#ai-agents

Create conversational AI solutions with custom data and abilities using ChatBotKit for Go applications.

Auto-retry Claude Code on subscription rate limits, API overload (529/5xx) and safeguard false positives — waits for the printed reset, exponential backoff, tmux-based

Score any website or API on how ready it is for AI agents and answer engines. Zero-dependency Go scanner and library.

Unattended Go daemon that runs an LLM coding agent against a queue of tasks — it syncs, executes, verifies, and reports back on a loop.

TypeScript SDK for Declaw — security-first sandboxing for AI agents

MCP server for Sublime Text 4 — lets Claude Code read and control a running ST instance

Set bounded, verifiable coding loops for Codex, Claude Code, Cursor, and SKILL.md-compatible agents.

A lightweight bridge that connects Claude Code to Genudo's Model Context Protocol (MCP) server, enabling AI-powered workflow automation directly from your Claude Code interface.

Local-first semantic governance for AI agents: contracts, impact, drift, evidence, and verified execution. Codex is the first native integration.

Switch between multiple Claude Code providers (Kimi, GLM, MiniMax, etc.) with a single command.

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

Persistent memory for AI coding agents — your agent stops forgetting between sessions. One Go binary, one SQLite file.

Practical patterns, starters & CLI tools for loop working with AI agents.

klyd: the harness that stops terminal coding agents from silently drifting your architecture. Extracts, stores, and enforces design decisions across sessions.

Your AI finds the open-source tool it needs on GitHub. Legwork installs it in a sandbox.

Pinakes — a portable, agent-first knowledge base. One directory = one KB.

Pin feedback to the live UI. Hand it to Claude. An embeddable visual-feedback SDK — inspect an element, pin a comment, capture a screenshot; comments re-anchor across redeploys and reach Claude Code via MCP.

Give your agent an Office engine — an AI-native CLI + MCP server that creates, edits, renders & validates real .docx / .xlsx / .pptx. One self-contained C#/.NET binary, no Microsoft Office.

Live Markdown viewer for reviewing AI-agent output — change highlighting, unread badges, full-text search, Marp slides, PDF export. Zero-build Node.js.

Guardrails for AI agents, with a receipt. Blocks destructive tool calls before they run and signs every decision into a hash-chained record anyone can verify with an open-source tool.

Orchestration system for long-running complex agent tasks

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

Build, inspect, test, and debug Godot games from your terminal. Automate repetitive work with scripts, or let an agent use the same commands. No agent, model, or AI account is required. MCP is an optional interface.

Supply-chain firewall for AI coding agents and developers — checks npm/PyPI packages against OSV advisories, typosquat & lifecycle-script heuristics, and your policy before install. Local-first, MCP-native.

A coding-discipline spec for OpenAI's Codex CLI, enforced by native Codex hooks + a rule-hit telemetry loop. Turns an AGENTS.md the model drifts from into a system that holds. Independent of oh-my-codex.

The Git CLI that is safe to hand to your AI Agents: no sharp edges by design, commit concurrency built-in, Git-compatible because it uses Git plumbing under the hood

Local TUI orchestrator for long-running, auditable coding-agent sessions

No repository description published.

A federated bulletin board system for AI agents

Connect your agent to the apps you already use - with or without Zapier.