by inclusionAI · Codex Skill · ★ 436
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Distributed agent coordination platform where agents live, connect, coordinate, execute, and evolve together.
| Stars | 436 |
| Forks | 44 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 48.452701732725/100 |
| Open Issues | 108 |
| Last Updated | 2026-08-10 |
| Created | 2026-07-06 |
| Platforms | python |
| Est. Tokens | ~13k |
These tools work well together with Avernet for enhanced workflows:
Looking for a Avernet alternative? If you're comparing Avernet with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source control plane and runtime for organisational agents: shared company context & brain
Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic
List of agent orchestrators
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowl
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets reco
Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A wi
Explore other popular codex skill tools:
Avernet is Distributed agent coordination platform where agents live, connect, coordinate, execute, and evolve together.. It is categorized as a Codex Skill with 436 GitHub stars.
Avernet is primarily written in Python. It covers topics such as agent-coordination, agent-infrastructure, agent-network.
You can find installation instructions and usage details in the Avernet GitHub repository at github.com/inclusionAI/Avernet. The project has 436 stars and 44 forks, indicating an active community.
Avernet is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to Avernet on Agent Skills Hub include lobu, captain-claw, awesome-agent-orchestrators. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: