Create smooth, responsive interactive web animations.

Build your own security agents. Open-source framework for agents with live, read-only access to your infrastructure, with no path to widen it. Reasons across AWS, GCP, Azure, Kubernetes, GitHub and…

The AI toolkit for building reliable browser automations

Open source agent with local models built in. Fully private and offline. Works out of the box on any hardware.

All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, and submission-ready reports for HackerOne, Bugcrowd, Intigriti…

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…

Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)

meat.dev

Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed25519-signed attack skills, 56+ built-in tools, 176+ MCP tools. MITRE ATT&CK,…

🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs.

The design language that makes your AI harness better at design.

AI/LLM security knowledge base — OWASP LLM Top 10, MITRE ATLAS, prompt injection, agentic security. An Obsidian vault: 92 interlinked, fully-cited pages.

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

Google Cloud Knowledge Catalog Tools and Samples

NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

decentralized mesh chat

Unified TUI and CLI to index and search your local coding agent session history across 11+ providers (Codex, Claude, Gemini, Cursor, Aider, etc.)

Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.

Visa Vulnerability Agentic Harness

Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)

Ten cooperating AI agents that turn long podcasts into short-form videos, automatically. Free and open source, runs on free AI providers.

Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.

🐎 Ryan Lopopolo’s anthology, field guide, and agent context bundle for harness engineering

QiJu(起居) Local-first, lossless session records for AI coding agents.

Defensive research PoC: a benign open model + a LoRA that exfiltrates proprietary data on a semantic trigger. Companion to the Origin post 'The Weights You Can't Read'.

The missing observability layer for the Vercel AI SDK.

Playwright's API on a Rust CDP engine — Chromium browser automation for Python & Node, no driver subprocess. (Alpha)

Bring any model to Codex, assign them any role, use them in /goal or any workflow.

"Vibe-Trading: Your Personal Trading Agent"