tafcear/kimi-tide
kimi-tide is a tool for DeepSeek Harness. ð kimi-tide â DSH's "auto-select a model at every step" plugin: images go to a model that can see them, coding goes to a coding model, chit-chat and translation go to a cheap model; the panel shows who was picked and why each time · The per-step model router for DeepSeek Harness: any connected model, routed by your rules
REVIEW SCORECARD
â No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A well-documented, actively maintained per-step model router that solves real multi-model switching pain in DSH.
README documents a build/test/pack pipeline (npm install && npm run build && npm pack), a CI badge, an interactive source-traceable architecture diagram, and a dedicated router architecture doc, indicating solid engineering structure.
README states API keys are stored by DSH and 'never written into any plugin config file', and install uses a local .tgz rather than a remote download-and-execute, though no independent security audit is shown.
It directly addresses concrete, common pain points (screenshot messages failing on text-only models, forgetting to switch back after switching, and quota burn) with per-step routing, @-directives, and a decision panel.
Last updated 2026-08-23 with a current version v1.2.1 (2026-09-11), a CHANGELOG, release-evidence docs, and a stated roadmap, indicating active maintenance.
README provides prerequisites, install commands, preset/rule tables, a 30-second acceptance test, an FAQ covering limitations and migration, and a documentation index, making it easy to install and use.
Generated by AI after reading the project README â a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
dsh plugin --profile web add ./dsh-kimi-tide-<version>.tgzThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
VALIDATION LADDER
FAQ
ð kimi-tide â DSH's "auto-select a model at every step" plugin: images go to a model that can see them, coding goes to a coding model, chit-chat and translation go to a cheap model; the panel shows who was picked and wh
kimi-tide has 7 stars and 1 forks on GitHub, last updated 2026-09-03.
kimi-tide is distributed under the MIT license.
kimi-tide is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:dsh-pluginã
YuJunZhiXue
DeepSeek Harness ç Žç²ïŒè®©æææš¡åéœèœç Žç²ïŒäžåæš¡åå¯æ¢äžåæ瀺è¯ïŒé»è®€æ瀺è¯é¢ååœæš¡ãå°ç é ±ããJailbreak for every model â swap prompts per model. æ± Star æ¶è â
EthanYoQ
AI novel writing software: organizes inspiration, characters, worldbuilding, outlines, chapter writing, review, and revision into a controllable workflow; offers Windows/macOS desktop versions and Ollama and DSH plugin previews.
agentrq
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness.
sandbaseai
Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.
vibeinging
DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.
syncable-dev
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.