Back to catalog

GITHUB TOPIC

self-improvement

8projects include this topic

The "self-improvement" topic on GitHub groups 8 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-self-improved with 8 GitHub stars. dsh-self-improved — DeepSeek Harness long-term memory & self-evolving plugin: L0 capture -> L1 memory extraction -> L2 scene grouping -> L3 user persona, auto recall injection + skill synthesis, fully local. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.

{count} projects

Exact GitHub Topic match

Agents & sessionsSkill

DeepSeek Harness long-term memory & self-evolving plugin: L0 capture -> L1 memory extraction -> L2 scene grouping -> L3 user persona, auto recall injection + skill synthesis, fully local.

Structure check pending
agent-memoryai-agentdeepseek-harnessdsh
Models & MCPPlugin

DeepSeek Harness full self-evolution upgrade plugin v2.4.0: six-stage closed loop of scan/monitor/identify/propose/approve/execute + real DSH subagent integration (task DAG orchestration protocol); MoonBit native rewrite, all 422 tests passing (347 MoonBit + 75 legacy-ts).

Structure check pending
deepseek-harnessdsh-plugindsh-plugin-marketdsh-plugins
DSH PluginsPlugin

dsh-refine

dushaobindoudou

DeepSeek Harness (dsh) plugin — /refine command + settings panel for the dsh-continual-harness self-refinement engine. npm: dsh-refine

Structure check pending
agentagent-harnesscontinual-harnesscordis
DSH PluginsPlugin

dsh-skillopt

WODE25500

Microsoft SkillOpt-Sleep integration for DeepSeek Harness (dsh): nightly sleep cycle - harvest sessions, replay recurring tasks, consolidate validated skills behind a held-out gate. ?? DSH ? SkillOpt ??

Structure check pending
cordisdeepseek-harnessdshdsh-plugin
Agents & sessionsPlugin

Session-level lesson ledger watch for DeepSeek Harness: did this session actually consult the ledger and record its pitfalls?

Structure check pending
cordisdeepseek-harnessdshdsh-bundle
Agents & sessionsPlugin

dsh-loom

DarknessLED

Human-in-the-loop recursive self-improvement for DeepSeek Harness: a plugin that turns one objective into an auditable, self-optimizing work chain running in child sessions while the main agent stays idle.

Structure check pending
autonomous-agentsdeepseek-harnessdshdsh-plugin
Agents & sessionsSkill

DSH self-improvement skill: reflect after a task and load relevant learnings before the next one

Structure check pending
agent-skillsai-agentdeepseek-harnessdsh
DSH PluginsPlugin

Privacy-bounded self-improvement plugin for DeepSeek Harness

Structure check pending
ai-agentscordisdeepseek-harnessdsh