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
apache/maka
Apache Maka (Incubating) is a local-first agent workspace under incubation at the Apache Software Foundation, aimed at running coding and tool-use agents for real work rather than demos. Sessions, settings, and run records stay on the user's own machine by default; the user brings the model, whether a cloud API, a local model, or a compatible gateway. Every model message, tool call, tool result, and how a turn ended is written to a durable record that the desktop UI and the next model call merely read from, rather than being the only copy of that state, so shortening the context sent to a model does not throw away the saved evidence of what happened. Three surfaces share one underlying Runtime Host: a desktop app built with Electron and React for daily interaction with streaming sessions, tool timelines, branching, search, and crash recovery; a TUI and CLI (maka, maka run) for using Maka from the current project directory or running a single non-interactive turn, sharing workspace and model connections with the desktop app; and an evaluation mode (maka eval run) for reproducible, declarative multi-arm benchmark experiments across Maka and external subjects, built from immutable per-cell attempts and a small result kernel covering score, usage, cost, duration, and failure reason. Built-in agent tools cover Read, Write, Edit, Bash, Glob, and Grep, with Computer Use and catalog skills available but off by default; any tool call that would leave the sandbox requires explicit approval, and failures are classified rather than surfaced as raw errors. Maka currently ships as unsigned nightly builds for macOS on Apple Silicon and a Windows preview, with Linux support planned; no Apache Software Foundation release has been made yet, so all current builds are convenience artifacts rather than ASF releases.
https://github.com/apache/maka
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.