Agents, MCPs, skills, and plugins worth running, curated daily. Test-drive anything without wrecking your setup.
93 projects found
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FL...
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.. An open-source agent for the AI coding ecosystem.
Open source inference server that runs the best local models for your hardware, plugged into the agent you already us...
Open source inference server that runs the best local models for your hardware, plugged into the agent you already use. Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My …
Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins
Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image...
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
Open-source inference server and production cluster for all the models your agent needs.
Open-source inference server and production cluster for all the models your agent needs.
Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission de...
Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log.
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors. An open-source agent for the AI coding ecosystem.
Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/
Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/. An open-source agent for the AI coding ecosystem.
Help AI coding agents write modern Go
Help AI coding agents write modern Go
local multi-agent harness
local multi-agent harness. An open-source agent for the AI coding ecosystem.
DSH 官方公众号收录的 TUI 补位插件:Claude Code 风,鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plu...
DSH 官方公众号收录的 TUI 补位插件:Claude Code 风,鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plugin — Claude Code style: whale bar, live status, streaming thoughts, dou…
An operating system for AI agents. Plug in the agent CLIs you already use (Claude Code, Codex, Gemini CLI, Cursor) an...
An operating system for AI agents. Plug in the agent CLIs you already use (Claude Code, Codex, Gemini CLI, Cursor) and they become a team: they split the work, hand tasks to each other, run…
Agent Substrate: the core system
Agent Substrate: the core system
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS...
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, cha...
Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, p…
编程笔记、 AI 学习、观影指南、读书笔记、生活感悟、游戏记录
编程笔记、 AI 学习、观影指南、读书笔记、生活感悟、游戏记录
Open-source ETL/ELT you deploy on your own servers or cloud. Built on DuckDB: no-code/low-code visual pipelines or SQ...
Open-source ETL/ELT you deploy on your own servers or cloud. Built on DuckDB: no-code/low-code visual pipelines or SQL, 385 components, dbt, CDC, data quality, reverse ETL, lineage, MCP for…
Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.
Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nod...
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Ed…
A native app for all your coding agents.
A native app for all your coding agents.
Secrets management for teams and AI agents.
Secrets management for teams and AI agents.
Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video work...
Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.
30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.
30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.
A GUI that runs on your Openclaw host and lets you totally manage it without touching the CLI. Not a technical user?...
A GUI that runs on your Openclaw host and lets you totally manage it without touching the CLI. Not a technical user? Deploy it on agentbay.space
Run Pi and Claude Code directly in Codex Desktop. 在 Codex Desktop 中直接运行 Pi 和 Claude Code。
Run Pi and Claude Code directly in Codex Desktop. 在 Codex Desktop 中直接运行 Pi 和 Claude Code。
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + option...
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.
Give cloud AI agents a real development environment on your own machines.
Give cloud AI agents a real development environment on your own machines.
Open-source workspace manager for AI coding CLIs: Claude Code and ChatGPT Codex in one browser app. Discovers every s...
Open-source workspace manager for AI coding CLIs: Claude Code and ChatGPT Codex in one browser app. Discovers every session on disk, embedded terminals, phone-ready, cost tracking, kanban, …
Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you fini...
Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you finished, summarised daily, and automatically drafts your project tickets fo…
Make WordPress as an AI operating system, every plugin becomes an agentic tool The "online Claude" vision — natural l...
Make WordPress as an AI operating system, every plugin becomes an agentic tool The "online Claude" vision — natural language → classify → plan → multi-step execution across plugins, zero co…
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.
A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agen...
A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, tmux alternative, Remote Linux VPS supported
Turn any research paper into a commercialization report — 6 AI agents, TRL/MRL scoring, patent landscape, market inte...
Turn any research paper into a commercialization report — 6 AI agents, TRL/MRL scoring, patent landscape, market intelligence, verified citations. DeepSeek / OpenAI / Claude.
Automated quality checks that nudge AI coding agents toward better habits
Automated quality checks that nudge AI coding agents toward better habits
Build an AI agent harness in Rust, from a minimal loop to tools, subagents, memory, teams, worktrees, MCP, and type...
Build an AI agent harness in Rust, from a minimal loop to tools, subagents, memory, teams, worktrees, MCP, and typed tool routing.
It's like Hermes Agent & OpenClaw but designed to work nicely with teams.
It's like Hermes Agent & OpenClaw but designed to work nicely with teams.
Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatib...
Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatible; runs on Cloudflare Workers/Durable Objects or Node.js. Apache 2.0.
AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face reco...
AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts. Cloud LLMs or fully local via…
The open-source operating system for robots — install it and your robot comes alive
The open-source operating system for robots — install it and your robot comes alive
Metrik 是一款桌面常驻工具,统一查看本机各个 AI 编程 Agent 的官方配额余量与 Token 消耗,支持 ChatGPT、Claude、GLM、Kimi 等主流 Agent。
Metrik 是一款桌面常驻工具,统一查看本机各个 AI 编程 Agent 的官方配额余量与 Token 消耗,支持 ChatGPT、Claude、GLM、Kimi 等主流 Agent。
Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor an...
Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.
Rove — the agent multiplexer for your terminal. Run coding agents on parallel tasks with isolated worktrees and persi...
Rove — the agent multiplexer for your terminal. Run coding agents on parallel tasks with isolated worktrees and persistent sessions.
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-...
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.. An open-source agent …
Dragonclaw: Maybe the best openclaw client. Built with Electron+SQLite, it doesn't touch OpenClaw's code but adds mul...
