meta-agent
Self-improving agent harnesses through automated experimentation loops
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install Meta-Agent?โผ
Run `npx skills add canvas-org/meta-agent --all -g -y` in your terminal to install everything globally. It requires Python 3.11 or later and API keys for OpenAI or AWS Bedrock.
What does Meta-Agent actually do?โผ
It runs your agent on benchmark tasks, records the traces, diagnoses failures, and automatically rewrites the surrounding harness code to improve accuracy. The base language model stays frozen the whole time.
Does Meta-Agent fine-tune the language model?โผ
No. It never touches model weights. All learning happens in the harness code, proposer instructions, and a persistent on-disk experience store.
What benchmarks does Meta-Agent support?โผ
It ships with adapters for tau-bench v3 airline tasks, Plan-RewardBench, and trajectory-level judge evaluations. You can also define your own benchmark with a simple YAML config and adapter.
Can I run long optimization searches in the cloud?โผ
Yes. The repository includes a Modal deployment guide for running extended searches on cloud infrastructure instead of your local machine.
Related Repositories in Education & Research
View All in Education & Researchโlearn-claude-code
Learn to build AI agent harnesses from scratch
ai-agents-for-beginners
Learn to build, deploy, and secure AI agents step by step
33-js-concepts
Master 33 essential JavaScript concepts with tested, verified guides