A curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表
Every tracked project
138 projects tracked. Filter by category, language, and trend.
- HealthyExperimentalPop0Python#awesome#awesome-list#deepseek-harness6.0k922
An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.
HealthyMaturePop0Python#physics-simulation#robotics#nvidia-warp5.4k640A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
HealthyEnterprisePop0Python#agent#llm#scanner5.0k482Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
HealthyMaturePop0Python#ai-agents#llm#self-hosted4.6k690A unified inference and post-training framework for accelerated video generation.
HealthyMaturePop0Python#diffusers#diffusion-models#video-generation4.0k4101M real LLM conversations with human preferences (research dataset).
SlowingMaturePop0Python#dataset#llm#research3.8k380TSP自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | 基于 TickFlow 数据源 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源 ,非第三方官方项目
HealthyEarlyPop0Python#a-stock#ai-agent#aigc3.8k877PipesHub is an open-source fully extensible AI context layer that unifies your business data for explainable enterprise search and agentic workflow automation.
HealthyEnterprisePop0Python#agent#agents#glean3.4k513Open-source framework for the research and development of foundation models.
HealthyMaturePop0Python2.1k191Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
HealthyMaturePop0Python#python#fine-tuning#gguf2.0k301Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
HealthyExperimentalPop0Python#agent#agent-memory#agent-skill1.2k142Remove multi-vendor AI provenance traces: Unicode text sanitization, statistical rewriting techniques, and C2PA/metadata stripping from PNG/JPEG/SVG/PDF/DOCX/HTML/MD files
HealthyExperimentalPop0Python#claude#claude-code#claude-skills91294- Pop0Python#diy#golf#radar900101
Salesforce's curated collection of agent skills for building applications. Optimized for Agentforce Vibes, compatible with all AI tools.
HealthyMaturePop0Python892305Offline vanity address generator for Bitcoin and Ethereum. CPU multi-process search with interactive CLI menu. Supports Legacy, Nested SegWit, Native SegWit, Taproot, and ETH (EIP-55).
HealthyExperimentalPop0Python80391Purge multi-vendor AI watermarks: clean Unicode text, apply statistical rewrite hooks, and clear C2PA plus metadata from PNG, JPEG, SVG, PDF, DOCX, HTML, and MD.
HealthyExperimentalPop0Python#claude-ai#claude-code#claude-code-plugin76072DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.
HealthyExperimentalPop0Python#agent#ai#ai-agents637226Offline utilities for Coldcard hardware wallet users: PSBT inspection, BIP39/dice entropy, Seed XOR split/combine, BBQr encode/decode, output descriptors, and firmware verification guidance. Companion to official Coldcard firmware. Not affiliated with Coinkite.
HealthyExperimentalPop0Python#airgap#airgap-devkit#airgap-download60779Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.
HealthyExperimentalPop0Python#a2a#agent-orchestration#agent-routing60710Community plugin marketplace for Claude Cowork and Claude Code. Read-only mirror — submit plugins at clau.de/plugin-directory-submission.
HealthyEarlyPop0Python604108AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
HealthyMaturePop0Python589158An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.
HealthyExperimentalPop0Python5761🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
HealthyExperimentalPop0Python#agent-orchestration#ai-agents#harness56356The simplest, thinnest harness that gives an LLM complete freedom to control a Mac.
HealthyExperimentalPop0Python#accessibility#agent#automation52636- Pop0Python#cpanel#cve#cve-2026-4194050296
Awesome skills for submitting url to free websites. Get more backlinks for your website to get more traffic.
HealthyExperimentalPop0Python#backlinks#codex#codex-skill468171- Pop0Python43415
ChatGPT Plus automation toolkit: PyQt6 desktop + JSON-RPC registration engine + card/CDK/PayPal/GCash flows
HealthyExperimentalPop0Python42968Free open-source extractor for AI coding assistant chat histories. Supports Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code, and more.
HealthyExperimentalPop0Python#ai#ai-data-extractor#claude37697- Pop0Python3741.3k
How GitPop ranks projects
Read the full methodology- What is PopScore?
- A 0–100 score combining star velocity (35%), fork engagement (20%), activity (25%), mentions (10%), and a noise filter (10%). Details →
- Why not just use GitHub Trending?
- Trending is dominated by awesome-* lists and tutorial repos. We weight commits and merged PRs above raw stars, and apply a noise penalty for content-only repos. Details →
- How is the AI Snapshot generated?
- An LLM summarizes each repo's README into strict JSON — TL;DR, 3 key features, difficulty rating. Cached and refreshed automatically. Details →