DeepSeek Harness Plugins
DeepSeek Harness PluginIndexed

ReMe

Local-first, self-evolving memory management kit and knowledge base integration for DeepSeek Harness.

Developer ToolsSkills & WorkflowsRemote Execution
3.4kGitHub Stars290ForksUpdated2026-08-27

Install

$ | **DeepSeek Harness** | Install [@agentscope-ai/reme](typescript/README.md#deepseek-harness) with dsh plugin --profile web add @agentscope-ai/reme. | Long-term memory guidance, the reme_search tool, and automatic capture of completed main-agent turns. |

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
ReMe is a local-first memory management kit for AI agents that turns conversations and external resources into structured, searchable, and interconnected Markdown notes. When integrated with DeepSeek Harness via @agentscope-ai/reme, it injects long-term memory guidance into agent prompts, exposes the reme_search tool for line-level BM25 and wikilink retrieval, and automatically captures completed agent turns into progressive daily notes and long-term digest nodes.

Key Capabilities

  • Injects long-term memory context and guidance into DeepSeek Harness prompt lifecycles
  • Provides reme_search tool for line-level BM25, wikilink expansion, and optional semantic vector retrieval
  • Automatically captures completed main-agent conversation turns into local Markdown memory files
  • Progressively consolidates daily conversation records into long-term structured knowledge and wikilinks via Auto Dream
  • Maintains readable Markdown files with frontmatter as durable source of truth

Useful For

  • Cross-session memory and preference tracking for DeepSeek Harness workflows
  • Personal agent knowledge base management using local Markdown notes
  • Procedural memory capture for complex coding and tool execution tasks
  • Fast retrieval of historical context and wikilinked reference materials

Who It Fits

  • Developers building persistent AI assistants with DeepSeek Harness
  • Users who need transparent, local-first file-based memory for agents
  • Researchers exploring agentic memory and self-evolving knowledge bases

Documented Limitations

  • Requires a running ReMe local daemon or service (Python 3.11+)
  • LLM-driven memory distillation (auto_memory and auto_dream) requires configured LLM API credentials
  • Embedding-based vector retrieval is optional and requires separate configuration

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

License Declared

GitHub reports the repository license as Apache-2.0.

info
Package Manifest Not Found

No root package.json was captured in the latest GitHub snapshot.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
agentscope-ai/ReMe
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
2dd2255 · 2026-08-27

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
3.4kGitHub stars
Forks
290
Open issues
23
Last commit
2026-08-27
Last release
2026-08-27
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app