Orchestrates a hierarchical multi-agent system for Mojo-based AI research and development, automating workflows across planning, implementation, testing, code review, and deployment phases with structured delegation and CI/CD integration.
This directory contains documentation, templates, and reference materials for the Odyssey multi-level agent
Each delegation reduces scope by one level:
<!-- markdownlint-disable MD051 -->
<!-- markdownlint-disable MD051 -->
<!-- markdownlint-disable MD051 -->
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Mojo-based platform for reproducing classic AI/ML research papers with production-quality implementations. ML Odyssey provides a shared library of SIMD-optimized tensor operations, an autograd engine, and a full training infrastructure — all implemented in Mojo for maximum performance and type safety.
ML Odyssey is a standalone Mojo-based ML framework for reproducing classic AI/ML research papers with production-quality implementations. It has two goals:
The project currently has ~198K lines of Mojo code, 7 fully-implemented neural network architectures, and 332+ tests across layerwise unit tests and end-to-end integration tests.
Note on project identity: The GitHub repo description says "Training framework written in Mojo." This repo is sometimes described elsewhere as an "experimental agent research sandbox" -- that description is incorrect. ML Odyssey is an ML training framework, not an agent platform. It has no integration with ai-maestro, NATS, or any distributed agent mesh. The "agent system" referenced in this repo refers to Claude Code automation for development workflow (code generation, PR creation, CI management), not a runtime agent mesh.
Odyssey is one of several repositories in the HomericIntelligence organization. Here is how the repos relate:
| Repository | Role |
|---|---|
| Odyssey (this repo) | ML training framework in Mojo -- neural nets, autograd, shared lib |
| [Odysseus][odysseus] | Ecosystem meta-repo and architecture docs |
| [AchaeanFleet][achaeanfleet] | Container images for the agent mesh -- Dockerfiles, Compose, CI |
| [Myrmidons][myrmidons] | GitOps agent provisioning -- agent definitions as code |
| [ProjectHephaestus][hephaestus] | Shared utilities and tools used across the ecosystem |
| [ProjectMnemosyne][mnemosyne] | Skills marketplace -- collective memory of team learnings |
| [ProjectScylla][scylla] | Testing and optimization framework for agentic workflows |
| [ProjectKeystone][keystone] | Foundation project |
| [ProjectArgus][argus] | Ecosystem project |
| [ProjectHermes][hermes] | Ecosystem project |
| [ProjectProteus][proteus] | Ecosystem project |
| [ProjectTelemachy][telemachy] | Ecosystem project |
npx claudepluginhub homericintelligence/odyssey --plugin fix-implicitlycopyable-removalShared tooling plugin for the HomericIntelligence ecosystem. Ships 23 skills: skill-advisor, advise, learn, myrmidon-swarm, brainstorm, test-driven-development, systematic-debugging, verification, git-worktrees, finish-branch, code-review, repo-analyze, repo-analyze-quick, repo-analyze-strict, repo-analyze-full, repo-analyze-quick-full, repo-analyze-strict-full, review-pr-strict, worktree-cleanup, tidy, create-reusable-utilities, github-actions-python-cicd, and python-repo-modernization.
Agent-host plugins and skills imported by Claude Code / Codex / Pi.
ML research skills: topic, plan, judge, run, sweep, verify, fortify, retro
ML/RecSys/LLM training workflow for AI agents: Validation Pyramid, experiment planning, process metrics, and proven ML development patterns
ML engineering plugin: Give your AI coding agent ML engineering superpowers.
Track and manage model versions
ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows
Core Hugging Face Hub operations through the hf CLI, including skill installation, repo management, jobs, datasets, models, Spaces, and discovery.