Top Picks

Flux is a Rust-based LLM inference planner and runtime that measures local hardware, chooses a model placement plan, and serves models behind an OpenAI-compatible API.

A privacy-focused Chrome extension that helps users quickly find tabs, pages, and notes with a command bar, optional AI help, and local-first storage.

Orbtile turns a Logitech MX Creative Keypad into a live status pad for AI coding agents, showing session state, approvals, and requests at a glance on macOS.

A GitHub repo for checking recorded agent runs against a TLA+ specification of the surrounding protocol. It models retries, acknowledgements, approvals, budgets, and can validate JSONL runs against the same spec.

A Claude Code skill and plugin that bulk-deletes old scheduled-task runs while keeping the newest N and preserving runs where a user replied.

Self-hosted cloud coding agent infrastructure for running Claude Code and Codex in per-thread sandboxes with a single Docker Compose setup.

Plannotator documents a workflow for letting AI agents ask questions in markdown-style question blocks and collecting answers asynchronously in one place. The page explains how it works, where it works, and how agents and reviewers exchange responses.

A tool that lets AI agents control Figma through a dedicated Chromium session and CDP, with MCP and HTTP API access, install steps, and agent/client setup guidance.

Premortem is an AI red-teaming tool for startup ideas. Users paste an idea, six specialized agents critique it, and a seventh agent synthesizes the findings into a memo.

Local tools for agentic software development: a Rust and egui workspace that groups tasks, shells, coding agents, and code review in one place, with remote browser access and reusable UI/terminal components.

A curated GitHub resource list for learning AI performance engineering, covering GPU fundamentals, kernel optimization, inference engines, and distributed inference.

Open-source coding agent for Windows desktop with CLI/TUI and a companion desktop workspace for managing sessions, agents, and workflows.

A simple AI tool that renames up to 10 screenshots in one batch, generating searchable filenames from image content without requiring sign-up.

An iPhone app for controlling coding agents like Claude Code and Codex from your phone, with push prompts, live terminal access, and quick approve/deny actions.

A blind listening arena for AI-composed music. Users compare two pieces against the same brief, vote A/B/tie/neither, and then reveal results and rankings.

A research project and proxy for Claude Code that chooses per-step reasoning effort with Jev while preserving the prompt cache. The repo includes benchmark results, a real-session measurement, and notes on how the mechanism works.

A React app that compares per-token prices across AI models and shows live or cached pricing from the LiteLLM Model Catalog API.

Event-driven API and CLI for watching live coding-agent sessions on a machine, with support for multiple harnesses and session inspection.

Open-source checker that opens a generated web page in a real browser, inspects rendered controls, and runs mechanical checks without tests or an LLM.

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.