Search

Secure your LangChain agents with per-agent identity, policy enforcement, and tamper-proof audit logs.

DevFortress SDK — API and application security with automated threat response, session privacy, and AI agent observability.

A lightweight, production-ready AI security SDK for protecting LLM agents.

ElizaOS plugin for Project Substitute Arena — counterfactual CEO simulation (Toys R Us 2006-2017)

Self-evolving R&D framework for Claude Code. Claude becomes an autonomous scientist who owns the project, researches deeply, builds knowledge, and never stops learning.

AI agent orchestrator that gives existing agents the drive to persist — set a goal, and PulSeed observes, delegates, verifies, and loops until done.

Cursor-native multi-agent development framework with 5-role review

Manage and sync AI agent skills across Claude Code, Cursor, Windsurf, and Codex

AI-powered JSON Schema document generator with TUI, web viewer and mock server

**Email infrastructure for AI agents.** Read and manage your Broodnet mailboxes from the terminal.

Phase 1 MVP CLI for Newton academic assistant

Your AI co-teacher. Generate lessons, games, slides, and assessments from your terminal. Learns your teaching voice, aligns to your state standards, and works with any LLM provider.

Browser automation for AI agents. Single binary, zero dependencies, CDP direct.

Build, debug, evaluate, and operate AI agents. The only SDK with fork-and-rerun Agent Replay.

Time completo de desenvolvimento autônomo por IA

A powerful AI agentic system

EngramX — The open-source agent memory framework with pluggable storage, lifecycle policies, observability, and framework adapters.

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. It is free in open claw for the first five days. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient qu