A MetaAgent orchestrates specialized sub-agents to solve tasks — while generator, evaluator, and optimizer agents continuously grow the tool, skill, and agent ecosystem.
A clean, registry-driven core where every capability is a hot-pluggable component, and dedicated agents grow that ecosystem over time.
A planning agent decomposes tasks, dispatches subtasks over an Agent Bus, executes in parallel, and evaluates — looping until done.
Generator, evaluator, and optimizer agents create, assess, and refine tools, skills, agents, and environments automatically.
The ExtensionManager layers evolved components on top of built-ins at runtime — versioned, archived, and instantly rollback-able.
Tools, agents, prompts, skills, benchmarks, hooks, constraints, memory — each self-registers via a clean mmengine registry.
Watch every agent step through a task in real time in your browser, with full run artifacts written to the work directory.
Ships with AIME, GPQA, GSM8K, HLE, LeetCode, DeepWeb and more — datasets-first with automatic HuggingFace fallback.
The MetaAgent plans and dispatches work over the Agent Bus to specialist sub-agents that run in parallel and return results for evaluation.
For every kind of component, three agents form a closed improvement loop — new capabilities are born, judged, and refined without touching the immutable core.
Hand-written built-ins live in src/ and never change. Evolved components live in an external extension/ tree, loaded and versioned by the ExtensionManager — so the system can grow safely and roll back instantly.
Each module self-registers with an mmengine registry — discoverable, swappable, and evolvable.
Datasets are read locally first, then snapshot-downloaded from HuggingFace on demand.
Set up the environment, then let the MetaAgent run a task to completion.
# 1 · create the Python environment conda create -n agent python=3.12 conda activate agent pip install -r scripts/requirements.txt # 2 · browser automation pip install playwright && playwright install pip install browser-use && browser-use install
# run the default task python examples/run_meta_agent.py # run an inline task python examples/run_meta_agent.py \ --task "Reverse a string + add unit tests" # run from a task document python examples/run_meta_agent.py \ --task-file examples/tasks/qsar_egfr_experiment.html
Full setup (Vault secret manager, opencode, Python env) is documented in scripts/INSTALL.md →