Search

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Clip can generate short clips, loops, previews.

Qwen 3.6 Plus Preview is the next-generation evolution of the Qwen Plus series, featuring an advanced hybrid architecture that improves efficiency and scalability. It delivers stronger reasoning and more reliable agentic behavior compared to the 3.5 series. In benchmarks, it performs at or above leading state-of-the-art models. Designed as a flagship preview, it excels in agentic coding, front-end development, and complex problem-solving. Note: The model collects prompt and completion data that

LangChain integration for Smara Memory API — persistent memory for AI agents

CrewAI integration for Smara Memory API — persistent memory for AI agents

Invisible, auto-syncing personal storage for any git repo

Explicit, async-first tool framework for LLM agents

Runtime Governance Framework for Multi-Agent AI Systems — deterministic enforcement, Pearl Level 2-3 causal reasoning, tamper-evident audit chain

Foclan 1.0: a compact LLM-first language for precise data transformation and output shaping.

Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.

Bridge any MCP server to Google A2A protocol — expose MCP tools as A2A-compatible agent skills

AI career agent with 36 tools — gathers LinkedIn/GitHub/GitLab data, builds a RAG knowledge base, analyzes skill gaps, tracks job markets, and generates ATS-optimized CVs. Chat-first, powered by LangChain + ChromaDB.

anqclaw 是一个用 Rust 构建的私人 AI 助理，支持飞书接入、CLI 对话、多 LLM、工具调用与持久记忆。anqclaw is a private AI assistant built with Rust, featuring support for Feishu integration, CLI conversations, multiple LLMs, tool calling, and persistent memory.

NTK — 基于信息密度路由的多智能体框架。用最少的 token 做最多的事。

100 production-grade Python libraries for LLM agents — fault tolerance, guardrails, memory, retries, observability. Zero dependencies. 4375 tests.

trama – Agents don't need frameworks. They need a runtime.

NostrMind is a config-driven Nostr monitoring worker with AI classification and optional DM alerts.

prompt building from https://github.com/yetone/voice-input-src

LLM scaffolding for independent operators — March 2026 collection. Deterministic 7-stage refinement pipeline, LLM Overdose Image Analyzer v5.0, arXiv PERSONAL Auditor v1.1, reproducibility primitives (SHA256 caching), and scholarly integrity tools by ZZZ_EPOCHE

Open-source React components for Agentic transparency. Trace every step of AI agent reasoning and make it visible, verifiable, and controllable.

Run AI coding agents from your phone. Bridges Claude Code, Codex, OpenCode, Pi, Gemini CLI, and Amp to Telegram with interactive permissions, voice input, cost tracking, and live progress.