deepseek-harness-brain
AgriciDaniel
Independent evidence-gated second brain for understanding and porting DeepSeek Harness architecture.
luobosibing220721Updated 2d ago
Opt-in Jev/Luna decision layer for DeepSeek Harness: skill and file selection, task supervision, tool-output filtering, approval assistance and recorded-stage navigation; features are disabled by default.
Practical score
83 / 100
Setup
Needs setup
License
MIT
Language
JavaScript
Copy the command, or hand the whole task to your harness agent.
git clone https://github.com/luobosibing2/dsh-jev-plugin.gitPlease install the DeepSeek Harness plugin "dsh-jev-plugin" for me. - GitHub repository: luobosibing2/dsh-jev-plugin (https://github.com/luobosibing2/dsh-jev-plugin) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version req…
A cleaned excerpt from the project's own documentation.
deepseek-harness-jev English 简体中文 中文功能与实测网站 Native DeepSeek Harness (DSH) plugin with Jev or Luna Decisions as its judgment model. deepseek-harness-jev connects DeepSeek Harness (DSH) to Jev by TypeSafe AI for agent skill and file selection, task supervision, shared-finding corrections, tool-output filtering, single-operation approval assistance, and historical stage navigation. Its 12 features are individually configurable from one Jev settings page and are all disabled by default. The main model continues to plan, generate answers, and call native tools. Enabled features use the saved Jev or Luna Decisions connection at DSH extension points for skill catalogs, agent lifecycle, tool results, and approvals, then apply results according to each feature. DSH configures the main model separately. Integration uses public Cordis / DSH plugin APIs without modifying the host source. This is an independent community project, not an official DeepSeek or Jev release.…
Open on GitHubSimilar tools from the same corner of the ecosystem.
AgriciDaniel
Independent evidence-gated second brain for understanding and porting DeepSeek Harness architecture.
yangdcm
Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out. 12 role subagents, 9 gated phases, shared-workspace artifacts, zero runtime dependencies.
TGYD-helige
Generic DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.