A Python/Rust rewrite of Claude's agent harness system for building AI tool workflows. Created as a clean-room implementation after Claude's code was leaked, focusing on harness engineering and agent orchestration patterns.
An open-source AI agent that runs locally and automates complex development tasks from start to finish. Beyond code suggestions, it can build entire projects, write and execute code, debug issues, and interact with external APIs autonomously.
An AI-powered coding assistant that lives in your terminal and understands your entire codebase. It helps developers code faster by executing routine tasks, explaining complex code, and handling git workflows through natural language commands.
AI pair-programming in your terminal. Edits files, makes commits, works with any LLM.
A personal knowledge management system that creates a searchable, AI-powered "memex" from your markdown files, notes, meetings, and calendar data. Uses Postgres + pgvector for hybrid search and integrates with AI agents to continuously enrich and maintain your knowledge base.
An open-source platform that turns AI coding agents like Claude Code and Codex into real teammates. Assign tasks to agents like human colleagues, track their progress on a board, and let them autonomously write code, report blockers, and compound skills over time.
A coding agent from OpenAI that runs locally in your terminal, providing AI-powered assistance for development tasks. Works with ChatGPT plans or API keys and offers multiple deployment options including IDE integration and desktop app.
A comprehensive performance optimization system for AI coding agents that provides skills, memory management, security scanning, and research-first development patterns. Works across multiple AI agent harnesses including Claude Code, Codex, Cursor, and OpenCode with production-ready configurations evolved from 10+ months of intensive daily use.
A self-improving AI agent with a built-in learning loop that creates skills from experience, improves them during use, and builds a deepening model of users across sessions. It runs anywhere from a $5 VPS to GPU clusters and works with any LLM provider.
An open-source super agent harness that orchestrates sub-agents, memory, and sandboxes to handle long-horizon tasks that can take minutes to hours. Supports research, coding, and creative tasks with extensible skills and tool integrations.
A comprehensive AI development toolkit that turns Claude Code into a virtual engineering team with 23 specialized roles including CEO, designer, engineer manager, QA lead, and security officer. Provides structured workflows for product planning, code review, testing, and deployment through slash commands.
An open-source Python library that enables AI agents to interact with web browsers through natural language commands. Automates complex web tasks like form filling, shopping, and data extraction using LLMs to control browser actions.
A Claude Code plugin that automatically preserves context across coding sessions by capturing tool usage, compressing it with AI, and injecting relevant context back into future sessions. Enables Claude to maintain continuity of knowledge about projects even after sessions end.
A comprehensive monorepo providing tools and libraries for building AI agents, including a unified LLM API, coding agent CLI, terminal/web UIs, and deployment management for GPU pods. Offers everything needed to create, deploy, and manage AI agents across different platforms.
An AI teacher that lives next to your cursor on Mac, can see your screen, and provides real-time guidance by talking to you and pointing at UI elements. Like having a personal tutor watching over your shoulder.
A native desktop development environment that lets you work with AI agents on an infinite canvas. Arrange terminals, code files, and running agents side-by-side without context switching or tab hunting.
A collection of specialized marketing skills for AI coding agents, covering CRO, copywriting, SEO, analytics, and growth engineering. Built for technical marketers and founders who want AI agents to help with marketing tasks using structured markdown skills that provide frameworks and best practices.
A distributed graph issue tracker designed for AI coding agents that provides persistent, structured memory using a dependency-aware graph. It replaces messy markdown plans and allows agents to handle long-horizon tasks without losing context.
A framework for training and optimizing AI agents using reinforcement learning and other algorithms. Supports any agent framework with minimal code changes and enables selective optimization of multi-agent systems.
Microsoft's MCP server for Playwright. Lets agents drive a browser via tool calls.
Open-source multimodal AI agent stack that lets you control computers and browsers through natural language commands. Connects cutting-edge AI models with real-world tools through desktop applications and CLI interfaces.
Open source AI chat platform that works with any LLM and includes advanced features like RAG, web search, custom agents, and connectors to 40+ knowledge sources. Can be self-hosted in completely airgapped environments.
Agent-native personalized learning assistant that combines unified chat workspace, autonomous TutorBots, AI co-writing, and guided learning paths. Features persistent memory and knowledge bases to create adaptive, context-aware tutoring experiences.
Dexter 🤖 Dexter is an autonomous financial research agent that thinks, plans, and learns as it works. It performs analysis using task planning, self-reflection, and real-time market data. Think Claude Code, but built specifically for financial research. Table of Contents - 👋 Overview - [✅ Prerequisites](#-prereq
An open-source orchestration platform for managing teams of AI agents to run autonomous businesses. Create org charts, set budgets, define goals, and let AI employees handle operations from development to marketing.
A comprehensive multi-language framework for building, orchestrating, and deploying AI agents and multi-agent workflows. Supports both Python and .NET with features like graph-based workflows, observability, and multiple LLM providers.
A self-hosted AI companion inspired by Neuro-sama that can engage in real-time voice chat, play games like Minecraft and Factorio, and interact with your desktop activities. It's designed as a "soul container" for AI waifus and virtual characters that can function as digital companions with gaming capabilities.
An open-source workflow engine for AI coding agents that makes development processes deterministic and repeatable. Define your coding workflows as YAML files to standardize planning, implementation, validation, and PR creation across projects.
Connects Blender to Claude AI through the Model Context Protocol, allowing Claude to directly create, modify, and control 3D models, scenes, and materials in Blender through natural language prompts. Enables AI-assisted 3D modeling with two-way communication between Claude and Blender.
Ultra-lightweight AI assistant written in Go that runs on $10 hardware with less than 10MB RAM. Designed for deployment on minimal embedded devices while providing full-stack AI capabilities including web search, code development, and task automation.