🖥️ Agent-project workbench for DeepSeek Harness — sidebar app drawer + dockable split workspace + a live control room watching every project.

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.

An everyday AI assistant you can leave running: in your terminal, on a schedule, and in your chat apps.

Shorter replies with Claude Code. Save output token spend.

Open-source alternative to Claude Cowork — a local-first AI agent desktop app · multi-model · self-evolving skills · privacy-first · multi-Harness roadmap · DeepSeek Harness integration in progress

Let Claude Code reach you on Telegram when it finishes work or needs decisions

芊云全景 Skills 技能管理平台 CLI：统一存储 ~/.agents/skills + 按需软链（--claude/--local），一条命令安装/更新/发布团队 Skills，内置私有源

Full-stack consulting skill for Claude Code — 6 AI agents, 16 strategy frameworks, CPA-level financial modeling, zero hallucinations

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. Part of Gen Agent Trust Hub.

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

🎬 Full video production studio for Remotion — for Claude Code, Codex, Gemini CLI & any Agent Skills agent. AI voiceovers, music, stock footage, image/video generation, TikTok captions, transitions & AI review loop. 15 skills, 5 MCP servers. Free & open source by Dojo Coding.

Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals.

Can AI engines cite your site, and do they? Free 0–100 readiness score on an open GEO rubric, plus ask and weekly citation tracking via OpenAI, Perplexity, Gemini, Anthropic and OpenRouter with your own keys. Zero dependencies; CLI, GitHub Action and MCP server.

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Website: https://apirelayaudit.com

ADHD-friendly study companion agent for Claude Code: spaced repetition, small-chunk teaching, Feynman reflection

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.

Enables AI agents to generate studio-grade fashion photography and 4K motion-captured video, perform garment try-ons and background edits, and export creative assets to commerce, productivity, and social platforms.

Fork of @deepseek-ai/dsh-agent-instructions that delivers the workspace instruction baseline as system-prompt sections, keeping the upstream mid-session reminder path.

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log

Heartbeat plugin for DeepSeek Harness: scheduled autonomous reflection loop with user profile, material pool, pace gate, and gated proactive expression.

CrawlForge MCP Server - Professional Model Context Protocol server with 31 web scraping, crawling, deep-research, and autonomous-extraction tools. Returns clean Markdown and structured JSON for Claude, Cursor, and any MCP client. Defaults to local Ollama