AI tool

A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.

A CLI for the Slack Web API built for coding agents. It exposes Slack methods through a single command format, supports JSON stdin, dry runs, pagination, and discovery commands, and installs via npm.

AI Buddy is a free macOS menu-bar app for screenshots and voice dictation. It lets users capture regions, windows, or full screen, copy instantly to clipboard, and transcribe speech to text using Gemini 3.5 Flash.

Harness is an agentic IDE for running coding agents on remote machines over SSH, with one-click backend setup, backend switching, web access, and notifications across machines.

A CLI-based mailbox and message bus for AI agents, with backends for GitHub, SQLite, S3, GCS, Postgres, and local storage. The repo also includes plugin support for Claude Code, Codex, and OpenCode.

An interactive site showcasing short AI-built arcade games and a model bench that compares coding models across the same tiny game constraints.

ClaudeLines is a registry for Claude Code status line scripts, letting users browse community-built bars and install them with a single prompt.

An autonomous AI agent that forecasts station temperatures and trades weather markets on Kalshi and Polymarket, with paper trading, risk limits, and public performance tracking.

A local CLI for replaying what AI coding agents accessed on your machine, including file reads, secrets that entered context, and possible read-then-network-call exposure paths. It also scans exported ChatGPT, Claude, and Gemini histories for sensitive data.

A local-first harness for turning coding models into reliable software agents, with memory, sandboxed execution, verification, recovery, GitOps, and deployment workflows. The repo describes a multi-agent architecture, approval gates, provider support, and a real shipped example.

An open-source project that runs full games of Diplomacy between 7 LLM-controlled powers, with negotiation rounds, validated orders, and saved transcripts for replay and analysis.

A zero-dependency TypeScript music theory engine with scale, mode, key, and interval utilities, plus MCP server support for AI assistants.

r3 is a local code review tool for AI-generated code and docs, with a browser UI, anchored feedback, and an agent loop for create/watch/reply workflows.

A local terminal UI for exploring AI coding spend across tools like OpenCode, Claude Code, Codex, GitHub Copilot, and more. It shows costs by month, day, project, session, and model, with drill-down views, heatmaps, exports, and a web browser mode.

Open-source runtime for coding agents that sits underneath Claude Code to reduce tool calls, shorten context, and track savings. The page includes installation steps, a local savings check, and benchmark results comparing cost and performance.

UnderstandDocs is a document analysis tool that summarizes pasted text or uploaded files, flags risks, extracts important dates, and simplifies dense language. The page shows a working analysis form, supported file types, a privacy/no-storage claim, and an example output for a tenancy agreement.

A visual benchmark that asks AI coding agents to generate a single-file Three.js animation of a banana plant’s full life cycle, then compares the live results side by side.

A free open-source Mac app that lets non-coders enable and manage Claude Cowork skills and personas through a switchboard-style UI.

An MCP server that gives coding agents a compiler-backed graph of a TypeScript codebase, so they can answer structure questions with fewer tokens and exact file-and-line references.

A from-scratch ~1B parameter language model on Hugging Face with open weights, open data, training details, and loading guidance. The page is unusually candid about capabilities, limits, and evaluation.

A TypeScript library for deterministic context folding in long-running LLM agent sessions, designed to preserve prompts, avoid extra summarization calls, and keep provider caches hot.

A deterministic Python project for empirical law discovery in elementary cellular automata, with simulation, discovery, reproducibility guides, and published preprints.

Tecture helps coding agents write and maintain architecture docs directly in the repo, then lets teams explore them as interactive diagrams in VS Code or the browser.

Recall is a local-first memory tool for Claude Code that logs sessions and generates a compact project summary offline, without sending data to an API.