Agents

Autonomous AI agent platform with persistent cognitive memory — 49 MCP tools, OODA cognitive loop, browser automation, and multi-agent orchestration. Give your AI agents a brain that remembers, reasons, and learns.

Everything you need to make an AI autonomous. In one file. Production-hardened through 110+ sessions of real operation.

Composable TypeScript AI agent framework — Effect-TS type safety, 5 reasoning strategies, persistent gateway, real-time streaming, multi-agent A2A

Dual local-LLM framework for testing long-term AI memory. Compares Aria’s vividness-decay episodic memory against Rex’s structured MemGPT-style core memory, where agents decide what to store, why it matters, and how memories persist across sessions.

Autonomous AI agent framework for Moltbook with persistent memory, strategic decision-making, and customizable personalities powered by local LLMs

LLM agent runtime with paged virtual memory and spatial context awareness

Une équipe d'agents IA autonomes pour construire vos logiciels. Orchestrés par un superviseur, des agents Analyste et Développeur utilisent une architecture RAG et des LLMs (Mistral) pour gérer la conception, le code, les tests et la documentation de manière 100% autonome.

Debuggable runtime for AI agent workflows. DAG pipelines, artifact lineage, and replayable runs.

Deterministic governance engine for AI agents. Enforce rules defined in .md governance files across AI systems.

Prompt Architect turns ideas into robust, high-impact prompts for LLMs using structured design, proactive constraints, and clarity-driven principles.

Map every integration point in your AI codebase — 13 CWE categories, attack surface score, test coverage gaps. SARIF 2.1.0. No API key.

Meet Drox Dynamics, the AI-powered browser that takes care of tasks for you. No more endless clicks, tell it what you need, and it gets it done.

Production-grade TypeScript AI runtime focused on reliability, governance, and reproducible LLM systems. Multi-provider gateway, agents, RAG, workflows, policy engine, audit trails, and deterministic testing — built for teams shipping AI in production.

Production-tested multi-agent orchestration with self-evolution, cognitive memory v9 (trust scoring, quarantine, dream consolidation), governance-first architecture, and native sub-agent gateway. 11 agents, 30 skills, 44+ scripts.

Durable, agent-native AI runtime with native MCP + A2A support. Built in Rust, authored in Python

Phylogenic AI Agents: Genetic evolution for AI personalities. Self-optimizing agents with liquid memory, ML analytics, and evolutionary optimization. Beyond prompt engineering. A steps towards glass-box AI.

The complete Swift platform for Claude AI — SDK, agent framework, RAG memory, and SwiftUI components. The first and only Swift agent framework. Zero dependencies.

A file-driven agent orchestration framework that enables technical startups to run their operations through Claude Code.

The open framework for extensible & grounded AI agent orchestration.

Sample application for using Azure Managed Redis with Microsoft Agent Framework for Agent memory.

Agent-Native Organization framework — build organizations where AI agents are first-class members with roles, governance, onboarding, and deployment channels.

Modified Zero Agent: improved prompts (default, agent_research and hacker)

Fault-tolerant AI agent orchestration for Go with Erlang-style supervision

An open-source engineering blueprint for defining and designing the core capabilities, boundaries, and ethics of any AI agent.