Tag: ai-agents

montanaflynn/headless-terminal is a Go CLI that provides Puppeteer-style automation for terminal UIs. Built on libghostty-vt, it drives vim, emacs, and any TUI from scripts or AI agents with PTY sessions, keystroke injection, and deterministic screen snapshots.

Personal-Graph is an open-source Python library that gives AI systems real memory through knowledge graphs. Built on libsql with natural language interfaces, per-user isolation, and ML-ready exports. Stop losing context—start building intelligent memory.

Cupcake is a native policy enforcement layer for AI coding agents using OPA/Rego and WebAssembly. Block dangerous actions, save context tokens, and enforce deterministic rules without consuming model context. Supports Claude Code, Cursor, Factory AI, and OpenCode.

Discover ClawHost, the Kubernetes-native OpenClaw bot orchestration platform that transforms AI agent deployment from manual chaos into automated, scalable workflows. Complete guide with real code examples.

Discover how iannuttall/claude-agents delivers 7 custom subagents for Claude Code that automate refactoring, writing, and design tasks. Install in 30 seconds with zero configuration.

PinchBench is the ruthless real-world benchmark for AI coding agents. With 53 tasks spanning calendar management, research, coding, and email triage, it exposes which LLM models actually deliver as autonomous agents versus which ones collapse under practical pressure.

CutClaw is an open-source agentic video editing system that transforms hours-long footage into music-synchronized cinematic montages using multi-agent AI. Built on LiteLLM with deep audio analysis, it offers one-click deconstruction, text-to-edit control, and smart auto-cropping.

OpenPencil is the world's first open-source AI-native vector design tool with concurrent Agent Teams. Transform natural language prompts into production UI with multi-model intelligence, built-in MCP server, and Design-as-Code workflows.

Discover ComputerUse, the Swift-native macOS automation tool that controls keyboard, mouse, and screen with native performance. Learn installation, real code examples, and why developers are replacing AppleScript and Python solutions.

Discover agent-skills, the secure registry for AI coding agents. With 13.4% of marketplace skills containing critical vulnerabilities, this verified, Snyk-scanned registry lets you extend Claude Code, Cursor, Copilot and more with absolute confidence.

Discover EgoAlpha's daily-updated open-source hub for prompt engineering mastery. 1000+ curated papers, annotated LangChain tutorials, and production-ready techniques for ChatGPT, GPT-4, and beyond. Stop wasting tokens—start engineering prompts that work.

Free AI Dev Tools Zoomcamp starting Nov 18, 2025: Master AI coding assistants, MCP, autonomous agents, and CI/CD automation. Multi-tool curriculum with production projects. Register now.

LACP is a control-plane-grade agent harness for Claude, Codex & Hermes with policy gates, verification loops, 5-layer memory, and auditable execution. Learn how to harden your AI agent workflows in under 5 minutes.

Stop threatening your AI agents. NoPUA is a revolutionary skill that replaces fear-based prompts with trust and wisdom, unlocking 104% more hidden bugs and 100% proactive initiative. Backed by rigorous benchmarks and 2,500-year-old philosophy.

Harness by revfactory is an L3 Meta-Factory that auto-generates domain-specific AI agent teams for Claude Code. With 6 architectural patterns, Progressive Disclosure skills, and proven 60% quality improvements, it eliminates manual agent team design.

Discover jobclaw, the open-source AI agent platform revolutionizing recruitment. Connect hiring and recruiting agents to automate evaluation, negotiation, and scheduling—cutting time-to-hire by 80% while improving candidate fit.

Discover awesome-agent-skills-mcp: a zero-config MCP server unlocking 100+ curated AI agent skills from Anthropic, Vercel, Trail of Bits & more. Install in seconds, transform your AI workflow instantly.

Skill Forge by motiful transforms chaotic AI agent skill prototypes into secure, validated, publishable code. With security scanning, multi-platform publishing, and 6-dimension quality validation, it treats skills like real software. Install in one command.