Open source code for Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Python · active 2025-07-07 → 2026-05-21 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 319 days from 2025-07-07 to 2026-05-21. Pushes: 12 total, peak 2 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 15 total, peak 2 in a day. Comments: 13 total, peak 3 in a day. Stars: 111 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| HUST-AI-HYZ | 22 | 10 | 0 | 11 |
| sz17320828912-tech | 4 | 0 | 0 | 1 |
| wangyu-ustc | 2 | 2 | 0 | 0 |
| NiNicoder | 2 | 0 | 0 | 1 |
| zcg-joker | 2 | 0 | 0 | 0 |
| aorogat | 1 | 0 | 0 | 0 |
| MOX-333 | 1 | 0 | 0 | 0 |
| smirnp | 1 | 0 | 0 | 0 |
| SKDDJ | 1 | 0 | 0 | 0 |
| raj-shah14 | 1 | 0 | 1 | 0 |
| Yangseung | 1 | 0 | 0 | 0 |
| Unturned3 | 1 | 0 | 0 | 0 |
| jisuozhao | 1 | 0 | 0 | 0 |
| Hanzhang-lang | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#19raj-shah142026-05-01 20:05
- Issue#17MOX-3332026-01-27 02:03estimated token usage per memory agent in the benchmark？
- Issue#15jisuozhao2026-01-13 05:55Question about reproducing Mem0 + LongMemEval(S*) results
- Issue comment#16HUST-AI-HYZ2026-01-12 06:02Request to Add GPT-5-mini Evaluation Results to Extend the Lifespan of MemoryAgentBench
- Issue comment#15HUST-AI-HYZ2025-12-05 06:53Question about reproducing Mem0 + LongMemEval(S*) results
- Issue comment#13HUST-AI-HYZ2025-12-04 08:16questions
- Issue comment#14HUST-AI-HYZ2025-12-04 08:15An Important question
- Issue comment#15HUST-AI-HYZ2025-12-04 08:13Question about reproducing Mem0 + LongMemEval(S*) results
- Issue comment#14sz17320828912-tech2025-12-03 03:04An Important question
- Issue#14sz17320828912-tech2025-12-02 08:33An Important question
- Issue#13sz17320828912-tech2025-11-28 08:19questions
- Issue comment#12HUST-AI-HYZ2025-11-19 04:34Missing Zep config file
- Issue comment#7HUST-AI-HYZ2025-11-19 04:25some questions
- Issue comment#7NiNicoder2025-11-19 03:37some questions
- Issue#12NiNicoder2025-11-18 16:07Missing Zep config file
- Issue#8zcg-joker2025-11-15 05:18Consider adding LLM-as-a-Judge evaluation metrics alongside traditional token-level metrics
- Issue#3HUST-AI-HYZ2025-11-14 23:58Question Regarding the paper
- Issue#9aorogat2025-11-14 20:37entity2id.json file
- Issue#8zcg-joker2025-11-13 04:14Consider adding LLM-as-a-Judge evaluation metrics alongside traditional token-level metrics
- Issue#7sz17320828912-tech2025-10-30 05:55some questions
- Issue comment#5HUST-AI-HYZ2025-10-29 23:25Clarification on Reported Metrics in Table Results
- Issue#6smirnp2025-10-29 15:55Chunk size for SH-Doc QA, MH-Doc QA
- Issue#5Yangseung2025-10-29 00:36Clarification on Reported Metrics in Table Results
- Issue comment#4HUST-AI-HYZ2025-10-26 04:32How does the Recommendation dataset map answers?
- Issue#3Hanzhang-lang2025-10-19 03:16Question Regarding the paper
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 111 stars here means stars gained during the window, not the repo's star count.