MCP server implementing dual-cycle metacognitive reasoning framework for autonomous agents
Linear-driven orchestrator + scaffolder for coding agents on Sandcastle. `runway init` scaffolds a target repo (sandcastle + varlock + 1Password); `runway run` drains a Linear queue against it; `runway doctor`, `runway upgrade`, `runway upgrade-repo` roun
OpenCode plugin for GitNexus — automatic graph indexing, staleness detection, and subagent hints
Rehearse — local-first GitHub Actions runner + TypeScript-pipeline CLI. Single binary `rh`.
Node.js bindings for Enki's Rust agent runtime.
Compozy CLI
Real-time Claude agent that connects to the Eventmodelers Platform and generates Code from Eventmodels
CHIP + Atom of Thoughts (AoT) Agent Harness — multi-provider n8n community node with a Process Analyst Worker for operational case triage (email, document, automotive service). Pluggable vaults (Obsidian, Supabase) and Human-in-the-Loop gate.
Vercel AI SDK provider for Sanity Content Agent API
RAG search system for Gist, GitHub, and Local Files.
A Simple and Beautiful 360 viewer for your product
Embeddable ASCII art components for React
Autonomous AI engineer — observes, judges, builds, ships
MCP server for analysing Claude Code sessions — cost breakdown, repeated tasks, file read patterns, and optimisation suggestions.
Node.js bindings for Enki's Rust agent runtime.
React hook to call function with delay
Clawd Leviathan — Sovereign AI Agent Runtime on Solana
The integration package is used to support Node.js monitoring. Once you import this package into your Instana environment, you will be able to monitor Node.js runtime and the applications on various aspects by checking the dashboards, alerts, etc. include
AI coding agent orchestration at scale. Karpathy optimization loops, multi-agent pipelines, DAG dependencies, autoscaling workers. Claude, Codex, Gemini.
angular directive to handle element scroll
OpenCode plugin for TaskSync — persistent daemon feedback loop for AI coding agents
Gulp plugin for dependencies building
AMQP component for gedai project
Close the eval-to-improvement loop for promptfoo. Automatically evaluate, identify low-scoring prompts, rewrite with any LLM, and re-evaluate.