kepano/obsidian-skills
Obsidian Skills provides a collection of agent skills enabling AI agents to interact with Obsidian vaults, facilitating content creation and editing of Markdown, Bases, and JSON Canvas files, as we...
Awesome AI Agents › AI Agent Development
google-antigravity/antigravity-sdk-python
The Google Antigravity SDK is a Python library for building AI agents powered by Antigravity and Gemini. It provides an infrastructure layer that hides the agentic loop, so developers describe what an agent should do rather than implementing how it runs. The package is installed from PyPI as google-antigravity, and the README stresses that cloning the repository is not enough because the SDK depends on a compiled runtime binary shipped only in the platform-specific wheels. The simplest entry point is the Agent class, an async context manager that handles binary discovery, tool wiring, hook registration and policy defaults; it is constructed from a LocalAgentConfig that optionally carries system instructions and an API key, and exposes a chat method returning a response object. Responses can be awaited as text or iterated with async for to stream conversational tokens as they arrive, and advanced properties allow separate streams of internal reasoning deltas and strongly typed tool call events, which suits user interfaces that display thinking bubbles or execution spinners. For safety the Agent runs read-only by default; passing a CapabilitiesConfig enables the full toolset including writes. A helper runs an interactive loop for console use. For finer control, the Conversation class combined with a ConnectionStrategy such as LocalConnectionStrategy and a ToolRunner gives a stateful session that accumulates step history, exposes turn count and last response, and can be driven at a low level by sending a message and iterating received steps. Multimodal ingestion accepts images, video, audio and documents, either constructed directly from in-memory bytes with typed content classes or loaded from a filesystem path through a helper that resolves the type and guesses the MIME format, then mixed with text instructions in a prompt list. The SDK also targets the Gemini Enterprise Agent Platform, formerly Vertex AI, configured through explicit project and location settings or environment variables with Application Default Credentials.
https://github.com/google-antigravity/antigravity-sdk-python
Also in AI Agent Development
Panniantong/Agent-Reach
Agent-Reach allows AI agents to access web content from major social media and video platforms through a CLI, without API fees, enhancing their perceptual capabilities.
JCodesMore/ai-website-cloner-template
This project provides a reusable Next.js template for reverse-engineering and cloning any website into a modern codebase using various AI coding agents.
huggingface/smolagents
Smolagents is a minimalistic Python library by Hugging Face for creating intelligent agents that think and act by generating and executing Python code, supporting multiple LLMs, modalities, and tool integrations.
alibaba/page-agent
Page Agent is a JavaScript in-page GUI agent enabling natural language control of web interfaces without browser extensions or headless browsers, supporting various LLMs.
TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory provides a local, 4-tier progressive pipeline for AI agent long-term memory, enhancing performance and reducing token usage without external API dependencies.
titanwings/distilly
A meta-skill that distills messages, documents, interviews and public sources about a person into a source-grounded Person Profile, packaged as an Agent Skill for coding agents and chat bots.
coze-dev/coze-studio
Coze Studio is an all-in-one AI agent development platform that simplifies the creation, debugging, and deployment of AI agents through visual tools and supports no-code and low-code development approaches.