Memori
#8 todayPersistent memory from agent trace, not just conversation
Votes
132
Comments
21
What this means
1.5×Growing 1.5× faster than the typical AI Agents launch.
Compared to 6 AI Agents launches at the same age.
+693%Launching in a 693% WoW growing category.
Developer Tools had 230 launches this week vs 29 last.
22Founder Conviction Index: 22 — low signal.
Few of the conviction sub-signals (reputation, velocity, buyer-intent, tagline clarity) are firing yet.
Prediction
Top-5 finish probability
29%
today
Projected end-of-day votes
132range 99–178
Trajectory
stable
Not enough snapshots yet to detect trajectory.
Speed vs peers
1.5×
6 AI Agents launches
About
Memori launched its new agent-native memory infrastructure, enabling agents to create structured, long-term memory directly from agent trace — including execution paths, tool results, workflow steps, outcomes, and decision-making logic. This allows memory to also be generated from what an agent actually does. Benchmark results: 81.95% accuracy on LoCoMo using only 1,294 tokens per query, roughly 5% of full-context cost, saving users 95%+ on inference spend. 15K GitHub stars, 200000+ downloads
AI Summary
Memori offers an agent-native memory infrastructure that generates structured, long-term memory from agent trace, enhancing AI decision-making and workflow efficiency. It boasts 81.95% accuracy on LoCoMo with significantly reduced inference costs and has gained 15K GitHub stars and over 200,000 downloads.
Vote & comment velocity
Scores
Velocity0.0
Vote pace vs avg
Momentum0.0
Sustained over 6h
Virality0.0
Spread × engagement
Engagement31.8
Comments per vote