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
Chen-zexi/open-ptc-agent
Open PTC Agent is an open-source implementation of programmatic tool calling, the pattern in which an agent invokes tools by writing and executing code rather than emitting one JSON tool call at a time. The agent discovers available tools, writes Python that orchestrates them, and runs that code inside a Daytona sandbox; intermediate data is filtered, aggregated and transformed locally, and only the final output is returned to the model. The README argues this matters most for large volumes of structured or time-series data, citing a demo that analyses two years of stock data spanning more than fifteen thousand lines of JSON and claiming token reductions of roughly 85 to 98 percent compared with returning full tool results into the context window. The project is built on LangChain DeepAgents, with its CLI bootstrapped from deepagent-cli, and remains compatible with LangGraph Cloud and Studio deployment. Features include universal MCP support that auto-converts any MCP server's tools into Python functions, progressive tool discovery so tool definitions are loaded on demand instead of up front, uploading custom Python MCP implementations directly into a sandbox session, and file tools such as glob and grep tuned for the sandbox filesystem. Subagents run asynchronously with task identifiers so the main agent keeps working while they execute, with helpers to wait for completion and retrieve cached output. Extensibility follows the open Agent Skills standard, a view_image tool adds vision and multimodal input from URLs, base64 data or sandbox files, and generated charts are auto-uploaded to Cloudflare R2, AWS S3 or Alibaba OSS. An interactive ptc-agent CLI provides session persistence, a plan mode and themes. Any provider configured in llms.json can be used. It requires Python 3.12 or newer and is MIT licensed.
https://github.com/Chen-zexi/open-ptc-agent
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.