Android in docker solution with noVNC supported and video recording

Desktop app that records your on-screen work session and uses the GitHub Copilot CLI to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Scout, Microsoft Copilot Cowork, or Copilot Studio.

A curated collection of reusable agent skills for designers and builders to generate UI prompts and workflows using AI coding agents.

An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.

Natively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Interview Coder. Real-time transcription, AI meeting notes, lecture recording, local RAG, BYOK, and stealth mode. Runs locally. No subscriptions. No data breaches.

A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.

Self-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.

A cross-platform instant messaging client application built with Tauri and Vue 3, featuring one-to-one chat, group chat, file transfer, audio/video calling, screen recording, screenshot capture, and QR code login capabilities.

Plan a practical long-form video with test prompts, recording structure, narration beats, screen-recording steps, and production handoff.

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

Build a reproducible local rough-cut workflow for talking-head or narrated screen-recording videos with transcript review gates.