— · MIT
Audit and fix your Mac's security in one command. No agent, no signup, open source.
v3.0.2 · MIT
:rocket: The Ultimate Image Uploader for Efficient Creators. Supports Obsidian, Typora, VS Code etc. and 60+ image hosting services (S3, GitHub, Cloudflare R2, Imgur, Aliyun OSS...). Paste, upload, done.
v3.8.2 · MIT
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.
v1.12.2 · MIT
DeepSeek Harness 用量与消耗插件(dsh-usage-plugin)—— 每次调用的 token 用量/缓存命中统计、峰谷计费、余额查询、CSV/JSON/PNG 导出,可经桌面端一键安装或命令行 dsh plugin add 安装。
— · AGPL-3.0
Yet another WebUI for Nginx
— · MIT
🤫 Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.
v0.5.0 · MIT
深迹 DeepTrace — Your Agent, in numbers. DSH 插件:从会话事件日志生成日报/周报/月报/年报/自定义区间,确定性洞察与协作复盘,只读、不改写历史。
v1.0.6 · MIT
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
v0.8.1 · MIT
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
v0.5.0 · MIT
Claude Code plugin that shows live session status (⚡ running / 💤 idle / 🔴 attention) in your iTerm2 tab title — no config needed, just install and go.
v0.2.0 · Apache-2.0
🐳 DeepSeek Harness Desktop
v1.0.2 · MIT
DSH - Dseam
v1.2.1 · MIT
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
v0.3.2 · CC0-1.0
DeepSeek Harness 独立社区插件商店:发现、安装并提交经过验证的插件、工具与扩展。 | Independent community plugin directory.
v0.1.25 · MIT
DeepSeek API 高峰/闲时(峰谷)计价标记 for DSH Web: 会话头部显示当前处于高峰还是闲时(半价)时段
— · GPL-3.0
小红书(XiaoHongShu、RedNote)链接提取/作品采集工具
— · Apache-2.0
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
v1.5.9 · MIT
clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.
— · Apache-2.0
Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.
v1.4.0 · MIT
⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.
— · MIT
Build, test, and archive Swift packages and Xcode projects for Apple platforms with Claude Code.
v0.3.0 · MIT
Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.
v1.10.0 · no license
Cross-session context for Claude Code. CLI + MCP server + /story skill that tracks tickets, issues, handovers, and roadmap in a .story/ directory.
— · MIT
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.