Plugin
roblox-devforum-mcp
EL4CTEO
Give your AI coding agent the Roblox DevForum and official creator docs — check if a bug is already known, read the accepted answer, and verify APIs before writing Luau.
aiai-agentsclaude
5Ready to use
81/100
PluginNeeds setup
MemOS
MemTensor12,3621,118Updated yesterday
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.
agentagentic-aiaiai-agentschatgptclaudedeepseek-harnessdsh-pluginhermesllmlong-term-memorymcpmemorymemory-management
Practical score
87 / 100
Setup
Needs setup
License
Apache-2.0
Language
TypeScript
Install
Quick startCopy the command, or hand the whole task to your harness agent.
git clone https://github.com/MemTensor/MemOS.gitDSH versionDSH 0.2.1-rc.3Setup required
Install with your agent
Please install the DeepSeek Harness plugin "MemOS" for me. - GitHub repository: MemTensor/MemOS (https://github.com/MemTensor/MemOS) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version requirement of 0.2.1-rc.3. Check my…
From the README
A cleaned excerpt from the project's own documentation.
MemOS 2.0 Stardust（星尘）
Open on GitHubProject details
- Repository
- MemTensor/MemOS
- by
- MemTensor
- License
- Apache-2.0
- stars
- 12,362
- Forks
- 1,118
- Updated
- Nov 11, 2026
- Created
- Jul 6, 2025
- Language
- TypeScript
- Indexed from
- topic
Related entries
Similar tools from the same corner of the ecosystem.
Plugin
dsh-mneme
slow-stack
Cross-session memory for DeepSeek Harness: SQLite + human-editable Markdown mirror, autoDream consolidation, six memory tools, and fully-offline semantic search (local embedding / rerank / clustering), 198 tests.
agent-memoryagent-memory-systemagentic-ai
221Needs setup
80/100
Plugin
dsh-Visual-Workflow
GZX2211
可视化 Agent 编排平台｜基于 DeepSeek Harness，支持 Workflow、Multi-Agent、元编排、MCP 与 Human-in-the-loop｜Visual AI Agent orchestration platform for workflows, multi-agent teams, MCP and human-in-the-loop
agentagent-teamagentic-ai
66Ready to use
87/100