Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

An MCP server that lets LLM agents play Civilization VI.

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

A security scanner for your LLM agentic workflows

A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Shell and coding agent on mcp clients

Build and run agents you can see, understand and trust.

Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs

The World's First Virtual Terminal for AI Agents

AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).

Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first, then verify. Skill for Claude Code, Codex, and other agents.

GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.

Use Codex and Claude Code with COMSOL via sim-cli: .mph inspection, live Desktop sessions, bounded execution, artifacts.

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI

Open-source control plane for AI coding agents. Run an AI engineering team: parallel Claude Code, Codex, and Gemini workers with a shared board, atomic tasks, schedules, loops, origin-stamped messaging, model switching, and self-healing recovery. One dashboard, or your phone. MIT, single Rust binary.

1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.