Dragonclaw: Maybe the best openclaw client. Built with Electron+SQLite, it doesn't touch OpenClaw's code but adds multi‑agent, high‑concurrency, DAG workflows. No prompt tuning needed (pre‑…
You write the specs. It clears the board: coding agent chains plan, review, implement, verify and merge unattended on...
You write the specs. It clears the board: coding agent chains plan, review, implement, verify and merge unattended on your own machine, on the GPT and Claude subscriptions you already have.
Token-efficient MCP CLI client. 97% less tokens on tool discovery, 40-60% on results. Zero deps. Cross-platform. Work...
Token-efficient MCP CLI client. 97% less tokens on tool discovery, 40-60% on results. Zero deps. Cross-platform. Works with every AI agent.
Every file not opened. Every folder not explored. ProjectAtlas guides coding agents with purpose metadata and an inte...
Every file not opened. Every folder not explored. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%.
A secure, stable, and lightweight alternative to OpenClaw and Hermes.
A secure, stable, and lightweight alternative to OpenClaw and Hermes.
Build your own software factory with AI agents
Build your own software factory with AI agents
A high-performance Rust implementation orchestration loop for LLM-driven tool execution.
A high-performance Rust implementation orchestration loop for LLM-driven tool execution.
本地优先的类飞书 Markdown 编辑器,内置可审改的 AI 助手 | Local-first WYSIWYG Markdown editor with a reviewable AI agent
本地优先的类飞书 Markdown 编辑器,内置可审改的 AI 助手 | Local-first WYSIWYG Markdown editor with a reviewable AI agent
Talk to your coding agents by voice. Realtime, fully local macOS dictation that streams words as you speak and ground...
Talk to your coding agents by voice. Realtime, fully local macOS dictation that streams words as you speak and grounds LLM polishing in the exact Claude Code session under your cursor — Gho…
CNE · 本地可日更的 A 股研究湖 · 42 数据集 · MCP 供数 AI agent · 零 token 零注册 | Local A-share research lake — history for humans & agents
CNE · 本地可日更的 A 股研究湖 · 42 数据集 · MCP 供数 AI agent · 零 token 零注册 | Local A-share research lake — history for humans & agents
Run Claude Code, Codex, Gemini and any other CLI Agent with upto 86% fewer tokens and 92% fewer tool calls
Run Claude Code, Codex, Gemini and any other CLI Agent with upto 86% fewer tokens and 92% fewer tool calls
Tag any agent, wherever work happens, your agents work alongside your team and each other, learning as they go.
Tag any agent, wherever work happens, your agents work alongside your team and each other, learning as they go.
A Fully free agentic browser driver for AI, few tools, full control, real stealth, top-tier token efficiency.
A Fully free agentic browser driver for AI, few tools, full control, real stealth, top-tier token efficiency.
Understand what your AI agents are building. Agent-native, human-sovereign ontology workbench — one markdown graph hu...
Understand what your AI agents are building. Agent-native, human-sovereign ontology workbench — one markdown graph humans and coding agents read, write, and keep fresh together. Local-first…
Verified, project-aware AWS contexts for any CLI or AI coding agent.
Verified, project-aware AWS contexts for any CLI or AI coding agent.
From ticket to reviewed pull request. Free and open-source, on your machine.
From ticket to reviewed pull request. Free and open-source, on your machine.
AI-Powered Zettelkasten Desktop Agent — local-first second brain with hybrid search, AI agents, knowledge graph, and...
AI-Powered Zettelkasten Desktop Agent — local-first second brain with hybrid search, AI agents, knowledge graph, and intelligent canvas. Fully offline out-of-the-box.
Best ready-to-run DeepSeek Harness distribution: DSH desktop GUI, terminal TUI, and harness integration.
Best ready-to-run DeepSeek Harness distribution: DSH desktop GUI, terminal TUI, and harness integration.
The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observabil...
The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observability, and audit trails
BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without a...
BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.
Tmux plugin that gives visual feedback for AI agent states (running/needs-input/done). Supports Claude Code, Codex,...
Tmux plugin that gives visual feedback for AI agent states (running/needs-input/done). Supports Claude Code, Codex, and custom agents. Pane borders, window title colors, status bar icons.
Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage a...
Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota r…
ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.
ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.
A block-based content engine and bilingual blog backend for Laravel Gutenberg-style editor, media library, post temp...
A block-based content engine and bilingual blog backend for Laravel Gutenberg-style editor, media library, post templates, roles, and an AI writing assistant, with zero host coupling.
Run AI coding agents in secure, isolated microVMs. Sub-125ms boot times, real hardware isolation.
Run AI coding agents in secure, isolated microVMs. Sub-125ms boot times, real hardware isolation.
OpenCode plugin: image generation via your ChatGPT subscription or OpenAI API
OpenCode plugin: image generation via your ChatGPT subscription or OpenAI API
Open bridge layer connecting local AI Agent CLIs to web, H5, mini programs, apps, IM, and custom clients.
Open bridge layer connecting local AI Agent CLIs to web, H5, mini programs, apps, IM, and custom clients.
AI 编程智能体统一桌面工作台 | Desktop hub for managing Claude Code, Codex CLI, Gemini CLI & OpenCode. Tauri 2 · Rust · React · SQ...
AI 编程智能体统一桌面工作台 | Desktop hub for managing Claude Code, Codex CLI, Gemini CLI & OpenCode. Tauri 2 · Rust · React · SQLite.
When a cluster heats up, a stack shift is starting.