Agents

This repo open-sources a full Chinese textbook on AI agent engineering—complete with Markdown source, compiled PDF, and runnable Python demos for every chapter.

A single Zig binary with an embedded Svelte dashboard that installs, supervises, and cross-wires local AI agents, workflow engines, and tracing tools so you don't have to juggle separate terminals.

wigolo gives AI coding agents a local, keyless web research layer that runs entirely on your machine and bills nothing per query.

LiveAgent is a local-first desktop client that gives LLMs real file-system and shell access, plus an optional gateway for remote browser control.

NitroStack treats MCP servers as first-class backends, not afterthoughts held together with glue code.

VulnClaw exists so that a single natural-language sentence can trigger the entire reconnaissance-to-report pipeline without manually orchestrating a dozen separate tools.

It bundles the entire AI drama workflow—script, storyboard, voice, and final cut—into a single pipeline you can host yourself.

A skill that spawns parallel reasoning processes under distorted cognitive frames, then scores and prunes them with a separate critic pass.

This repository packages the public metadata that lets MCP clients discover and query Vybe’s live Solana API.

PhyAgentOS treats robot hardware like pluggable drivers so the same agentic session can run in simulation or on a real arm without rewriting the control stack.

Raven wraps agents in durable memory and self-refining skills so workflows survive past the chat session.

iFixAi runs up to 32 inspections against any LLM or agent and returns a letter-grade scorecard in minutes, using a separate provider as judge so the model isn't grading its own homework.

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.

Agentlas OS compiles plain-language requests into portable, ownable agent packages that run locally across whatever LLM host you already use, while a Hub and owner-scoped Cloud handle sharing and retrieval.

A library of 75 portable Markdown playbooks that teach AI coding agents to design and build interfaces with constraints instead of vibes.

A terminal multiplexer that tracks whether your coding agents are blocked, working, or done—without leaving the shell.

This fork rebuilds a popular multi-agent trading framework for the A-share market, replacing Yahoo Finance with free local data feeds and adding analysts who track policy shifts, hot-money flows, and lockup expirations instead of just fundamentals.

It keeps the entire agent loop—prompts, tool calls, browser state, and memory—on your laptop so you don't have to rent a control plane in the cloud.

It wraps your operating system's accessibility APIs into an MCP server so any AI agent can see and control your desktop without waiting for OpenAI's closed beta.