The AI tools that matter — tracked, explained, no hype.
Universal, model-agnostic operating harness for AI agents, providing a lean core and work-type profiles assembled by one setup script.
★ 254AIHOT is a self-hosted news aggregator and RSS reader that uses AI to summarize and categorize articles.
★ 8,733An agent skill that answers hard questions with a one-page HTML you can actually read.
★ 4,544Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training.
★ 1,253All-in-one RAG and AI agent platform combining document chat, multi-tool agents, and knowledge retrieval in a unified interface.
★ 62,300ARTEX is a multi-agent system for autonomous penetration testing in an isolated lab.
★ 1,450Open-source personal finance app with an AI financial advisor to track net worth, investments, ETFs, cash, and debts on your own computer.
★ 324A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
★ 2,482A curated list of tools built for Jev, TypeSafe AI's System One model for typed decisions.
★ 648Cindy is an open-source AI agent that works out of the box, doing real work on your own computer.
★ 2,386Anthropic's terminal-native agentic coding tool that understands your entire codebase and executes development tasks through natural language commands.
Free, open-source VS Code AI agent extension offering autonomous coding with transparent human-in-the-loop control and 30+ LLM provider support.
★ 65,626Powerful node-based interface for Stable Diffusion and diffusion models with production-grade capabilities.
★ 70,000Open-source AI coding assistant for VS Code and JetBrains IDEs with flexible model switching — archived June 2026 after Cursor acqui-hired the team.
★ 34,900AI-first code editor built on a VS Code foundation with multi-model support, autonomous agents, and composer-style multi-file editing.
Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.
★ 823A handbook for DeepSeek Harness, a plugin-based framework for running agents.
★ 785DeepSeek Harness EAC is a Windows/Linux desktop client with a bundled Node.js and dsh CLI for one-click launch and 10 built-in UI skins.
★ 855Benchmark evidence that J-Space reduces capability-realization loss on DeepSeek V4.
★ 1,019Run full Kimi K3 on a single device with an OpenAI-compatible API server for local chat and coding agents.
★ 673Open-source platform for building production-ready AI applications with workflow, RAG, and agent capabilities.
★ 151,335Open-source dots for the web: an AI agent with its own browser, one that does not get blocked.
★ 2,630A local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.
★ 587Install this plugin in dsh to use frontier models like DeepSeek V4.1 Flash and Kimi K3 for free, with no usage cap.
★ 46,675Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model.
★ 4,005The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest.
★ 2,228Flawless is an AI-native SRE control plane for Kubernetes and cloud infrastructure, connecting alerts, evidence, topology, human approval, controlled remediation, and recovery verification in one auditable AgenticOps loop.
★ 861Open-source visual LLM workflow builder for creating AI agents and RAG applications without coding.
★ 53,400A Codex-based AI agent that provides relationship advice and analysis based on user input.
★ 2,298Transform Chinese architecture, cultural places, and travel photos into art-directed editorial posters with GPT Image.
★ 478Open-source desktop AI chat application that runs 100% offline with support for local and cloud-connected models.
★ 43,600A chat assistant that can read out messages and provide responses in various apps, including WeChat and QQ.
★ 8,124Run Kimi K3 locally on CPU with ~55GB measured runtime RAM, a single-file Linux inference server powered by cPilot Runtime.
★ 1,013A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM, portable C99 with no dependencies.
★ 6,954Open-source framework for building LLM-powered applications with 700+ integrations and agent orchestration.
★ 124,000A comprehensive learning path for large language models, from foundation to application and interview.
★ 1,270Desktop application with native GUI for running and managing local language models with built-in REST API and developer tools.
★ 5,100One place to pick every agent's model: Codex on DeepSeek, Claude Code on Kimi, Gemini CLI on GLM, from the menu bar.
★ 23,538A one-ink and controlled two-ink editorial image skill for posters, zines, portraits, packaging, and visual field notes.
★ 2,744MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
★ 918Open-source, self-hosted workflow automation platform with 400+ integrations and native AI capabilities.
★ 108,000Open-source framework for running large language models locally on consumer hardware with zero dependencies.
★ 173,000Self-hosted, privacy-focused AI chat interface supporting Ollama, OpenAI APIs, and local LLMs with an extensible plugin framework.
★ 124,000OpenChatCut is a local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion-powered rendering.
★ 1,524An open-source coding agent for the CLI that runs anywhere and uses anything.
★ 569The open-source AI workbench for scientific research
★ 2,662Paw Work - selection-first web agent for Chrome: select on the live page, describe the outcome, take away an editable office file.
★ 2,882A TypeScript coding agent that can read and write code, and is designed to be a pi-agent.
★ 1,209A 15-step textbook project that guides users through building a Pi-style coding agent from scratch.
★ 1,301Open-source app builder engine — intent to working app
★ 333Open-source Grok Bot alternative that allows users to choose their own model and sandbox, with web, desktop, and mobile support.
★ 2,519Continual learning infra for self-improving agents
★ 7,580Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence.
★ 1,252De-AI writing skill for any Agent Skills-compatible agent, with native plugins for Claude Code, Codex, Grok Build, and Antigravity.
★ 2,911A design system for AI applications with a refined glass-inspired aesthetic.
★ 2,413Your personal AI agent in your own Cloudflare account, with chat, memory, tasks, notes, and scheduled reminders.
★ 1,355UNIGIT is an AI workbench built for real work, bringing models, tools, files, and project context into one clear environment.
★ 1,135Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg.
★ 1,366OpenAI's robust speech-to-text model trained on 680K hours of multilingual audio data.
★ 105,000A practical, open-source guide to mastering WorkBuddy through real-world workflows.
★ 2,338Agent Skill for Refining AI-Generated Japanese into Natural Japanese
★ 2,601