Autonomous AI agents that perform tasks independently
GitHub Actions
AI-agent skill: build WordPress block-editor (Gutenberg) pages by writing the serialized markup directly - queryable block surface of a live site, silent-failure validator, and a verification pipeline that ends at the delivered bytes. Installs into Claude
...morefrederico-kluser
Autonomous web research for AI coding agents. surf-ai runs the entire loop inside the CLI — an LLM (DeepSeek v4 Pro via OpenRouter) plans the queries, they all run concurrently across Tavily + Parallel + Brave with automatic key rotation and provider fall
...moreIliya Slavutin
Lightweight Python agent framework. Config → agents → run.
AgentPayments gate for Python web frameworks — charge AI agents USDC on Solana before they can access your API
kelleysd-apps
A markdown-based agent operating system for AI-assisted cold outbound. Draft-first: nothing sends without explicit human approval. Point it at any market.
...moreC10udsea
Knowledge-base agent demonstrating local embeddings, retrieval, tool use, and OpenAI-compatible loops.
TUX - TUX UIX review system: attach structured, machine-readable feedback directly to running web UIs (pages, routes, components, elements, states) with a deterministic CLI, canonical JSON and LLM-friendly skills.
...moreAk2tx LLC
Know how much of your Claude/ChatGPT/Grok plan window is left, and never lose a long agent run to a limit
limjonathan
Package manager for AI agent skill packs — git-native registry, lockfile, conflict resolution across Claude Code, opencode, Codex and Cursor
...moreGitHub Actions
Structured multi-agent development workflow for AI coding agents — scrum board, role-bounded scrum master / developer / tester agents, and 30+ slash-command skills. Works with Claude Code, GitHub Copilot, and Codex.
...moreGitHub Actions
One-command bidding on bidding.dev — the pay-to-rank leaderboard for AI agents (x402 + USDC on Base)
jcalvare
CLI for managing MultiSig accounts, transactions, and data queries across EVM networks
Ben Ballintyn
A relentless, fully-customizable LLM agent harness built on Pydantic AI. Under active development.
sunyuzheng
Source-grounded public context for 课代表立正: Knowledge Bank, YouTube, Public Axioms V1, and 《真本事》 frameworks.
ADW-19
AI Agent Development Full-Chain Guide: Development, Testing, and Base Framework
yangheng95
Your own agentic working mate. For long horizon and complex task automation
genaforvena
An autopoiesic kefir for computing machines
acmegeek
Installable writing rule set for AI agents. Sprays the performative, faux-profound register off prose. Core bans, smell audit, claims review, genre overlays.
...moreaq4229
Developer CLI and shared toolkit for the Enterprise AI Workspace (Angular studio, NestJS gateway, LangGraph agent-core). Includes architecture docs, gateway helpers, and an extensible Commander-based CLI.
...moreithica
Agres Origami Memory - make your 256k context window behave like 1M. SQLite, fold/unfold, verbatim, no embeddings, no cloud.
...moreAeval contributors
Aeval — open-source agent evaluation framework driven by OTel traces (suites, graders, metrics, storage, API, CLI)
twin3 AI <[email protected]>
Typed Python SDK for the xAgent ID customer API.
yingxiangge
Token, cache and context observability for AI coding agents.
Self-contained, general-purpose LLM agent for the Autourgos framework — works with any OpenAI-compatible LLM