AI product Open source
Reef is open-source continual-learning infrastructure for self-improving AI agents, developed by Human-Agent-Society. It connects agent inference, interaction records, feedback, learning jobs, evaluation, and versioned delivery, supporting updates to model weights as well as agent harnesses such as prompts, rules, and skills.
Each learning cycle has four stages: Reef serves requests and records interactions; matches later scores or structured feedback to those records; produces a candidate update from eligible records; and evaluates the candidate against a configured selection policy before publishing it. Rejected candidates leave the previous release serving, while accepted updates are committed and delivered without restarting the service.
The project provides an HTTP API with OpenAI- and Anthropic-compatible inference endpoints, feedback reporting, scenario-based releases, and integrations for training or inference components including Slime and SGLang. It can be installed from PyPI as `reef-infra` or from source; artifact and checkpoint management requires Git LFS.
1 use taken from transcripts — each links to the moment in the video.
Infrastructure for agents that improve from real feedback while continuing to serve requests. It records interactions, connects later scores or comments to runs, evaluates candidate updates, and publishes only versions that pass policy.
1 in the library.