#typescript #ai #ai_agents #ai_memory #anthropic #artificial_intelligence #claude #claude_agent_sdk #claude_agents #claude_code_plugin #claude_skills #codex #embeddings #long_term_memory #memory_engine #openclaw #openclaw_skills #postgres #rag

Hivemind is a shared memory system for coding agents that saves prompts, tool calls, and replies, then turns repeated patterns into reusable skills for the whole team. It can make agents faster and cheaper, improve recall, and help you search past work, reuse solutions, and keep team rules and goals in one place.

https://github.com/activeloopai/hivemind

#c_lang #aider #ast #claude_code #code_analysis #code_intelligence #codex #cursor #cypher #developer_tools #gemini_cli #graph_visualization #kilocode #knowledge_graph #mcp #mcp_server #model_context_protocol #opencode #sqlite #tree_sitter #windsurf

This is a fast, local code tool that builds a smart map of a codebase, so you can find functions, calls, routes, and dependencies in seconds instead of reading files one by one. It works on macOS, Linux, and Windows, supports many languages, and helps you understand changes, reduce wasted tokens, and save time while coding.

https://github.com/DeusData/codebase-memory-mcp

#python #agent #agentic_ai #ai #claude #copilot #cursor #elevenlabs #ffmpeg #flux #image_generation #open_source #openai #python #remotion #stable_diffusion #text_to_speech #text_to_video #video_generation #video_production

OpenMontage turns a plain idea or even a reference video into a full video production workflow, handling research, script writing, asset creation, editing, captions, and final rendering. Your benefit is faster video creation with lower cost, more control, and fewer surprises, because it can use free/open footage or AI tools, estimate cost first, and check quality before showing you the result.

https://github.com/calesthio/OpenMontage

#swift #ai_video #claude #macos #mcp #seedance2 #swift #video_editor

Palmier Pro is a free, open-source Mac video editor made for AI. You can edit videos in a timeline, generate images and video inside the editor, and let tools like Claude, Codex, or Cursor help with the work through MCP. The main benefit is that you can create and edit faster in one place, without switching between different apps. It works on macOS 26 with Apple Silicon only, and the AI generation features need a login and subscription.

https://github.com/palmier-io/palmier-pro

#typescript #ai #ai_agents #ai_tools #automation #boilerplate #claude #claude_code #clone #developer_tools #nextjs #react #reverse_engineering #shadcn_ui #skills #tailwindcss #template #typescript #web_scraping #website_clone

This template helps you rebuild a website into a clean Next.js app with AI coding tools. You point it at a URL, run `/clone-website`, and it finds the design, downloads assets, writes component plans, and builds the site in parts, which saves time and helps you recreate a site more accurately.

https://github.com/JCodesMore/ai-website-cloner-template

#typescript #ade #agent_ide #ai_agents #claude_code #cli #codex #cursor_agent #devtools #ghostty #ide #mobile_app #opencode #orchestration #parallel_agents #pi #terminal #worktrees #yc_backed

Orca is an open-source AI development environment that lets you run multiple coding agents like Claude Code or Codex side-by-side in isolated worktrees, monitor them from your phone, and merge the best results. You benefit by saving time avoiding repetitive tasks, comparing AI outputs instantly, and building faster without switching contexts, all while using any CLI agent you prefer on macOS, Windows, or Linux.

https://github.com/stablyai/orca

#rust #agent #agent_orchestration #ai #ai_agents #claude_code #cli #codex #coding_agents #developer_tools #devtools #multiplexer #rust #terminal #terminal_multiplexer #terminal_ui #tmux #tui #workspace_manager

Herdr is a single Rust terminal multiplexer that lets you run multiple AI coding agents in real panes with live status tracking, showing exactly who is blocked, working, done, or idle. Your benefit is effortless management: you see all agents in one terminal, detach and reattach without losing work, and use mouse-native controls plus remote SSH access, so nothing dies when you close your laptop and you always know which agent needs help.

https://github.com/ogulcancelik/herdr

#python #antigravity #claude_code #codex #gemini #graphrag #knowledge_graph #leiden #openclaw #rag #skills #tree_sitter

Graphify is an AI tool that maps your entire project—code, docs, PDFs, images, and videos—into a searchable knowledge graph instead of forcing you to grep through files. You simply type `/graphify .` in your AI coding assistant (like Cursor, Claude, or Copilot) to get three outputs: an interactive HTML map, a report with key concepts and surprising connections, and a JSON file for instant queries. The main benefit to you is that you can instantly ask complex questions like "what connects auth to the database?" and get precise answers from the graph, saving hours of manual file searching and helping you understand your project's architecture faster.

https://github.com/safishamsi/graphify

#csharp #ai #ai_integration #anthropic #claude #copilot #cursor #game_development #gamedev #gemini #llm #mcp #model_context_protocol #openai #unity #unity3d #videogames

MCP for Unity lets you control your Unity Editor using natural language with AI tools like Claude, Cursor, or VS Code. You can create scenes, edit scripts, manage assets, and run tests just by typing prompts. The benefit to you is faster game development because AI automates repetitive tasks, so you spend less time on manual work and more time creating your game. It is free under the MIT license and works with any MCP client.

https://github.com/CoplayDev/unity-mcp

#python #agent_skills #agentic_ai #ai_agents #autonomous_agents #claude #claude_code #claude_skills #codex #coding_agent #context_engineering #copilot #cursor #developer_tools #github_copilot #llm_agents #long_running_agents #manus #multi_agent_systems #pi #planning

This tool makes your AI coding agent keep a plan in files like `task_plan.md` so it never loses its goals when context fills up, you run `/clear`, or it crashes. You get a working memory on disk that auto-recovers past sessions and holds the agent until the plan is truly done, letting complex, multi-step tasks finish reliably without goal drift or repeated errors.

https://github.com/OthmanAdi/planning-with-files