Autonomous AI agents that perform tasks independently
stacksmart
UI kits + AI agents for Claude Code, Cursor, Copilot, Windsurf and more. Go from idea to solid product base faster.
pi-porenta
Pi extension package for a sequential ML/algo-trading quant agent chain.
trstnk
Agentic AI assistant that turns natural-language requests into AWS CLI commands and runs them locally.
pisama
Catch silent failures in your AI agents. TypeScript SDK for Pisama, the failure detector for vibe-coded agents (Cursor, Claude Code, LangGraph, Vercel AI SDK).
...morethinkfleetai
Activepieces piece — convert any web page or PDF into an AgentMark snapshot, then drive it from any flow.
GitHub Actions
SDLC enforcement for OpenCode CLI — privacy-first, any-backend portability with a four-tier backend picker plus an OSS-tier cross-model-review skill so the full SDLC loop can run with zero Anthropic+OpenAI lock-in. Ships JSON Schemas for review artifacts
...moreyannborie
Serge for React — drop-in <Analytics /> + <DetectionPixel /> components for catching AI-agent sessions on your site.
firatcand
A lightweight framework for shipping software products from idea to production with AI coding agents (Claude Code, Codex CLI, Cursor, Gemini)
...moreGitHub Actions
A browser-only GeoAgent MapLibre GL JS control with Strands agent tools
Palveron adapter for Microsoft Agent Governance Toolkit (AGT) — enforce Palveron governance policies locally in AutoGen and LangChain agent pipelines.
...moreA-share single-stock deep-dive multi-agent research workstation with three-tier trust isolation, FTS5 memory retrieval, dream loop introspection, and BYOM extensibility.
...moreManage and sync coding-agent skills (Claude Code, Codex, skills.sh)
itechgenie-user
CLI agent that bridges ITG Playwright Studio data into local Playwright workflows
Autonomous Ventures
Queue/event agent communication layer for multi-agent systems
Pavan Subhash Tirumalasetti
Chaos engineering for AI agents — inject realistic production failures (tool timeouts, malformed responses, cost spirals, prompt injection) and find out what breaks before your users do.
...moreAirframe Contributors
Vendor-neutral agent runtime: one protocol, pluggable adapters for Claude Code, GitHub Copilot, OpenAI Codex, and OpenCode Zen.
...morePromptClarity
A quality, clarity, and risk validation SDK for LLM inputs.
Yuan Yuan, Jing Liu
Calibrated dynamic scheduling benchmarks and tools for LLM-based scheduling-agent analysis.
Are your AI tokens paying off? CLI that classifies your Claude Code sessions and shows ROI.
An autonomous text-to-dataset agent — turns any website or document corpus into a typed, research-grade dataset in minutes. Works with Gemma, Llama, Gemini, GPT and any OpenAI-compatible model.
...moresashvat-bharat
The JIT (Just-in-Time) Tool Spawning Protocol: A Smart Routing System for Infinite-Tool AI Agents
huangjia2019
A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider, OpenHands, DeerFlow. Companion to Designing AI Agents (Manning) by Jia Huang.
...moreBaruchEric
Flexible UI framework that streams UI to the user, guided by an AI agent
srinitude
Mastra memory provider for Hermes Agent — 8 tools, per-profile isolation, versioned artifacts, 425+ tests