Search

Browser SDK for the Loop Voice Agent platform — start a voice call from a publishable key and an agent id.

科豆 AI Agent CLI —— 基于 @kedouai/agent-core 的交互式 AI Agent（自带大模型 API key，不消耗作者 token）

A git-native memory tool for AI agents. Personal + team/project memory that any harness (Pi, Claude Code, cloud review bots) can use. Built with Effect.

OpenSpec agentic workflow extension: schema, role models, installation and migration.

Run Flowriki UI tests on your own computer. Connects this machine to your Flowriki account.

LangChain.js integration for the Velrim document-extraction API: a document loader that turns files into Documents with per-field state, confidence, and source anchors in metadata, plus an agent tool.

Independent Python implementation of the AINRA agent-passport verifier (verify-only, offline, fail-closed). The fourth column of the conformance differential.

Structured corpus of AGENTS.md — the written rules humans hand to AI agents ｜ 人写给 AI 智能体的书面规约的结构化语料库

CLI for the AI-Augmented Developer framework: validates skills, scaffolds feature specs, installs presets.

Kata (型) — Karpathy Development Cycle: CLI + OpenCode agent + Claude Code skills

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

A lightweight Python framework for orchestrating agent workflows: DAG scheduling, a stateful StateGraph with SQLite checkpoints for resume and idempotent re-execution, an MCP tool registry over stdio and SSE, and SKILL.md-based skill discovery — with no heavy framework dependencies.

Evil Hermes — sovereign agent framework by Lord Tanzeel Shujah Khan. Cyber-security tooling, automation, and adversarial research.

跨境物流HS Code智能归类Agent：RAG混合检索+ReAct主动追问+三层防幻觉+50组评测

목표만 주면 필요한 Agent 를 찾아 검증하고, 권한과 협업 순서까지 구성한다

AgentScope long-term memory middleware backed by Agentbase Memory

Evidence-backed reliability infrastructure for AI systems.

Spec-driven delivery for LLM coding clients, with a deterministic gate.

Minimal, model-agnostic harness for LLM agents: tool permissions, draft-commit approvals, verification, cost caps, and traces.

Turn local Next.js websites into interfaces AI agents can understand and use.