Autonomous AI agents that perform tasks independently
bolivestilo
Homekit gives any AI agent direct, physical control over Apple Home. Flip lights. Lock doors. Read sensors. Through a single open interface.
...moreTristanBrotherton
Give your AI assistant a phone — OpenClaw plugin for real phone calls via Twilio + OpenAI Realtime, with in-call tools, transcripts, and call screening
...moreZenyaDAR
AI-powered MCP proxy for Playwright and Figma. Optimize Claude Code and AI agents with session recovery, context reduction and intelligent tool routing.
...moreagentlas-ai
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
kdcube
Open-source multi-tenant agent runtime for production. Tenant isolation, per-user cost controls, dual-sandbox security, deployment from Git.
...moreahmedhabibo
Cloud-first AI agent via NVIDIA NIM Free API — rate limiting, key rotation, smart fallback chain. Local mode for offline use.
...morenesirli
RAG-based question answering over the metagenomics literature
VoDaiLocz
An MCP server for safer coding agents: skill routing, C4 workflow gates, memory checks, and verification before completion.
...moreitwanger
Python terminal AI agent CLI with ReAct tools, MCP, Runtime API, memory, snapshots, web search, and image input
Raghav Mishra (PowerAI Labs)
Build an LLM agent with spending limits, a tamper-evident audit trail, PII redaction, and record/replay testing built in from the start — a governed agent in about 10 lines.
...moreGitHub Actions
aPaaS OpenAPI Node.js 客户端 SDK，内置 AI Agent 友好的模块化 Skills 与 Schema 辅助规则。
GitHub Actions
A registry and manager for AI agent skills — install, update, link and compose skills (presets) from git, npm and local sources, following the agentskills.io standard.
...morepine_forge
PineForge decentralized compute provider agent CLI
Continuous memory for coding agents — Claude Code and Codex CLI, one shared memory
GitHub Actions
Interactive terminal UI for exploring AppThreat atom files with AI agent
marksulls1234
The Directive command-line tool: coordinate AI agents from the terminal.
agentpack contributors
Write your agent skills once, ship them everywhere: Cursor, Claude Code, Codex, GitHub Copilot and any SKILL.md-compatible agent.
...moreExternal effect-admission gate for LLM-agent frameworks (Rust core, Python bindings)
ned
Recursive context-aware reasoning & planning for LLM agents — the ReCAP loop (arXiv:2510.23822) as a thin, provider-agnostic library.
...more一款纯净的自主 Agent 系统。
vhrtanek
reeeliance GmbH AI skill installer — select and install skills from the library into any AI agent
Raghav Mishra (PowerAI Labs)
Wrap your LLM client once and capture exact token counts and cost on every call — the shared foundation the other Cendor tools build on.
...moretarunkartikeya
AI company workforce simulator — multiple AI agents work together as departments on your projects
FinOps for LLM agents — unit economics and cost accountability in the developer workflow