Top Picks

Cloud-based iOS publishing pipeline for AI agents. It builds signed releases on cloud Macs, pushes to TestFlight, submits to the App Store, and can be driven via CLI, API, or MCP.

Post-mortem for an AI-assisted port of F-Zero X to the New Nintendo 3DS, including the build stack, hardware performance results, timeline, and agent workflow used to get the game running at native 60 Hz.

Open-source CLI for searching past coding agent sessions locally and tracing code changes back to the original agent transcript. It also offers a paid pro add-on for “git blame, but for agent sessions,” with cited results and local-only indexing.

Release page for vLLM v0.28.0, a high-throughput and memory-efficient inference and serving engine for LLMs. The snapshot shows release highlights, model support updates, breaking changes, and installable artifacts for PyPI, Docker, ROCm, CPU, and XPU.

Kith is an AI clinical workspace for therapists and clinical psychologists with ambient session transcription, automated SOAP notes, scheduling, and online session support.

KinoPipe is an FFmpeg-as-a-service platform for AI agents and developers, offering typed video-editing tools over MCP and REST. The page shows supported actions like trim, resize, compress, subtitles, and scene splitting, plus playground access, pricing, and deployment details.

A hosted relay that lets Claude, ChatGPT, or any MCP client securely access local, NAT'd, or firewalled MCP servers through one connector and a single URL.

grith is a Linux security proxy for AI coding agents that supervises file, process, and network actions at the OS level before they execute. It supports tools like Claude Code, Codex, Aider, Cline, and Goose, with local audit logging and profiles for common agent workflows.

Self-hosted, read-only MCP server that lets an AI assistant search and summarize mail from one or more IMAP accounts indexed locally with notmuch.

unbox-ai is an open-source CLI and local viewer for inspecting AI agent traces. It visualizes token usage, latency, tool calls, and repeated context in a bundle-analyzer-style interface, and also includes read-only commands for agents and a live AI SDK DevTools mode.

Open-source, self-hosted remote controller for coding agents like Claude Code, Codex, opencode, and Kimi Code. It runs sessions on your own Linux box or Mac with tmux underneath and lets you monitor and approve work from desktop, phone, or browser.

A searchable index of Claude Code skills, subagents, plugins, and marketplaces, each scored on whether it actually loads. The site says listings are rebuilt nightly from GitHub and skills.sh and includes breakdowns for score components, install counts, and last commit data.

Open-source AI IDE for running coding agents in parallel with isolated git worktrees, reusable workflows, and self-hosting support.

An agent stack for Claude Code with 60 MIT-licensed skills and 145 tested engines, built to surface failures instead of hiding them.

A local SQLite-based memory database for AI agents with graph memory, hybrid search, and a tamper-evident thought/edge journal.

ApplyWise is an AI job-hunt toolkit that generates ATS-friendly CVs and cover letters, scores applications against job descriptions, rewrites drafts to sound more natural, and offers a prompt library for job seekers.

A Telegram bot for controlling local coding CLIs from your phone. It supports Claude Code, Codex, Pi, and Gemini, with per-chat sessions, command confirmation for risky actions, image attachments, streaming responses, and macOS auto-start setup.

Shoehorn is a Rust library and CLI for fitting GGUF LLMs into available Mac VRAM by choosing a per-tensor mixed-precision quantization plan. It can probe usable GPU memory, account for KV cache and compute buffers, generate or use an imatrix, write a fitted GGUF, and launch llama.cpp inference.

Phinq is an open-source runtime governance layer for AI agents that intercepts tool calls, classifies risk, pauses irreversible actions for human approval, and records decisions in a tamper-evident audit log.

Open-source coding agent that keeps a persistent memory of your repo, with a CLI, self-hosted gateway, model routing, and support for OpenAI-compatible and provider-native endpoints.

A web-based tester for MCP servers that inspects tools, resources, and prompts, measures latency, estimates token usage, and flags tool-poisoning risks.

compactdiff snapshots, diffs, replays, and branches AI coding-agent sessions locally. It reads Claude Code and Codex logs natively, redacts sensitive data by default, and exports shareable replay HTML or forked JSONL branches.

Cloudflare’s Kitesurf is an agent-first browser built to run in V8 isolates on Workers, aimed at scalable browser execution for AI agents.

Chrome extension that helps humans review AI-generated GitHub PRs by clustering diffs into review units and adding short AI summaries.