AI tool

A small open-source benchmark repo comparing edge AI boards by real or vendor-reported YOLO FPS, board price, and FPS-per-dollar. It includes a machine-readable CSV, source links, contribution guidelines, and notes on how the figures were gathered.

Open-source Python safety layer for AI agent actions. It checks proposed actions before execution, supports approvals and blocking rules, and includes a demo, receipts, and docs for running locally or with Postgres.

Vigilator is a human-in-the-loop layer for AI agents, offering approvals, live agent monitoring, escalation routing, analytics, audit logs, notifications, and webhooks.

TokenDelivery.ai is an OpenAI-compatible API for open-weight LLMs with deterministic outputs, prepaid per-token billing, and a playground for testing prompts, images, video, and sampling settings.

A Chrome extension that helps users triage Gmail with one-click actions, bulk sender sweeps, optional phishing checks, and optional AI summaries using their own keys.

Verso is an open-source macOS app that orchestrates local AI agents for knowledge work, with app connections, local memory, and support for switching between frontier models.

An open-source tmux plugin that shows Claude Code and Codex activity status, with window indicators plus optional popup and sidebar views.

A Rust PTY wrapper that adds Codex-style syntax colors to Claude Code shell commands without changing how Claude Code runs.

Uno is a research repository for speeding up LLM inference with discrete diffusion and lossless multi-token decoding. The repo includes inference, training, and evaluation code, plus installation steps, checkpoints, and example workflows.

A public leaderboard comparing how different language models solve Redactle under several evaluation setups, with cost, speed, and solve-rate data.

HEIDES is a deterministic local harness for AI coding agents that maps a codebase, grounds plans against the current graph, and checks proposed patches for conflicts, edge cases, and security issues before changes land.

A local zero-dependency sandbox for agents that records files, commands, database activity, network access, and screenshots for review before approving changes.

TronZap is a TRON resource rental service for buying energy and bandwidth to reduce USDT TRC-20 transaction fees. The page also shows an API, SDK example, Telegram bot, dashboard, recurring rentals, and AML wallet screening tools.

A browser-based WYSIWYG editor and presenter for decks written in Markdown, with optional AI usage for rewriting and figure generation workflows.

A local bridge that connects Claude Code and Codex for bidirectional, in-session collaboration. It supports turn-based message passing, cross-review, pair-aware workflows, and resume/diagnostic commands for running multiple agent pairs.

Anthropic’s research preview introduces the Model Hardware Standard (MHS), a shared spec for AI agents to control physical devices and orchestrate lab or manufacturing equipment. The page explains how the standard works, shows early lab examples, and positions it as an upcoming open source standard for hardware integra

Octomind Routines is a scheduled-agent product for running agents on persistent cloud machines with visible run history, state files, cost controls, and timezone-aware scheduling.

Shared, append-only memory for AI coding agents. Vera lets Claude, local models, and Codex read and write the same numbered memory log so projects can continue across sessions.

Sloppie is a Linux development environment for coordinating multiple coding-agent tasks with a dashboard, diff review, async comments, and real terminals per task.

A GitHub repository that publishes a week of controlled runs comparing seven Google models on the same software task, with transcripts, telemetry, screenshots, and scored benchmark artifacts.

Local privacy gateway that redacts sensitive text before sending prompts to external LLMs, then reconstructs the final answer locally.

Ante is a self-contained coding agent that runs in your terminal, supports local models, and offers CLI, TUI, server, and gateway modes. The page highlights public benchmarks, low resource usage, and support for multiple providers and agent orchestration.

An open-source project that deploys a persistent DeepSeek-based coding agent on Cloudflare Workers with one-command installation and durable workspace support.

Self-hosted multi-agent federation for running Hermes agents and OpenClaw minions with a board, tender market, memory layers, and decision provenance.