AI tool

Browser-based infrastructure for running coding agents persistently, with workspace management, status tracking, and support for tools like Claude Code and Codex.

Maith is an open-source research workspace for exploring open mathematics with AI while keeping proof standards explicit and checkable.

A French public demo of an autonomous Claude agent competing in timed money-making challenges, with live episode tracking, Stripe payments, and public results from prior runs.

Pulse is an AI incident response tool that watches systems, diagnoses PagerDuty incidents with Claude, and posts suggested fixes to Slack for one-click resolve or escalation.

CodeZero is a no-code backend and automation platform that now includes AI flow generation, a module system, and an execution results view inside the IDE.

Humbug is an open-source, GUI-based agentic development platform for human-AI collaboration. The page says it supports multi-model workflows, local and cloud LLMs, tool use, approvals for risky actions, and local-first data handling.

A side-pane companion for Claude Code that shows daily AI news and spaced-repetition concepts while the agent is working, then hides when it needs user attention.

Rust-based DAG pipeline engine with a visual node editor for building and running workflows. The repo shows programmatic usage, a UI package, and examples for chaining processors like image loading, grayscale conversion, and saving output.

Hawkeye is a developer tool for fast local code search and navigation across large codebases, with editing, focused replace, tabs, shortcuts, and Perforce support.

A live demo that shows an AI agent using KINETK’s API/MCP workflow to analyze live social signals and generate an evidence-backed launch and growth plan for a product prompt.

Open-source email firewall that classifies inbound mail into SILENT, QUEUE, PUSH, or AUTO using a deterministic policy around LLM-scored signals.

An ICML 2026 research project page arguing that prompt injection comes from how LLMs misread roles, with an extended writeup, examples, and links to the paper, code, arXiv, and BibTeX.

Attestor is a TypeScript control plane for high-risk AI-driven operations. It sits between an AI-generated request and the real system action, applying policy, approval, scope, freshness, replay, and evidence checks before returning admit, narrow, review, or block.

A custom Claude Code status line script that shows workspace, model, session, context usage, token totals, code churn, and 5-hour/7-day rate-limit runway in two colored rows.

PaperProfit explains an AI-assisted stock evaluation approach that combines fundamentals, technical signals, and qualitative analysis from transcripts and SEC filings into a weighted score.

A macOS utility that keeps a MacBook awake while AI agents are running, then lets normal sleep resume when they go idle. It includes install scripts, hooks for Claude Code and Codex, and a menu bar status indicator.

A TypeScript zot extension that adds an /answer slash command for responding to numbered questions from the latest assistant message in an interactive panel.

A research write-up on detecting AI agents through process differences in CAPTCHA and related cognitive tasks. It outlines the CogCAPTCHA30 approach, reports human-vs-model differences, and connects the findings to Roundtable’s Proof of Human product.

arXiv paper on a self-speculative decoding framework for speeding up reasoning LLM inference on edge hardware, with hardware co-design and reported speedups.

A practical guide to building an always-on personal AI assistant with Pi, OpenCode Go, Telegram, Resend, Hetzner, Tailscale, GitHub, and Nginx.

Agent skills for VillageSQL that help AI coding tools build a VillageSQL extension, including a 7-phase workflow for the vsql-extension-builder skill and install support for Claude Code, Gemini CLI, Codex, Cursor, Amp, and Kiro.

An open-source multi-agent coding framework that uses a commit-bound project graph to scope worker tasks, replay failed runs, and merge accepted diffs through ordered Git reconciliation.

A research preprint describing ADHD, a parallel divergent ideation method for LLM coding agents that isolates branches, uses cognitive frames, and then prunes with a separate critic pass.

A bilingual satirical idle simulation where you run an AI startup from toy classifiers to near-AGI, managing data, compute, launches, crises, and rivals.