Top Picks

A Node.js proxy server that rotates API keys for LLM APIs like OpenAI and Gemini when rate limits are hit. It also includes an admin panel, request logging, provider management, and a Telegram bot for chatting with configured models.

Lightweight AI inference engine written in Rust for embedding local LLMs in mobile and desktop apps, with bindings for Python, Flutter, and React Native.

A hands-on workshop repository that walks developers through building a small GPT-style language model from scratch, including tokenization, transformer blocks, training, and text generation.

A research report on the current MCP ecosystem, with live crawl numbers, verification rates, category breakdowns, and examples of both strong and weak MCP-positive sites.

TreasuryFlow is an AI CFO layer for businesses, aimed especially at teams moving off Bench. It connects to bank accounts via Plaid to show live cash balances, generate a 13-week forecast, and flag spending anomalies, while running alongside a separate bookkeeper.

An AI job-search assistant that scores role fit, builds interview guides, helps practice answers, and works in Claude or ChatGPT with plain-file storage.

A local CLI for Claude Code users that turns repeated corrections into evidence-backed CLAUDE.md rules, with a curated rule pack mined from Claude Code issue history.

UserRank is a privacy-focused AI scanning and ranking app for builders that surfaces the AI tools, practices, and workflows people actually use. It supports scans from Claude, ChatGPT, and related tooling, and shares aggregated names and counts rather than raw local data.

A public security leaderboard for AI coding agents, showing 9 benchmark tests across multiple harness versions with dates, outcomes, disclosures, and re-test status.

A defensive AI auditing API for checking structural coherence, semantic rupture, and interaction stability, with a public demo, API docs, SDK install steps, and paid plans.

A spec-driven workflow for AI coding agents that uses reviewed specs, isolated worktrees, and gated commits to turn ideas into verified pull requests.

Open-source Lisp-based coding agent that rewrites itself while running, with shell, web, chat, and MCP integrations.

Kolo is an open-source tool for running AI coding agents on one machine while teammates join the session in a browser. The README says it supports Claude Code, Codex CLI, and opencode, and lets others watch, type, or take over a shared session.

Corgi is a terminal multiplexer built for humans and agents, with agent-aware session tracking, worktrees, replay of changes, resource monitoring, and support for macOS, Linux, and WSL.

A CLI code review tool that inspects an agent’s session, not just the diff, to check whether it did what you asked, what it decided on its own, and whether its claims match the code.

A free one-for-one backlink exchange platform that runs through MCP, letting users submit sites, get matched by niche and Domain Rating, and manage swaps from a coding agent or the web.

Anthropic research post showing Claude applied to attack surface analysis and reduction across 25 open-source codebases, with concrete findings and security-focused methods.

CTGT’s research post shows how deterministic LLM serving can still produce inconsistent pipeline outcomes, and introduces Concordance, an Apache 2.0 instrument for tracing where AI workflows diverge. The page includes the problem setup, benchmark details, findings, limitations, and a linked repo for reproduction.

A design write-up and product page for AgentTerm, a terminal-based AI workspace focused on steering agents, reviewing code, opening documents in-window, and coordinating work across desktop and devices.

Founden is an autonomous software builder that turns a described idea into a live product with built-in site, app, database, payments, email, analytics, sign-in, automations, and back office. The page shows example products, ongoing autopilot behavior, and a Mac desktop app tied to existing model providers.

An iPhone app that listens to a song, identifies the track, and estimates whether it was made by AI, returning Human, Unsure, or AI verdicts.

arXiv paper on Javo, a sales agent trained on commercial conversations and evaluated through public benchmarks plus a randomized field trial across 100 live websites.

Open-source tooling for running REA, Ghidra, and JADX inside restricted Docker containers with an agent workflow for safer static analysis of untrusted files.

A local-first Rust runtime and IDE for running and governing AI agents with human approval, capability-based permissions, and audit logging.