DEDUPED Hot AI repos, turned into use cases Get the Monday 5
7,731 stars · Python

How to use Reef: what you can do with it

What is Reef? Reef is open-source infrastructure that connects agent inference, feedback, learning, and versioned delivery so that models or agent harnesses keep improving.

How do I use it? Install the package with uv pip install reef-infra inside an activated virtual environment; then start the harness recipe with reef serve --recipe reefine --inference.upstream-url http://127.0.0.1:11434 --inference.upstream-model gemma4:26b; create a scenario with curl -fsS -H "Content-Type: application/json" -d '{"name": "my-harness"}' http://127.0.0.1:8901/reef/scenarios. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

Authorization notice. This tool is dual-use. Only use it on software, sites and systems you own or have explicit permission to test, and follow the relevant licenses and terms of service.

What do you want to do?

3 use cases

Quick start with Reef

  1. Check you have what it needs: Python with uv installed; git-lfs system package for artifact and checkpoint features; A model endpoint, such as a local Ollama server, for harness work.
  2. Open Human-Agent-Society/reef on GitHub and read the README and license.
  3. Install the package with uv pip install reef-infra inside an activated virtual environment.
  4. Start the harness recipe with reef serve --recipe reefine --inference.upstream-url http://127.0.0.1:11434 --inference.upstream-model gemma4:26b. (inferred, check the README)
  5. Create a scenario with curl -fsS -H "Content-Type: application/json" -d '{"name": "my-harness"}' http://127.0.0.1:8901/reef/scenarios. (inferred, check the README)
  6. Install the harness with curl -fsS -H "x-reef-scenario: my-harness" 'http://127.0.0.1:8901/reef/harness/install?adapter=pi' | bash, after checking the script contents. (inferred, check the README)

These steps come from our top use case, Let your coding agent harness improve itself from requests, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Human-Agent-Society/reef

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Reef alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and ML engineers who run LLM agents and want them to improve from feedback, either by editing the agent harness with a model API or by training weights on a GPU.
  • Why it is hot7.7k stars, launched 56 days ago
  • LanguagePython
  • Sourcegithub.com/Human-Agent-Society/reef · Back to Hot repos

Requirements

  • Python with uv installed
  • git-lfs system package for artifact and checkpoint features
  • A model endpoint, such as a local Ollama server, for harness work
  • A CUDA GPU stack that meets the Evolve your model requirements, for weight training

Add this badge to your README

Maintain Reef? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/Human-Agent-Society/reef.svg)](https://dedupedai.com/use-cases/human-agent-society-reef/?utm_source=github&utm_medium=badge&utm_campaign=Human-Agent-Society-reef)

HTML 

<a href="https://dedupedai.com/use-cases/human-agent-society-reef/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=Human-Agent-Society-reef"><img src="https://dedupedai.com/badge/Human-Agent-Society/reef.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Reef

What is Reef?

Reef is open-source infrastructure that connects agent inference, feedback, learning, and versioned delivery so that models or agent harnesses keep improving. It is an open-source project on GitHub: https://github.com/Human-Agent-Society/reef.

How do I use Reef?

Install the package with uv pip install reef-infra inside an activated virtual environment; then start the harness recipe with reef serve --recipe reefine --inference.upstream-url http://127.0.0.1:11434 --inference.upstream-model gemma4:26b; create a scenario with curl -fsS -H "Content-Type: application/json" -d '{"name": "my-harness"}' http://127.0.0.1:8901/reef/scenarios. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Reef for?

Developers and ML engineers who run LLM agents and want them to improve from feedback, either by editing the agent harness with a model API or by training weights on a GPU.

What can I do with Reef?

3 use cases so far, for example: Let your coding agent harness improve itself from requests; Train model weights from your own scored responses; Serve a model behind an API that records every interaction. Each has steps and a copy-paste agent prompt.

What do I need to run Reef?

Python with uv installed; git-lfs system package for artifact and checkpoint features; A model endpoint, such as a local Ollama server, for harness work; A CUDA GPU stack that meets the Evolve your model requirements, for weight training.

What are alternatives to Reef?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Reef safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.