Search

A non-interactive coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenAI, Anthropic, and Google models.

CLAF — Closed-Loop Agent Framework. Anthropic's skin, your brain. Off-grid by default; cloud convenience optional.

Run AI coding agents in sandboxed CI environments

A Linux-only, ncurses based TUI AI coding agent.

Professional Odysseus AI Workspace deployment and support services, including Linux server setup, domain configuration, AI integrations, NGINX, SSL, troubleshooting, optimization, and maintenance available on Telegram https://t.me/AnythingLinux

Delegate-first OpenCode plugin with seven agents, thoth-mem persistence, and bundled SDD skills.

TypeScript SDK for Relay Agent — developer-first voice AI engine

Pi extension that adds subagent delegation.

Next-generation memory provider for Hermes Agent — fusing OpenViking vector storage with MemOS cognitive engine

Platform-specific compiled core extensions for myrm-agent-harness

Platform-specific compiled core extensions for myrm-agent-harness

Gaia AI Agent Skill Registry CLI

SIA: Self-Improving AI framework

Estimate the USD cost of an AI-agent transcript (Claude Code, Codex, Pi).

Official Python SDK for Make Your Agent (MYA) — build AI agents with knowledge bases, tool execution, streaming chat, and per-session token usage

Python routing library for local LLM agent loops: score prompts, map tiers to model names, embed in your runner.

Stream-first observability for distributed LLM agents

Human-in-the-loop API client for LoopPause. Includes LangGraph and CrewAI integrations.

Ultra-lightweight Claude-like AI agent for ARM devices

Production-grade memory infrastructure for AI agents — storage-agnostic, self-evolving, observable.