Awesome AI Agents › Weekly › 2026-08-10
Claude Code Guide is a comprehensive and authoritative resource providing detailed instructions, tips, and references for using the Claude Code CLI tool to interact with the Claude AI model, including advanced features and MCP integration.
AI Agents From Scratch is an educational repository that teaches users to build AI agents locally using local LLMs and node-llama-cpp, focusing on understanding agent architectures, function calling, memory, and the ReAct pattern through progressive, hands-on examples.
Open-source workspace for building agents through chat using AGENTS.md, skills and MCP servers, with swappable harnesses, background runs, per-tool permissions, tracing and cost tracking.
SkillHub is a self-hosted, open-source agent skill registry for enterprises, enabling publishing, versioning, governance with RBAC and audit logs, and on-premise deployment via Docker or Kubernetes.
Agency Swarm is a reliable and production-ready agent framework that enables the creation and management of collaborative multi-agent AI systems using the latest OpenAI Assistants API, designed to automate workflows through customizable agent roles and efficient communication.
Go AI gateway that translates any SDK request into any provider format, adding request tracing, role-based access control, load balancing with failover and per-request cost tracking.
OpenAgents is an open platform providing versatile language agents for data analysis, plugin integration, and autonomous web browsing, designed for real-world applications and easy deployment.
Youtu-Agent is a high-performance, open-source agent framework that enables building and running autonomous agents with powerful capabilities like data analysis and research, featuring automatic agent generation and strong benchmark results.
Koog is a Kotlin-based framework by JetBrains for building scalable, production-ready AI agents that operate across multiple platforms and integrate with major LLM providers.
AI agent skill that turns documents into browser-editable HTML slide decks across 12 visual themes, with in-page editing controls and export to HTML, PDF and editable PPTX.
AI agent skill that turns documents into browser-editable HTML slide decks across 12 visual themes, with in-page editing controls and export to HTML, PDF and editable PPTX.
Self-evolving multi-agent research system built on DeepAgents, with six specialised sub-agents and a knowledge-graph memory, exposed through a web UI, a terminal interface and mobile.
X-CMD is a compact, AI-powered command-line toolkit that bootstraps over 1000 CLI tools, offers extensive environment management, secure sandboxing, and a stylish terminal experience to enhance productivity and streamline development workflows.
Open-source terminal coding agent from the Qwen team with subagents, skills, hooks and MCP support, speaking the OpenAI, Anthropic, Gemini and Qwen API formats plus local model runtimes.
ByteRover CLI (brv) provides persistent, structured memory for AI coding agents, allowing developers to curate context, share knowledge, and interact with LLMs.
Markdown-defined coding agents on top of the OpenCode CLI that load project-specific patterns before generating code and require human approval before every execution step.
AutoDev is an AI-powered coding assistant plugin for IntelliJ IDEA that offers multilingual support, automatic code generation, bug detection, customizable prompts, and a suite of interactive development tools to enhance the software development lifecycle.
Integuru is an AI agent that generates integration code by reverse-engineering platforms' internal APIs using browser network requests and OpenAI models to automate platform interactions without requiring permission.
Tokscale is a CLI utility and dashboard for tracking and visualizing token usage and costs across various AI coding agents.
DeepAnalyze is the first agentic large language model designed for autonomous data science, automating the entire data science pipeline from data preparation to report generation across diverse data types.
Visual retrieval-augmented generation pipeline that renders web pages, PDFs and images to screenshot tiles and retrieves over them with a LoRA-tuned Qwen3-VL embedding model.
Zep is an AI memory foundation that uses a temporal Knowledge Graph to enable continuous learning and personalized experiences for AI agents by efficiently managing and retrieving contextual chat and data artifacts.
OpenAgents Control is an AI agent framework for plan-first development workflows, emphasizing repeatable results, approval gates, and pattern-aware code generation across multiple languages. It hel...
Agent skill for Claude Code and Codex that rebuilds the object in a reference image as procedural Three.js TypeScript code through a gated, vision-reviewed, token-efficient pipeline.
Liveblocks is a platform providing customizable pre-built features to easily add multiplayer, engaging, and AI-ready collaborative experiences to applications without disrupting development roadmaps.
CADAM is an open-source web application that converts natural language and images into 3D CAD models using AI, running entirely in the browser with WebAssembly.
Cipher is an open-source memory layer designed for AI coding agents, enabling seamless memory and context management across multiple IDEs and AI assistants with MCP integration.
ACI.dev is an open-source platform that connects AI agents to over 600 tool integrations with multi-tenant authentication, granular permissions, and access via direct function calls or a unified MCP server, enabling production-ready AI agent development without infrastructure complexity.
Local-first MCP server giving AI agents keyless web search, fetch, crawl, extract, cache, find-similar and research tools that run on device and return cited, scored evidence.
AgentScope Java is an agent-oriented programming framework for building production-ready LLM-powered applications, offering features like ReAct reasoning, tool calling, memory management, and multi...
PPTAgent is an innovative system that automatically generates and evaluates high-quality presentations from documents using a two-phase approach and a comprehensive multi-dimensional evaluation framework.
AI-Infra-Guard by Tencent is a comprehensive AI Red Teaming platform offering intelligent vulnerability scanning, MCP server risk detection, and jailbreak evaluation to enhance AI security.