ai-agents
Tracked open-source repos tagged ai-agents, sorted by stars.
- #271
List of 67 awesome DESIGN.md and SKILL.md design skill files for agentic tools like Claude Design, Google Stitch, Codex, Cursor, and other AI tools
★ 2,585+112Star change over the last 7 days - #272
Agent Skills to help developers using AI agents with Supabase
★ 2,561+27Star change over the last 7 days - #273
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
★ 2,561+9Star change over the last 7 days - #274
YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.
★ 2,557+160Star change over the last 7 days - #275
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
★ 2,529+38Star change over the last 7 days - #276
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
★ 2,503+6Star change over the last 7 days - #277
🥂 Gracefully face hCaptcha challenge with multimodal large language model.
★ 2,484+8Star change over the last 7 days - #278
180 free CSS3, Figma, Sketch & PSD gradients — plus a JSON dataset for design tools, generators, and AI agents.
★ 2,473+1Star change over the last 7 days - #279★ 2,439+5Star change over the last 7 days
- #280
An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.
★ 2,408+28Star change over the last 7 days - #281
Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring, and CTF modes. Built with Go, Claude API, and 7+ native security tools.
★ 2,398+181Star change over the last 7 days - #282
Collection of Apify agent skills
★ 2,363+7Star change over the last 7 days - #283
Workflow SDK: Build durable, reliable, and observable apps and AI Agents in TypeScript
★ 2,363+20Star change over the last 7 days - #284
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.
★ 2,356+56Star change over the last 7 days - #285★ 2,349+1Star change over the last 7 days
- #286
🌀 AI-native framework for building data portals. Scaffold a full portal from a brief and load datasets in minutes with agentic skills — any backend (CKAN, GitHub, Frictionless).
★ 2,347+4Star change over the last 7 days - #287
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
★ 2,346+12Star change over the last 7 days - #288
Real-time AI coding agent status panel in your MacBook notch — live status, approvals & replies for 13 AI tools, with iPhone & Apple Watch companions
★ 2,337+19Star change over the last 7 days - #289
:sunglasses: All the required resources to build your own startup
★ 2,335+4Star change over the last 7 days - #290★ 2,324+6Star change over the last 7 days
- #291
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
★ 2,313+15Star change over the last 7 days - #292
【A common used C++ & Python DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流
★ 2,301+1Star change over the last 7 days - #293
A general purpose scientific writer
★ 2,274+34Star change over the last 7 days - #294
DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.
★ 2,274+3Star change over the last 7 days - #295
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
★ 2,267+23Star change over the last 7 days - #296★ 2,262+44Star change over the last 7 days
- #297
A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every query.
★ 2,257+6Star change over the last 7 days - #298
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.
★ 2,254+0Star change over the last 7 days - #299
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
★ 2,252+16Star change over the last 7 days - #300
🧭 Architecture-first system design: 26 bilingual tutorials, 25 architecture templates, and 6 end-to-end cases covering distributed systems, AI-native systems, RAG, coding Agents, and production trade-offs.
★ 2,233+38Star change over the last 7 days