MemSkillViktorAxelsen/MemSkill
Provides a reusable skill bank plus batch evaluation and training pipelines for long-conversation memory agents,…
No ratings yet
Rate this skill
Stars581
Forks37
Watchers581
Open Issues7
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/ViktorAxelsen/MemSkill.git
OverviewOverview
Key Features
Provides a reusable skill bank plus batch evaluation and training pipelines for long-conversation memory agents, solving the problem that memory capability is hard to measure in a standardized way and evaluations are slow to run. Key capabilities include: 1. Reusable skill bank: maintains a shared, continuously evolving skill bank so different agents can reuse the same memory skills instead of reimplementing them; 2. High-throughput evaluation: calls models concurrently with multiple API keys, greatly shortening benchmark time on large sample sets; 3. Scalable training and runs: offers horizontally scalable training and experiment execution, making it easy to reproduce experiments on more data and at larger scale; 4. Dataset splits and built-in samples: ships split files such as locomo10, longmemeval_s, eval_50 and eval_200, and supports switching datasets via the --dataset argument to run different evaluation tasks directly.
Use Cases
Evaluating an agent's memory recall and comprehension in long conversations, building a reusable memory skill bank, running batch comparative experiments across multiple datasets, and scaling training and evaluation workloads.
Target Roles
AI / Algorithm Engineer, Data Analyst / Data Engineer, Test / QA Engineer.
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 1350 |
|---|---|
| Data source | GitHub |
| Repository | ViktorAxelsen/MemSkill |
| Category | AI & Data Science / AI Agents & Memory Systems |
| Primary language | Python |
| License | Apache License 2.0 |
| Default branch | main |
| GitHub repository ID | 1146040039 |
| Node ID | R_kgDORE8u5w |
| Rank | #1135 (position within the source ranking) |
| Site-wide popularity rank | #1303 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now581
- Previous point · 09-27 582
- vs previous point -1
- 2 data points 14 days
- Now37
- Previous point · 09-27 38
- vs previous point -1
- 2 data points 14 days
TimelineTimeline
Repository created2026-01-30 14:46:199 months ago
Data last updated2026-10-26 12:09:2721 days ago
Last commit2026-10-01 15:00:151 months ago
CommitLatest commit
Version [latest] committed by ViktorAxelsen. Update Category: Codebase Iteration & Routine Maintenance. Commit details: update project website and alfworld codes. This update updates core functional modules and advances project iteration.