Lists (10)
Starred repositories
Open-source production-ready mobile server-less AI apps. Clone, customize, and ship on Android & iOS with MLange.
High-Performance Serving Runtime for World Action Models
URL-to-calendar agent skill for Claude Code and Codex
Lean specification of neural architectures with verified GPU codegen.
One-click Render deploy template for nanobot — a lightweight self-hostable AI agent
A bash CLI for coordinating multiple Claude Code accounts across rolling usage limits. Profile setup, health checks, and per-repo account pinning.
Open-source graph database superpowers for your existing Postgres data.
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent …
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.
Fast, scriptable CLI for the App Store Connect API. Automate TestFlight, builds, submissions, signing, analytics, screenshots, subscriptions, and more. JSON-first, no interactive prompts
Agent-native prospecting for Claude Code, Codex, and Claude Desktop: interview -> ICP-matched discovery -> spreadsheet work area -> DM queue. You send every message.
Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.
On-demand /consult skill — a Claude Fable 5 plan-consult plus an automatic warm diff-review on any task. Opus drives; Fable consults.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
Cold-outreach harness for solo founders. Markdown-as-database. 16 pre-send lint rules. Regenerable engagement metrics. Apache-2.0.
Run, deploy and monitor CLI agents in secure cloud sandboxes.
Framework for AI agents to build and maintain a digital brain through Obsidian wiki
Python tool for converting files and office documents to Markdown.
Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
Your LLM can decompile a function. It cannot understand a binary.
An experimental Chrome extension that reimagines LinkedIn messaging with a keyboard-driven, local-first UI.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…