TESIGN
SAVED

EN · KO

Auto-generated — not yet edited · only the numbers are verified

  1. TESIGN / RADAR
  2. REPOSITORY CARD
  3. mem0ai/mem0

mem0ai/mem0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

★ 65.2k▲ +31 / 7dDaily star increases over 14 days. Hollow bars mean no data. The last day may be partial.2026-09-03 no data2026-09-04 +52026-09-05 +142026-09-06 +162026-09-07 no data2026-09-08 no data2026-09-09 no data2026-09-10 +22026-09-11 +102026-09-12 +82026-09-13 +42026-09-14 no data2026-09-15 +22026-09-16 +5largest one-day increase in the 14 days+16last 14 days · stars per dayhollow = no data

RANKS All-time #88

AT A GLANCE

LANGUAGE
Python
LICENSE
Apache-2.0
USAGE
Commercial use, redistribution OK. Keep notices; mark changes.
ACTIVITY
last commit 5 days ago ()
TOPICS
  • agentic-memory
  • agentic-memory-system
  • agents
  • ai
  • ai-agents
  • chatgpt
  • genai
  • llm
  • long-term-memory
  • memory
  • memory-management
  • python
HOMEPAGE
https://mem0.ai
REPOSITORY
GitHub ↗
CATEGORY
AI

A summary, not legal advice.

README EXCERPT

Learn more · Join Discord · Demo 📄 Benchmarking Mem0's token-efficient memory algorithm → New Memory Algorithm (April 2026) Benchmark Old New Tokens Latency p50 --- --- --- --- --- LoCoMo 71.4 92.5 7.0K 0.88s LongMemEval 67.8 94.4 6.8K 1.09s BEAM (1M) — 64.1 6.7K 1.00s BEAM (10M) — 48.6 6.9K 1.05s All benchmarks run on the same production-representative model stack. Single-pass retrieval (one call, no agentic loops) at a top 200 retrieval budget. Scores reflect Mem0's managed platform, which includes proprietary optimizations not available in the open-source SDK; open-source users should expect directionally similar gains but not identical numbers. What changed: - Single-pass ADD-only extraction -- one LLM call, no UPDATE/DELETE. Memories accumulate; nothing is overwritten. - Agent-generated facts are first-class -- when an agent confirms an action, that information is now stored with equal weight. - Entity linking -- entities are extracted, embedded, and linked across memories for retrieval boosting. - Multi-signal retrieval -- semantic, BM25 keyword, and entity matching scored in parallel and fused. - Temporal Reasoning -- time-aware retrieval that ranks the right dated instance…

The opening of the GitHub README as stored, at most 1,200 characters. Markdown is not rendered.

TIMELINE

  1. Repository created
  2. Last push
  3. FIRST SEEN BY TESIGN ◌ BACK CATALOG

AI chooses the lists under the owner’s delegation. No human review is running in September 2026. Total stars, increases, cross-source signals, last updates and licences are shown as evidence. How ranks work →

If this repository gets editorial text (why, build, who, start, caveat) it becomes an edited entry. Until then the page shows only stored GitHub metadata and numbers.