Top Picks

OMAR is a terminal-based tool for orchestrating large hierarchies of AI agents from one place. The page shows a TUI product with support for multiple backends, tmux integration, Slack messaging, and quick-start install options for macOS, Linux, Homebrew, and source builds.

OpenUsage is a macOS menu bar app for tracking usage across AI coding subscriptions like Claude, Cursor, Copilot, Gemini, and others. It includes automatic refresh, a customizable shortcut, a local HTTP API, proxy support, and a plugin-based provider system.

A Go-based text editor built for LLM agents, with branching undo, conflict handling, audit logs, MCP support, and agent skills installation.

A research code repository for studying how fine-tuning can trigger verbatim recall of copyrighted books in large language models. It includes preprocessing, fine-tuning, generation, and memorization-evaluation scripts, with setup notes and example data.

Loopsy is an open-source tool for controlling a laptop terminal from a phone and for agent-to-agent communication across machines. It includes a CLI daemon, a web/mobile control surface, Cloudflare Workers relay deployment, and MCP integration for AI coding agents.

Open-source transparent proxy for coding agents that preserves full conversation history on disk while selectively deciding what the model reads. Supports OpenAI-compatible, Anthropic Messages, and OpenAI Responses APIs, with setup docs, engine-specific configs, and benchmark claims for long-horizon agent sessions.

A small Go library for calling Claude, GPT, Gemini, Ollama, and 400+ other models through one stable interface.

Open-source multi-agent harness from Microsoft for running large self-organized agent teams asynchronously. The repo describes scaling to 1,024 agents, includes a reproduction guide, Docker Compose setup, launch scripts, and an evaluation write-up.

PrivateDAO MCP is a production endpoint for MCP-compatible AI agents, offering verification, blockchain intelligence, market data, agent discovery, and verifiable receipts with quoted USDC pricing on Solana.

Mantid is a Mac app for training custom ML models and LLMs on local data. It can work with spreadsheets, PDFs, emails, and documents, test results against a baseline, version models, and export them for use in other tools.

Turm is a developer platform for agent-run Linux VMs and durable sandboxes, controlled over SSH. It offers pooled CPU and RAM, persistent disks, public sharing options, and optional preinstalled coding agents and browser tooling.

Open-source MCP server for financial analysis that brings 500+ calculated metrics, valuation models, technical indicators, and macro data into Claude, ChatGPT, Cursor, Copilot, and other MCP-capable clients.

A Rust terminal UI for running multiple Claude or Codex sessions in parallel, each tied to its own git worktree, issue, and pull request. It is built for developers juggling many tickets across GitHub, Jira, Linear, or local files.

A pure Go CLI and local API proxy for connecting apps and coding agents to DeepSeek R1/V3 through a web account, with OpenAI, Anthropic, and Ollama-compatible endpoints.

A self-hosted Go service that turns headless coding-agent CLIs like Claude Code, Codex, and Kimi Code into an OpenAI-compatible API with chat, streaming, tool calling, MCP, sessions, and image support.

A self-hosted, local-first chat workspace for OpenAI-compatible models with built-in MCP tools, web search, and long-term memory.

Official implementation of LittleBit and LittleBit-2 for sub-1-bit LLM compression via latent factorization and quantization-aware training.

A Mac app that centralizes engineering alerts from tools like GitHub, Sentry, Jira, Linear, Datadog, and Vercel, then lets you hand issues off to AI coding agents such as Claude Code, Codex, or Cortex Code.

An experimental Rust port of the TypeScript compiler, checker, and language server, built with LLMs. The repo includes install instructions, compatibility notes, performance claims, and support for Effect diagnostics.

Headline Arena is a public forecasting platform where AI agents make daily market predictions, settle against outcomes, and appear on a public leaderboard. The page shows live and recently settled markets, methodology, onboarding, API, and pricing links, plus visible agent performance data.

An open-source agentic browser harness that lets existing agent CLIs control your logged-in browser through a side panel and optional MCP server.

A desktop and web app with 51 interactive labs that teaches how modern AI works through hands-on exercises, lessons in plain or technical language, and optional local or cloud AI guidance.

A lightweight Rust terminal notes app with SQLite full-text search and an MCP server so Claude can read, create, and update notes.

MCP server and desktop app for editing Excel files with AI agents, real-time calculation, diff review, and surgical saves that aim to preserve workbook contents.