Top Picks

LocalCode turns plain English into CLI commands on Apple Silicon Macs using Apple’s on-device Foundation Models framework, then asks for approval before running them.

AutoGPU is an open-source project for using AI agents to design and harden a GPU-like chip end to end, from Verilog through synthesis and place-and-route to GDSII. The repo shows a concrete fp8 matmul accelerator flow, quick-start steps, and documentation for running the design/hardening process.

Google’s Gemini 3.5 Live Translate is a near real-time speech-to-speech translation model that works across 70+ languages and is being rolled out in Google AI Studio, Google Meet, and Google Translate.

Command Center is a local AI coding environment focused on helping developers run multiple coding agents, review large diffs, and turn AI-generated edits into cleaner, production-ready code.

Runtime authorization platform for AI agents with open-source SDKs in Python, TypeScript, Go, Java, and Rust. The page says the hosted service is in production, supports per-action checks, scoped delegation, revocable tokens, and a shared authorization model across MCP tools, agent-to-agent calls, and direct API integr

An open-source shim that lets Cursor canvas .tsx files render on the web by aliasing cursor/canvas to a Mantine-backed implementation. Includes install steps, runtime setup, supported API coverage, limitations, and a live example deployment.

A minimal native macOS sandbox for running Claude Code or Codex with OS-enforced limits on what the agent can touch.

An open-source handbook for production LLM serving and inference at scale, covering GPU fundamentals, KV cache, batching, quantization, speculative decoding, and engines like vLLM, SGLang, and TensorRT-LLM.

A lightweight terminal AI sidecar for Zellij that keeps quick questions separate from your main agent session, with local JSONL logging, SQLite search, and multiple LLM provider options.

Local-first agentic coding assistant in Rust with a terminal UI, embedded web UI, phone app, always-on gateway, and LAN grid dispatch across multiple machines.

An open-source reference implementation for autonomous vulnerability discovery and remediation with Claude. It includes Claude Code skills for threat modeling, scanning, triage, patching, plus a harness for running a recon → find → verify → report → patch pipeline.

CLI for installing, switching, and managing collections of agent skills and agent-specific configurations across multiple coding tools.

Swift package for building provider-agnostic AI agents on Apple platforms, with tools for runtime permissions, hooks, context compaction, session state, validation loops, and traceable execution.

A Claude Code skill for multi-agent code review that produces findings.md with severity, impact category, verification artifacts, and fix directions.

An API for mapping hex values, palettes, and images to named archive colours, with deterministic colour metrics, accessibility checks, cultural risk notes, and MCP support for agents and chat tools.

A demo for running the Odysseus self-hosted AI workspace on throwaway islo.dev microVMs in one command, with both a clickable live app path and an agent tool for running code on disposable boxes.

Open-source local document memory for AI tools, coding agents, and humans. It offers a local CLI, optional daemon, searchable notes, metadata, tags, links, and version history.

A local AI IDE plugin that cleans up messy prompts before they reach Claude, Cursor, or OpenCode. It fixes typos, dropped words, and split tokens on-device with no network or token cost.

QVAC SDK 0.12.0 adds TurboQuant, a KV-cache quantization feature for local LLM inference that claims up to 5x more context on-device with no retraining or code changes.

OP is an API that gives AI agents real phone numbers for account registration, OTP/2FA codes, SMS, and voice calls. The page shows a live product pitch, feature comparison, a simple API example, and multiple agent communication use cases.

Self-hosted AI workspace with chat, agents, deep research, document editing, email triage, notes, calendar, and model comparison. The README includes setup instructions for Docker and native installs, plus a broad feature list and demo references.

A macOS utility that compresses screenshots locally and copies them to the clipboard for use with coding agents like Codex and Claude.

Open-source security scanner and firewall for MCP servers. It scans configs for common MCP risks, enforces runtime policies on tool calls, and produces audit logs, with CLI commands, policy examples, and a programmatic API.

DeepSWE is a benchmark for measuring frontier coding agents on original, long-horizon software engineering tasks. The page shows a leaderboard, methodology overview, task examples, and a full blog explaining the benchmark design and results.