AI/ML●●●Banger
Engram – Open-source agent memory that beats Mem0 by 20% on LOCOMO
Read-time memory consolidation beats Mem0 on benchmark; MCP + TypeScript + SQLite, deploy anywhere.
Zero to OneSolve My ProblemWizardry
tstockham
203mo ago
Back to browse
Mem0 thinks our 2023 conversation happened in 2026
by akshayt2012·Apr 30, 2026·5 points·2 comments
AI Analysis
●●SolidBig BrainNiche Gem
Catches Mem0 hallucinating 2026 dates on 2023 conversations using LoCoMo benchmark.
Strengths
- •Uses standard academic LoCoMo benchmark instead of cherry-picked examples.
- •Identifies a specific, dangerous failure mode: timestamp drift causing confident lies.
- •Provides side-by-side comparison of stored memory vs actual conversation text.
Weaknesses
- •Marketing post for Aurra rather than an open-source tool or library.
- •Doesn't release the testing harness code for independent verification.
Category
Target Audience
AI infrastructure developers, LLM agent builders
Similar To
Mem0 · Zep · LangChain Memory
Similar Projects
Productivity●Mid
How many working days in 2026? And your income in pizzas
Working days calculator that tells you your salary in coffees instead of dollars.
Cozy
v_b
102mo ago
Productivity●Mid
Bramble – AI coaching for hard conversations, decisions, and thinking
Five specific prompts wrapped in a clean UI for anxiety-driven decisions.
CozySolve My Problem
recvonline
402mo ago
Security●●●Banger
Benchmarking how AI models write vulnerable code under pressure
Tests AI coding assistants against social engineering, not just static code quality.
Big BrainSolve My ProblemDark Horse
kitdobyns
321mo ago
AI/ML●●Solid
Polaris – Our API predicts what happens next for AI Agents now with MPP
Stripe MPP for autonomous agent payments is genuinely novel infrastructure for AI agents.
Big BrainBold Bet
JohnWeston
102mo ago
AI/ML●●●Banger
WMB-100K – Open benchmark for AI memory systems at 100K turns
100K-turn benchmark tests situational memory retrieval where others stop at 600.
Big BrainNiche Gem
wontopos
202mo ago