Task fit
30%15 points for catalog classification, 8 for an explicit category tag, and 7 when the name, description, or tags match: memory, context, session, archive, history, recall, knowledge.
Memory, context, session, and knowledge plugins ranked by more than popularity alone.
Published selection rule
Standalone, installable public repositories classified as Memory. Upstream, directory/list, archived, adaptation-required, watch, removed, placeholder, and non-plugin records are excluded; category fit is checked again against names, descriptions, and tags.
Ties are resolved by maintenance score, then Stars, then repository name.
100
point scale
15 points for catalog classification, 8 for an explicit category tag, and 7 when the name, description, or tags match: memory, context, session, archive, history, recall, knowledge.
25 points if updated within 30 days; then 20 within 90, 14 within 180, 8 within 365, and 2 thereafter.
Stars are bucketed, not directly sorted: 20 at 1,000+, 17 at 250+, 14 at 50+, 10 at 10+, 7 at 3+, and 4 at 1+.
Forks are bucketed: 10 at 100+, 8 at 25+, 6 at 10+, 4 at 3+, and 2 at 1+.
8 points for Awesome + Topic, 6 for Awesome only, or 2 for Topic only; 4 for an 80+ character English description or 2 for 30+; 3 for 3+ tags or 1 for 1–2.
Scores use public catalog and repository metadata. They do not replace hands-on evaluation, permission review, or a security audit.
Scored results
EverMind-AI / everos
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Why it placed here
Han-1413141 / dsh-cost-meter
Cost tracking for DeepSeek Harness: session and model costs, token usage, budgets, provider balances, and coding-plan quotas. Bilingual English/Chinese UI.
Why it placed here
ruvnet / ruflo
The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Why it placed here
MemTensor / MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Why it placed here
mindscale-noah / MindMemOS
Why it placed here
plastic-labs / honcho
Memory library for building stateful agents
Why it placed here
agentscope-ai / ReMe
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
Why it placed here
ZSeven-W / dsh-noema
Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.
Why it placed here
ranxianglei / billion-context
基本稳定可用 A context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).上下文压缩插件,兼顾小窗口(100k上下文足矣)省token(省5倍token)和超长会话(数月级别几十亿token单会话)。billion-context is all you need
Why it placed here
modusensus / dsh-mneme
The memory that dreams — cross-session memory for DeepSeek Harness
Why it placed here