React bindings for @worldcoin/human-in-the-loop
Code Shell — general-purpose agent orchestration framework with a terminal coding preset
ffmpeg static binaries for Mac OSX and Linux and Windows
A framework for creating videos based on Node.js + Puppeteer + FFmpeg.
Thin client for the Synapse organizational-memory API — bind a repo to an agent identity, run OKR-bound workflows, and report work (checkins, facts, learnings, artifacts) back to Synapse.
Shared scanning logic for Testomniac scanner and Chrome extension
AI runtime for agent-driven products — agents, memory, LLM providers (Inference Snaps, Ollama, OpenAI-compatible), tools, and orchestration. Anthropic-SDK-free.
A durable AI agents component for Convex with automatic retries, crash recovery, and tool execution.
A simple render task scheduler
TraceWeaver CLI: stitch mabl step traces into MP4 (command: traceweave)
Node.js performance measurement metrics (cpu, memory, event loop, gc)
Cawdex — terminal coding agents with a mind for the whole repo. Speaks any OpenAI-compatible API with repo-aware context, benchmark tracing, MemPalace memory, and terminal-first agent workflows.
Generate narrated short-form videos from a prompt with Cloudflare Workers AI, Pexels, and ffmpeg.
Encode video, audio, and images into common formats.
Autonomous desktop AI agent — 22 tools, multi-provider LLM, self-learning skills, sub-agent parallelism, mistake memory. Runs locally with OpenAI, Anthropic, DeepSeek, Ollama or any OpenAI-compatible API.
Autonomous agent execution for feature specs — break specs into agent roles, run them in phased pipelines with coding agents
Record Playwright demo specs as gifs and embed them in PR bodies.
Automated task execution system with coder/reviewer loop
Local-first ADE CLI for planned, verified, reviewable code changes.
An Angular service which helps with creating recursive directives.
Core utilities for parsing, chunking, and assembling TTS audio
Some dank loop functions!
TEA runtime for terminal UIs — model/update/view with keyboard input, alt screen, and layout helpers.
Execution intelligence for AI agents. Trace, understand, and prevent recurring failures in AI-assisted development.