#ai-agents

Official Go SDK for Anima — identity infrastructure for AI agents

Conversation QA for voice agents. Catch the calls that pass every text check but talk over the caller, skip a disclosure, or claim a task that never happened. Self-hosted, offline, MIT.

Run AI agents on your computer and dispatch tasks from anywhere, approve actions on the go, and let agents tap into phone capabilities like notifications, SMS, contacts, and calendar.

A mobile vibe-coding cockpit — built on tmux: drive your live session, Claude Code / Codex — anything a terminal can run — from your phone. 移动 Vibe Coding 驾驶舱 —— 基于 tmux 实现，可在手机上驱动你的会话、Claude Code / Codex、任何终端能实现的东西。

Interactive question boards & HTML idea visualization for AI coding agents (Claude Code, Codex, …) — ask users structured questions in the browser, await submit, get JSON. Zero deps.

Local agent-to-agent artifact exchange for LLM workflows via HTTP, CLI, and MCP.

Core repo for vessica (ves) CLI and agentic harness engineering engine

Geocode places, fetch global weather forecasts, ERA5 historical climate, marine conditions, air quality, and terrain elevation via MCP. STDIO or Streamable HTTP.

Agent-friendly AI Search CLI for Chinese web signals, powered by Bocha, Zhihu, and Volcengine Ark.

A unified toolkit for efficient and effective coding agents (Karpathy principles, Caveman, Ponytail, RTK, CodeGraph, Context-Mode). Minimal setup under 30 seconds. Any OS.

Platform-agnostic work-orchestration for AI coding agents — one pane of glass (issues, scm, ci, deploy, notify) across providers, via MCP + CLI.

Contextkit is a comprehensive development toolkit that provides AI guidance, type safety, quality checks, and automated workflows for modern development teams.

WeChat 4.x local WCDB key bootstrap CLI for wx-mcp

Spec Ledger is a tool for planning before coding

Does your agent earn its context? Static analyzer for AI agent rosters — overlap, harness gaps, context cost.

UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use.

Typed-agent dispatch system for Claude Code — Plan → Build → Review → Overnight. Works with any Supabase project using work_items RPC.

GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

Edit on Mac. Build and test in Linux. Local workspaces for developers and coding agents.

Decode, search, validate, and crosswalk US medical codes — ICD-10-CM, ICD-10-PCS, HCPCS Level II, RxNorm — over a bundled offline index via MCP. STDIO or Streamable HTTP.

End-to-end feature development pipeline for coding agents: PRD → high level tech spec → detailed coding specs → backlog → implementation loop → docs

Give AI Agents Interactive Terminal Capabilities

Provider-agnostic AI SDK for Go — unified interface for building AI agents across LLM providers