Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
ReMe (formerly MemoryScope)
From Alibaba's AgentScope team: local-first, file-based memory kit that stores agent memory as Markdown with frontmatter and wikilinks, shared across agents via CLI, HTTP, MCP and plugins.
reme.agentscope.io/Changed direction
modelscope/MemoryScope now redirects to agentscope-ai/ReMe (MemoryScope kept on memoryscope_branch; last memoryscope PyPI 0.1.1.0 2024-09-11). ReMe v0.4.1.13 released 2026-10-04; pushed 2026-10-23. (checked 2026-10-25)
In Agent memory
Where it stands apart
- How is it mainly sustained? big company side project (5% of 20 others)
- Which shared standard or format does it mainly build on? plain Markdown files (wikilinks, frontmatter) (5% of 21 others)
- Where do memories live in the default setup the docs lead with? on the end user's own device (14% of 21 others)
- What is the main storage model for long-term memory? plain files (Markdown, text, JSON) (15% of 20 others)
What it shares with most of the community
- Is it actively maintained? active (67% of 21 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (67% of 21 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (67% of 21 others)
- Who is it for? developers (76% of 21 others)
- In the default setup, who mainly decides what gets remembered? the system, by extracting memories from conversations or data in the background (67% of 21 others)
- By default, how do old or wrong memories mainly go away? the system updates, merges, or decays them automatically (58% of 19 others)
- Does it work with models from different LLM vendors? yes, model-agnostic (86% of 21 others)
- Is there a first-party MCP server for it? yes (67% of 21 others)
- Does it publish scores on public memory benchmarks (LoCoMo, LongMemEval, BEAM, etc.)? yes (62% of 21 others)
Nearest neighbors
- MemOS (MemTensor) 65% of 17 shared answers match
- LongMemory (formerly OpenMemory) 63% of 16 shared answers match
- MCP reference memory server 59% of 17 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active Active after pivoting from MemoryScope's design to 'memory as file'. | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) Apache-2.0 | source 2026-10-25 |
| How is it mainly sustained? | stands apart big company side project AgentScope (Alibaba/ModelScope ecosystem). | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-25 |
| Do you need an account to use it? | no account Local file-based; no account mentioned, only optional LLM/embedding API keys. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart plain Markdown files (wikilinks, frontmatter) Markdown with frontmatter and wikilinks. | source 2026-10-26 |
| In the default setup, who mainly decides what gets remembered? | the system, by extracting memories from conversations or data in the background Automatic turn capture and scheduled 'Auto Dream'; agents also get search tools. | source 2026-10-25 |
| How can the person the memories are about see and edit them? | directly, as readable files or in a UI they control 'readable, editable' Markdown; users retain control of the files. | source 2026-10-25 |
| By default, how do old or wrong memories mainly go away? | the system updates, merges, or decays them automatically Self-evolving workflows and scheduled consolidation. | source 2026-10-25 |
| Where do memories live in the default setup the docs lead with? | stands apart on the end user's own device | source 2026-10-25 |
| Does it work with models from different LLM vendors? | yes, model-agnostic | source 2026-10-25 |
| What is the main storage model for long-term memory? | stands apart plain files (Markdown, text, JSON) | source 2026-10-25 |
| What shape does it mainly take (the one its docs lead with)? | memory service (self-hosted server or hosted API) | source 2026-10-25 |
| Is there a first-party MCP server for it? | yes | source 2026-10-25 |
| How is memory separated between users or tenants? | one store per user or agent; the app partitions it One shared memory workspace across agents. | source 2026-10-25 |
| Does it publish scores on public memory benchmarks (LoCoMo, LongMemEval, BEAM, etc.)? | yes LongMemEval 89.4%, BEAM. | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/agentscope-ai/ReMe · read 2026-10-25
- Web page · reme.agentscope.io/ · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.