Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

18 plugins found

F

dsh-memory

furongjun-1999/dsh-memory

White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

69819 hours agoMemoryMIT
B

agentdescent

birfy/agentdescent

Evolve skills, agents, prompts, code and plugins from inside DeepSeek Harness, with AgentDescent.

2332 months agoSkillsMIT
P

dsh-host-rsi

pk14742952-ad/dsh-host-rsi

Reflective self-evolution plugin for local Qwen3.8 27B/3.8 Flash and online APIs: a coding-loop convergence steerer curbs Qwen3.8 27B/Flash repeated-verification deep-thinking to converge faster and cut thinking time; a five-state delivery guard detects and corrects stuck turns and infinite loops; model-agnostic host logic, mostly compatible with online APIs; per-use continual self-improvement with counter-reason self-checks, critic escalation, inverted-index memory retrieval, coding-loop convergence steering, and a five-state delivery guard.

3918 days agoMemoryMIT
M

dsh-self-improved

madage/dsh-self-improved

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).

153 months agoMemoryMIT
P

open-dream-rsi (deepseek_harness)

patrykorwat/open-dream-rsi

Not another memory plugin: ODR is an evolving-worlds self-improvement loop (Dream-RSI) — attempts are recorded into a Discovery Tree, and between runs thousands of strategy variants are replayed against that recorded world; a strategy, recipe or lesson is promoted only after surviving counterfactual replay, never on the model's word alone, and Sentinel gates tool calls before the budget burns; the LLM stays frozen, installable from npm as dsh-open-dream-rsi.

1414 days agoTools & CapabilitiesMIT
A

dsh-harness2

asiu-x/dsh-harness2

Harness² recursive self-improvement for DSH agents: Propose–Probe–Compose, isolated probes, anonymous selection, and a per-domain experience library.

135 days agoMemoryApache-2.0
P

open-dream-rsi

patrykorwat/open-dream-rsi

Let your coding agent dream: strategies must survive counterfactual replay before they earn trust. An offline self-improvement loop over an evolving world model — no fine-tuning, the LLM stays frozen. Speaks MCP. Ships its Python server inside the package

11last monthMCP & ConnectorsMIT
W

dsh-skillopt

wode25500/dsh-skillopt

Nightly self-improvement for your DeepSeek Harness agent: harvest past sessions offline, replay recurring tasks on your own API budget, and consolidate validated skills behind a held-out gate. Brings microsoft/SkillOpt's SkillOpt-Sleep engine to dsh as native tools plus a bundled skill - no weight training. Requires Python 3.10+ and the SkillOpt-Sleep engine (pip install skillopt).

418 days agoSkillsMIT
L

dsh-five-session-evolution

liuhuishang/dsh-five-session-evolution

Review every five distinct ended project sessions in DeepSeek Harness, retain sourced lessons and workflow drafts, and supply project memory to later sessions.

113 days agoMemoryMIT
O

dsh-ledger-watch

oldmanding/dsh-ledger-watch

Ships a minimal lesson ledger: brief.ps1 to look up past pitfalls, add-lesson.ps1 to record new ones, deployed into the skills directory and wired into AGENTS.md by the installer. The model checks it before working and turns what it hits into rules, so the same mistake is not made twice. This plugin watches whether that actually happens and shows the result in a tab and under the composer.

114 days agoMemoryMIT
D

dsh-self-improvement

dxxcao/dsh-self-improvement

Cross-session memory as plain Markdown per workspace: weighted injection, bi-temporal invalidation, TTL review with stale markers, credential redaction, error and session retrospectives, SOP skills, and approval-gated self-improvement proposals.

1last monthMemoryMIT
D

dsh-loom

darknessled/dsh-loom

Human-in-the-loop self-improvement loop: one objective becomes an auditable work chain that iterates in child sessions while the main agent stays idle.

06 hours agoWorkflow & AutomationMIT
A

dsh-fathomkernel

az13js/dsh-fathomkernel

Self-evolution algorithm optimization plugin for DeepSeek Harness: You only declare the objectives and acceptance criteria. For personal use, stability is not guaranteed under the current status.

016 days agoWorkflow & AutomationMIT
Z

zagent

z-asset/zagent

Zagent — unified three-role self-improvement loop with three operators. Data-RSI (daily cross-sectional cleaning: winsorize → cross-sectional standardization → median fill, plus experience extraction), Harness-RSI (evolves system prompt / memory / skills), and Model-RSI (evolves alpha training recipes via framework-native walk-forward with 2-day gap and multi-seed). Offline one-command run, GPU auto-detect. Ships one skill.

02 months agoWorkflow & Automation
T

dsh-self-evolution

tommy00748/dsh-self-evolution

Bounded self-managed long-term memory (Hermes-style MEMORY.md / USER.md with hard character limits and a safety scan), a review that runs after every turn and writes plain-language notes or refines an existing skill instead of adding a near-duplicate, a curator that finds and surgically repairs skills the loader would silently discard, cross-session search over past messages, and a learning card above the composer that appears only when there is news and asks before it deletes or rewords a memory.

02 months agoMemoryMIT
Z

alpharsi

z-asset/alpharsi

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

02 months agoWorkflow & Automation
M

dsh-missher-evolution

missher12/dsh-missher-evolution

Records scoped workflow rules and correction reminders with bounded evidence, local settings, and optional Brain Hub integration.

0last monthWorkflow & AutomationMIT
D

dsh-refine

dushaobindoudou/dsh-refine

DeepSeek Harness (dsh) plugin: /refine command + settings panel for the dsh-continual-harness self-refinement engine — entry browsing, refinement history timeline, one-click rollback, auto-gate audit; engine optional at runtime.

03 months agoDev & Plugin ToolsMIT