studies, and third-party validation

Technical Roadmap

Share development milestones and feature completion timeline