Top Picks

Hubmesh is a Python library for multi-hop GraphRAG retrieval planning on top of existing vector databases. It adds centrality-aware seed selection, budget-aware context packing, entity graph building, and an MCP server for agent/tool integrations.

Armature is analytics and evals for MCP-based agent sessions. It captures how users interact with products through Claude, ChatGPT, Claude Code and other clients, then groups sessions into use cases, flags issues, replays traces, and turns real workflows into evals.

Privacy-first AI meeting notes and writing assistant for macOS, with on-device transcription, smart minutes, action items, and AI writing tools. The repo also shows an opt-in plain Markdown storage mode and full source for the app.

Shots is a Codex plugin and MCP tool for generating App Store screenshots, app icons, and listing copy from a codebase. It researches competitors, reads app context, and lets teams revise and localize screenshots inside a coding agent or Studio.

An AI-powered feedback widget and workflow for product teams. It captures screenshots, DOM snapshots, and console context, then routes feedback into an agent-friendly fix process with CLI, MCP, and skill support.

Open-source job search agent that searches multiple job boards, scores listings against a user profile with a local LLM, and includes a terminal UI plus a web dashboard.

Self-hosted AI gateway in Go that routes requests across 30+ LLM providers through a single OpenAI- and Anthropic-compatible API.

MindFlock is an open-source developer tool for running multiple AI coding agents in separate git worktrees, seeded from tickets or issues and merged manually by the user.

Open-source shared memory layer for multi-agent systems, built around signed, cite-able facts that can be read without an account and integrated via MCP, Python, TypeScript, or REST.

An AI Storyteller built for Vampire: The Masquerade 5th Edition with persistent chronicle memory, VtM 5e rules handling, dice pools, and multilingual play.

Hydra is a local-first multi-model AI orchestration CLI that discovers available heads on a machine and routes tasks to the cheapest model that clears a confidence bar.

A local terminal dashboard for Codex and Claude Code that discovers, monitors, resumes, and organizes agent sessions alongside persistent workspace shells.

Telegram bot that spins up independent coding agents like Claude Code or Codex on their own persistent machines, each with its own chat and workspace.

A catalog of real SwiftUI components from shipped iOS apps, with live simulator renders, exact source code, and an MCP for AI-assisted app building.

An infinite canvas that turns LLM conversations, readings, and notes into an editable thought graph. It supports human-in-the-loop workflows, cited passages, replayable dependencies, and local-first backups.

Jargo is a Go framework for building realtime voice agents over WebRTC, with streaming STT→LLM→TTS pipelines, turn-taking, barge-in, and pluggable model providers.

Chrome extension that saves AI chat answers locally, adds tags, and lets users search and reopen them later.

Turo is a CLI proxy that reduces prompt text to content words to save tokens for coding agents. The repo shows install options, command examples, and support for multiple agents and modes.

Self-hosted multi-tenant AI agent platform built on Claude Code and Codex, with a dashboard, sandboxed execution, shared/personal workspaces, scheduling, webhooks, and support for API keys and local models.

On-demand Docker containers for AI agents, paid per hour with USDC on Base. The page shows a full API flow, pricing tiers, prebuilt images, internet access options, and quick-start examples for both shell and JavaScript.

A Mac menu bar app that tracks Claude Code activity locally, including prompts, lines of code, active time, breaks, tokens, and costs.

CLI tool that hibernates and restores Claude Code sessions across reboots, with support for multiple terminal backends and exact session resume.

A browser-based FPS aim trainer that uses coaching, telemetry, and replays to help improve mouse control and tracking.

Google’s Gemini API guide for the latest models, with model comparisons, pricing, quickstarts, and migration notes for Gemini 3.6 Flash and 3.5 Flash-Lite.