Search

Context scaffolding for AI agent-driven development

Self-hosted browser workspace for AI coding agents, review, supervision, and cross-device continuation.

Orchestrate AI agents from your terminal — multi-source credential import, swarm topology, background queue, live dashboard

Experimental Python-runner coding agent with a Textual TUI

Hugging Face Space: bharat_voice_assistant

A modular framework for evaluating and verifying agentic LLM outputs.

A modular framework for evaluating and verifying agentic LLM outputs.

React Native SDK for the THG AI Shopping Assistant — exports a single <Chatbot /> component that host apps can mount however they like.

STDD (Spec and Test Driven Development) を既存・新規プロジェクトに導入する CLI

Give an AI agent read/write/deepen access to your real Obsidian vault as a living knowledge graph. Zero dependencies. Works with any LLM framework.

Orchestrate AI agents from your terminal.

Solana Agent Commerce Protocol (sACP) — TypeScript SDK. Job lifecycle escrow + bonded validator registry on Solana, ERC-8183 compatible. Reference implementation by Telaro Protocol.

Premium AI Agent templates, Skills, and Workflows for the Edward Yin Academy

Import existing test plans into test-lab.ai from the command line (or an AI agent).

Safety-oriented execution harness for coding agents

KRAIL client for local projects and the local API runtime

Minimalist coding agent harness with a Textual TUI and headless CLI. <1k-token system prompt, 18+ LLM providers, AGENTS.md + skills context, session tree, prompt/auto permissions.

Build portable, citation-verified, agent-loadable knowledge packages (wikillm) — a research-landscape foundation for starting a PhD-level paper.

Lightweight Python framework for multi-agent LLM workflows — MARL episode loop, LLM pool scheduling, OTEL observability, and compile-to-any-runtime.

Agentic systems specialist agent for Bluetemberg — agent memory design, state management, orchestration patterns.