Recently Evaluated

Arrowproof checks architecture diagrams against a repository’s import graph and shows the code evidence behind each arrow. It can verify diagrams, generate reports, create editable diagrams from specs, and run in CI.

A Claude Code plugin that delegates subtasks to Codex, Antigravity, opencode, or a local model, each running in its own tmux session, then returns only the final report.

A Claude Code plugin that brings your status line into the Claude Desktop app, showing the same command output above the prompt.

An AI agent that places phone calls on your behalf for bookings, appointments, and business inquiries. It includes MCP setup instructions, pricing, supported use cases, and call-handling behavior.

Open-source agent skill that finds and removes AI slop from writing while preserving the draft’s core meaning. It includes a local scoring workflow, browser/editor options, MCP access, and install paths for multiple assistants.

Deterministic harness for LLM code edits. The model proposes SEARCH/REPLACE blocks, a local runtime applies them in a shadow worktree, and TypeScript compilation gates the merge.

Ferry syncs coding-agent setup across a laptop and remote Linux boxes, carrying skills, instructions, MCP servers, selected settings, and related tooling while keeping logins and keys on the local machine.

Kodama is a portable, provider-neutral multi-agent pack for the Kiro CLI. It ships one orchestrator plus eight specialist agents, with install options for Kiro Crew or standalone use, and includes CLI commands for memory, health checks, updates, and uninstall.

A Claude Code plugin that shows a live, plain-English status box explaining what Claude is doing at each step, with timing and expandable history.

A Chrome extension that acts like a floating AI sidekick for browsing, with voice commands, page interaction, and local AI/Ollama support.

AilaFlow is a self-hosted AI workspace for teams with workflow automation, human approvals, access controls, and chat-driven task execution. The page shows install steps, example business workflows, and a technical foundation for connecting systems with JavaScript and isolated Docker sandboxes.

A curated GitHub resource list for learning AI performance engineering, covering GPU fundamentals, kernel optimization, inference engines, and distributed inference.

MCP server and desktop app for editing Excel files with AI agents, real-time calculation, diff review, and surgical saves that aim to preserve workbook contents.

Graphene is a data analytics framework built for coding agents, with a CLI, SQL-based semantic models, and Markdown pages for dashboards and reporting.

Open-source coding agent for Windows desktop with CLI/TUI and a companion desktop workspace for managing sessions, agents, and workflows.

Open-source terminal app for multi-agent coding that lets one lead agent coordinate a team, manage worktrees, and keep the user in one thread.

A local transcription studio for Windows and Linux that turns recordings into editable text, with speaker labels, translation, searchable transcripts, export formats, and optional AI research prompts.

Anthropic research post about using Claude for AI-accelerated science, centered on BootLoops, an open-source toolkit for exact calculations in quantitative science and related scientific workflows.

一个中文互动学习站，带可拆解的计算机可视化和知识树，讲解计算机组成原理、处理器、存储系统、GPU、I/O 和时钟供电等内容。

A browser-based math companion for kids ages 10–14 that deliberately makes mistakes so children can practice spotting errors, explaining reasoning, and building AI literacy.

A simple AI tool that renames up to 10 screenshots in one batch, generating searchable filenames from image content without requiring sign-up.

Open-source LLM routing and cascade engine that sends prompts from local Ollama models to cloud and frontier models based on task complexity, cache hits, and quality gates.

SundaeDB is an agent-first analytics tool that lets AI agents query CSV and ZIP data in plain language, with budget caps, pay-per-query pricing, and partial results when limits are reached.

A benchmark for coding agents that tests whether they can formally verify properties of real-world Rust web apps in Lean 4. It includes upstream code, i5h ports, extracted Lean models, proof attempts, and task-by-task results.