Search

Embeddable voice AI website assistant widget for dabalabs projects — press Ctrl+Space, talk to your site.

Shareable, provider-aware agentic flows for OpenCode

All-in-one installer for ework (issue tracker) + ework-daemon (AI bridge) + opencode-ework (plugin). One command: npm i -g ework-aio && ework-aio install.

Terminal-based coding assistant (AWAS CLI)

Designer-authored, LLM-rendered, Code Connect-native Figma UI Kit for conversational AI agent design.

LLM-backed AI agents provider for molecule.dev — a tool-calling loop over the swappable @molecule/api-ai chat bond

Dependency-free Python client for the AgentWeb API.

Zero-dependency browser SDK to surface an Atoa payment-approval — open the hosted approval page (popup, modal, or redirect) and resolve the human decision. The decision credential (OTP, passkey) is only ever collected on the Atoa origin; host apps forward

Contract testing for LLM agent tool-calls — catch tool-calling regressions when a provider ships a new model version.

Agent-native CLI, package contracts, and seller-owned local Runner framework for portable digital employees.

Visual editor and runtime for explicit agent workflows built on OpenCode.

AgentHarness runtime, session storage, and orchestration layer for pi-agent-core

Python port of pi-agent-core with LangChain LLM adapter

Protocol bridge for OpenAI Responses, Chat Completions, and Anthropic Messages clients.

Local-first shared long-term memory for multiple AI agent CLIs

Local-model agent loop for Ollama, LM Studio, Hugging Face, MLX, and OpenAI-compatible servers.

One-click synchronization tool for AI Agent Skills (SKILL.md) across platforms.

Local-model agent loop for Ollama, LM Studio, Hugging Face, MLX, and OpenAI-compatible servers.

Deterministic, receipt-preserving context compaction middleware for LLM agents

AgentGuard installation entry point