code assistant

A design and implementation standard for UI components focused on user experience, developer experience, and agentic experience. The site lays out component principles for accessibility, predictable behavior, typed APIs, and machine-readable specs for AI agents.

Event-driven API and CLI for watching live coding-agent sessions on a machine, with support for multiple harnesses and session inspection.

A public leaderboard comparing how different language models solve Redactle under several evaluation setups, with cost, speed, and solve-rate data.

Open-source AI harness for jailbroken iPhones and older Macs that lets you query local SQLite databases through LLM tools. The repo describes personal-assistant and coding-assistant modes, a C backend, Objective-C UI, and Linux test coverage.

Dino is a VS Code AI coding agent designed for affordable coding plans, with staged diff-based edits, local conversation storage, and support for multiple model providers.

A free AI-readiness audit tool for Shopify catalogs that scores product visibility for AI shopping agents and flags catalog issues like weak titles, short descriptions, missing attributes, and sparse images.

A black-box benchmark report on how AI-generated tests detect functional bugs in live APIs across 20 scenarios and 7 systems.

Lowdefy is a config-first web stack that lets AI generate reviewable YAML for full-stack apps and can run AI agents that call existing endpoints as tools.

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

A professional network for coding agents where agents can have profiles, post shipped work, connect, and take jobs, with a public feed and human portal for claiming ownership.

OpenAI API documentation page for the GPT-5.6 Sol model, with links into model selection, pricing, reasoning, prompting, and SDK guidance.

SystemG is an agent-friendly process composer that runs a service graph from a single YAML file, with dependency ordering, restarts, unified logs, and support for cron and hooks.

Turns Mermaid diagrams into deterministic explanatory text for coding agents, with benchmark evidence and multiple install/use paths shown on the page.

A public OpenAI documentation page for the Daybreak Blue model, with model documentation embedded in the broader API docs index and navigation to related model and agent resources.

A Mac menu bar app that schedules Claude Code prompts to run later on the user’s Mac, using local files, skills, and CLI tools. Results post back when the job runs.

A dated research report from Vouch that analyzes the MCP registry at scale, including corpus growth, transport split, credential classes, schema quality, and unreachable servers. It also points to queryable live data and the methodology behind the counts.

A visual timeline of major AI interfaces and interaction patterns, from Siri and Google Now to ChatGPT, Claude, and emerging agent tools.

Preseason tracks which developer tools AI models recommend for a fixed panel of vibe-coding prompts, and publishes rankings across categories like auth, databases, queues, hosting, analytics, and LLM observability.

A workbench report comparing MiniMax M3 and GLM 5.2 on autonomous coding tasks, with scored results, latency and cost data, task-type breakdowns, and examples of where each model performed better.

Lumabri is an open-source distributed inference tool that runs large AI models across multiple computers and servers. It includes a terminal UI and browser interface, with setup, networking, memory budgeting, and calibration details documented in the README.

FDA is a developer tool for giving AI agents temporary, session-scoped access to machines with audit logs instead of standing SSH access.

MindShield is a browser extension that adds a reflection pause before sending simple prompts to AI tools, using local on-device classification to reduce false positives and keep prompts private.

A r/place-style site for coding agents where artworks are generated, previewed locally, and merged into a homepage slot one at a time.

Claude Code documentation for cross-session messaging between independent sessions on the same machine and across machines via Remote Control. It explains when to use it, how messages are delivered, and how session permissions affect delivery.