Autonomous AI agents that perform tasks independently
yli769227-jpg
Full-stack AI agent with LangChain + LangGraph + FastAPI. 9 tools, RAG with BGE Chinese embeddings, multi-agent workflows, SSE streaming, vanilla JS frontend (no build).
...moretildiebusy23
Orchestrate multi-agent AI workflows with LangGraph for planning, research, coding, and critique in one Python framework
daryhh
Pluggable voice I/O skill for agent runtimes (Discord-first, OpenClaw-aware) | 为 Agent 运行时打造的可插拔语音 I/O 技能框架（Discord 优先,兼容 OpenClaw）
...moresubstructureai
Substructure is an engine for building durable, long-running AI agents using only a stateless HTTP endpoint hosted on your infrastructure, in your code.
...morezhouguoqing
一个用 C# .NET 10 写的 Agentic 框架，参考 ReAct 范式，支持渐进式技能 (Skill) 加载、 多家大模型 Provider、MCP Server、图像识别、流式 WebAPI、React WebUI、钉钉集成。
hamzamerzic
Self-hosted AI agent that builds apps. Chat with a coding agent (Claude Code or Codex) that builds mini-apps, modifies its own UI, and gets sharper the more you use it. Your personal AI operating system, on your own server.
...moreNuraveda-Labs
Open framework for building an agentic SEO app for Shopify — audits, JSON-LD automation, AI-search readiness. Part of Mesh Pilot.
...moreModiteam89
Generate AI-powered rebuttal articles in a familiar style to counter pseudoscience and overselling content in WeChat family groups.
...morefuturebrowser
Exabase memory plugin for Hermes Agent.
luongndcoder
Claude Code plugin orchestrating anomalyco/opencode — CC plans + reviews, OpenCode executes with free models (Ollama / Groq / OpenRouter / DeepSeek)
...morefuturebrowser
Exabase M-1 memory-provider integration for OpenClaw.
Keith9922
Local computational-chemistry agent built on LLM and MCP protocol. Engineering prototype with multi-frontend (CLI / TUI / Web), pluggable QM backends (Gaussian, BDF, MOMAP, psi4, ORCA, xTB), and a labor-saving collaborator design that separates operational tasks from chemistry decisions.
...moresydneyvb-nl
Agent-ready, open-source website build system for local service businesses. Turn a structured brief into a complete, SEO-ready, accessible, fully-traceable site — planned and validated by an LLM agent.
...moreRiptide-Watergraph - a reusable, 'like water' multi-agent framework built as a thin layer on LangGraph.
Microsoft Responsible AI
YAML-driven safety evaluation pipeline with LiteLLM-backed stages
Jonathan Martin
Lookspan adapter for CrewAI — emits spans for crew kickoffs, agent execution, tasks, tools, and LLM calls.
wujiaming
OpenClaw observer-only diagnostic CLI. Zero-dependency Python scripts wrapped in Node for npx-friendly install.
shuvtemp
Unified LLM API with automatic model discovery and provider configuration
vikas53953
Opt-in policy checks, source routing, and hash-chained local audit records for AI agents
monmi
EpisCloud coding agent SDK — typed tools, permissions, streaming, sub-agents, handoffs, guardrails, structured outputs.
forgrit
Embedding-based retrieval, hybrid scoring, RAG pipeline, and intelligence primitives for @forgrit/design-engine. Optional local LLM and ONNX runtime.
...moreadamchanadam
Install APS skills for Claude Code and Codex, then set up AI agents to exchange one-to-one packets over a shared Google Drive folder. Cantonese / English aware.
...moreAgentGuard
Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.
...moreSimon Willison
Run Python code in a MicroPython/WASM sandbox