reef

Open-source infrastructure for continually self-improving agents that serves requests, learns from feedback and versions updates.

Harness by Human-Agent-Society

IndexedApache-2.0★ 7,694

Write a review

Install

From the package registry. Read the repository before you give any tool access to your data.

pip install reef-infra

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Reef is open-source infrastructure for agents that keep improving from their own interactions. It serves agent requests, matches feedback to recorded interactions, produces updates from eligible records, and commits accepted updates to a version history. Updates can train model weights with Slime and SGLang, or change an agent's harness such as its prompts, rules and skills.

Use cases: agent-orchestration

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages: PythonREADME
Packages: reef-infra (pypi)README
Maturity: Betagithub.com

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Signals

Stars: 7,694
Forks: 714
Open issues: 77
Weekly downloads: 78
Last commit: Oct 24, 2026 (3 days ago)
Last release: Oct 14, 2026 (13 days ago)
Last package publish: Oct 14, 2026 (13 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages: pypi reef-infra
License: Apache-2.0
Repository: github.com/Human-Agent-Society/reef
Website: reefinfra.ai
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql