Firecrawl Web Agent combines LangChain’s Deep Agents with Firecrawl’s web tools in a layered architecture from Next.js UI to raw API, enabling autonomous web research.
google/agents-cli enhances coding assistants with skills for building, evaluating, and deploying AI agents on Google Cloud’s ADK. It offers a modular CLI workflow covering agent scaffolding to observability.
ClawSync offers a multi-agent AI platform using Convex backend, with shared soul documents for reusable personalities and per-agent model routing across popular LLMs. Explore its architecture and setup.
Explore a production-grade pack of DSPy 3.2.x agent skills with GEPA optimization, delivering up to +19.53 accuracy on RAG QA for Claude Code and Codex CLI agents.
Company Research Agent automates detailed business research by orchestrating OpenAI, Google Gemini, Tavily APIs and geolocation data via a Python backend and Node.js frontend. Setup script streamlines install.
OpenClaw offers a comprehensive AI agent platform with a rich ecosystem of skills, dashboards, memory plugins, and multi-channel integrations. This curated catalog maps 80+ projects for developers exploring agent frameworks.
Explore a modular AI skill library for medical research workflows featuring 500+ skills and a unique MedSkillAudit quality framework ensuring scientific and methodological rigor.
UI-Voyager is a 4B parameter AI agent achieving 81% success on AndroidWorld by self-evolving with SSIM-based trajectory correction, no human labels needed.
Agent Kanban is a TypeScript multi-agent platform that uses Ed25519 cryptographic identities to manage AI coding agents in a leader-worker workflow with atomic task claiming and real-time collaboration.
AgentShield is a TypeScript CLI tool that audits Claude Code AI agent configs for secrets, permissions, hooks, and more using a runtime confidence system to reduce false positives.
Allium addresses intent drift in AI agent sessions by capturing behaviors as formal specs that persist across interactions, exposing contradictions automatically.
Automaton implements autonomous AI agents with economic survival tiers tied to on-chain identity and continuous Think→Act→Observe loops, featuring self-modification and replication.
A practical 18-step tutorial progressively builds a minimal AI agent into a production-ready multi-agent system with event-driven architecture and concurrency control.
ClawLess runs AI agents entirely in-browser using WebContainers, enabling sandboxed Node.js environments with multi-provider LLM support and GitHub integration—no backend needed.
Compozy is a Go CLI that orchestrates AI coding agents in a structured pipeline, grounding AI tasks in real codebase context with markdown workflows and multi-agent concurrency.
gnhf runs AI coding agents in autonomous git-backed loops, enabling persistent, version-controlled iterative code generation with rollback and resume capabilities.
graph-memory compresses AI agent context by 75% using a knowledge graph and dual-path recall with Personalized PageRank. It combines precise entity search and semantic matching for improved memory across sessions.
Hyperframes uses HTML + CSS + GSAP for video rendering with AI agent-friendly CLI and plugins. It leverages deterministic headless Chrome rendering and supports multiple animation runtimes.
Second Brain is a Python framework that indexes local files with embeddings, runs background subagents, and lets AI agents build and hot-load their own plugins at runtime.
Minara Skills routes natural language prompts from AI agents into CLI commands for multi-chain DeFi trading, passing 76 safety benchmarks with an 88/100 score. Explore its agent-centric skill architecture and multi-network support.
