It gives Claude Code and Codex a motion-design vocabulary—106 shot recipes, 161 previews, and a Remotion template—so they can direct cinematic product videos instead of generic slideshows.
Coding Assistants
underdogs breaking outIt breaks the vendor lock on Codex and Claude Code by translating their API calls to any LLM backend you choose.
wigolo gives AI coding agents a local, keyless web research layer that runs entirely on your machine and bills nothing per query.
A skill that spawns parallel reasoning processes under distorted cognitive frames, then scores and prunes them with a separate critic pass.
LiveAgent is a local-first desktop client that gives LLMs real file-system and shell access, plus an optional gateway for remote browser control.
pi-web gives the pi coding agent a local browser UI so you can browse past sessions, fork conversations, and preview files instead of digging through terminal history.
An unofficial proxy that borrows your ChatGPT/Codex OAuth tokens to serve a local OpenAI-compatible API, bypassing API credit billing.
It turns draw.io into a live artboard for Codex, letting an AI agent build and refine scientific figures one editable shape at a time.
NitroStack treats MCP servers as first-class backends, not afterthoughts held together with glue code.
Agent skills that turn your existing LLM coding assistant into a parallelized SAST scanner without extra tooling.
Flint compiles compact, human-editable chart specs into polished Vega-Lite, ECharts, or Chart.js visualizations so agents and developers can skip hand-tuning scales, axes, and spacing.
codex-keysmith exists because copying a Markdown file and editing one TOML key is simple, but existing files, active hooks, and interrupted writes are not.
It exists to stop AI slide generators from hiding their work, turning deck creation into a persistent, steerable project inside your coding agent.
Hyperresearch turns Claude Code into a tiered, multi-agent research pipeline that persists every source in a searchable, compounding vault.
MoonshotAI built a terminal-native agent that reads code, runs shells, and watches screen recordings so you can stop writing bug reports in prose.
pilotfish keeps Claude Fable 5 in the boardroom by delegating the grunt work to cheaper Sonnet and Haiku subagents.
This repository packages the public metadata that lets MCP clients discover and query Vybe’s live Solana API.
It turns Claude, Codex, or OpenCode into hyperparameter optimizers that actually read your parameter docs before proposing the next trial.
A terminal multiplexer that tracks whether your coding agents are blocked, working, or done—without leaving the shell.
It turns the formulaic tics of LLM prose—'What nobody tells you,' 'The best part: it learns'—into a lintable, removable rule set.



