Top Picks

Local-first MCP gateway that lets multiple AI clients share one server setup, with lazy tool discovery to reduce token usage and built-in tool integrity and quarantine controls.

Fuse is an open-source .NET MCP/CLI tool that helps coding agents work on C# codebases with Roslyn-backed indexing, dependency injection and route resolution, scoped context reduction, and compiler checks before edits are written.

Agentty is a terminal-based AI pair programming tool and a drop-in alternative to Claude Code, built as a single static C++26 binary with support for multiple model providers. The repository shows installation paths, provider examples, sandboxing, air-gapped mode, and integration with Zed via ACP.

A command guard for AI coding agents that blocks destructive git and shell commands before they run, with support for multiple agent and CLI tools.

A Mac-native menu bar app that tracks AI token usage, shows spend by model, and pops up break reminders when usage crosses configurable thresholds.

A macOS utility for customizing the native Slack app by injecting CSS and JavaScript, hiding Slackbot, upsells, tabs, and other UI elements in real time.

Blocks.ai is an infrastructure and network layer for AI agents, offering outbound-only connectivity, routing, auth, billing, streaming, and a marketplace/network for builders and callers.

A CLI BI tool built for Claude Code that lets agents connect to data sources, generate live dashboards, publish shareable links, and even write back to connected systems.

A macOS app for browsing, searching, and resuming local history from coding agents like Codex, Claude, Cursor, OpenCode, Copilot, Pi, and Antigravity. It also adds transcript views, image browsing, analytics, and a live quota meter for Codex/Claude usage.

Nicasa is a native macOS image viewer and Chrome extension for fast image browsing, with AI image enhancement, smart image extraction, screenshot capture, and local-only processing.

Abralo is a native desktop app for running multiple Claude Code agents at once in one window. It focuses on keeping several agents visible, showing token usage, and surfacing when an agent needs attention.

Local CLI for analyzing when a coding agent starts degrading as session context fills, using transcript data already stored on disk.

AI-powered code review tool that analyzes git diffs and produces structured review reports, with support for GitHub Action workflows and multiple model providers.

A cross-platform MCP-powered distraction blocker that lets AI assistants manage system-level site blocking and focus sessions through the hosts file.

Bootable Rust no_std kernel built as an inference substrate for LLMs, with tensor-native memory allocation, layer-boundary scheduling, and streaming-focused runtime primitives.

Open-source tool that runs on a machine to intercept, inspect, and optionally route Claude and ChatGPT traffic through an AI gateway for logging, policy checks, and governance.

wavecat is a fully local personal agent that watches your screen and runs entirely on-device. The page explains its privacy focus, hardware requirements, local model setup, and supported platforms.

Exfault is an autonomous Android security testing tool that uses AI agents, static analysis, dynamic analysis, authenticated workflows, and cloud emulators to produce reproducible findings and reports.

A local-first, self-hosted home assistant that runs a local LLM as a single brain for Home Assistant, voice, memory, reminders, media control, and other scoped tools.

FencePreview is an AI fence visualization tool for contractors. It lets users upload a yard photo, trace the fence line, and generate a realistic preview of different fence materials and styles to help close jobs faster.

A detailed setup guide for building a two-node AMD Strix Halo cluster with Intel E810 RDMA networking for distributed vLLM inference.

open-geo is a GEO visibility tracker for AI answers. It runs queries in a logged-in browser, records whether a brand appears in sources, citations, or answer text, and outputs a FastAPI/React dashboard plus PDF reports.

An OpenAI-compatible LLM proxy that routes requests to the fastest healthy provider. It runs as a small sidecar, supports latency/error-aware routing, session affinity, and Vertex AI, and can be deployed as a single static binary or Docker container.

A web utility for creating end-to-end encrypted share links for single-file HTML generated by agents. It stores ciphertext for seven days and lets browsers decrypt and render the page from the URL fragment in a sandbox.