deepseek-rlm
Persistent IPython workspace, durable state snapshots, and native recursive subagents for DeepSeek Harness.
Install
$ dsh plugin --profile <profile> add -w /absolute/path/deepseek-rlm-dsh-rlm-bundle-0.1.0-preview.0.tgzPlugin 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.
Key Capabilities
- Persistent IPython/Jupyter kernel per active DeepSeek Harness agent
- Durable variable snapshots using digest-authorized serialization with dill
- Native recursive subagent spawning (rlm primitive) with enforced depth and lineage
- Bidirectional agent-to-parent and parent-to-child messaging via agent_message
- DSH tool execution routing directly from Python scripts via dsh_tools.call()
Useful For
- Multi-step Python data analysis and coding sessions requiring variable persistence between prompt turns
- Delegating focused sub-tasks (e.g. debugging, investigation) to recursive child agents without spawning detached runtimes
- Snapshotting and restoring in-memory Python state without re-executing historical code cells
Who It Fits
- DeepSeek Harness developers building multi-agent workflows
- Data scientists and engineers requiring stateful REPL execution inside DSH agents
- AI automation engineers leveraging recursive subagent patterns
Documented Limitations
- Targets DSH 0.1.2-alpha.3 specifically and requires two bundled host patches
- IPython operates with OS-level authority and is not a sandboxed execution environment
- Packages are distributed as buildable local tarballs and require Python 3.11 with uv
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- OpenCnid/deepseek-rlm
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 0e9f030 · 2026-09-11
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
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-01
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Local, fast cross-agent memory and session indexing system with DeepSeek Harness integration.
View plugin →