Human-Agent-Society/reef

🎯 When to use Reef

Use Reef when you want your agent to keep improving simply by learning from how you interact with your agent.

| Your goal | Learning path | What you need | |---|---|---| | Keep getting stronger model designed for you | Model weight training | A trainable model, a supported GPU stack, and feedback your recipe can use | | Get your harness to self-improve | Harness optimization | A model endpoint, representative tasks, and an evaluator; no local training GPUs | | Scientific discoveries | Test-time training | An execution environment, a correctness checker, and a measurable objective |

🧩 How Reef fits your stack

| Ability | Inference engine (vLLM, SGLang, …) | RL training framework (Slime, veRL, AReaL, …) | Reef | |---|:---:|:---:|:---:| | Serves live traffic | ✅ | ❌ | ✅ | | Trains weights | ❌ | ✅ | ✅ | | Version management | ❌ | ❌ | ✅ | | Stays live through updates | ❌ | ❌ | ✅ | | Evolves beyond weights (skills, harness) | ❌ | ❌ | ✅ |

🔄 How it works

Reef processes each learning cycle in four steps. The table also shows which modules implement each step.

| Step | What happens | Where it lives | |---|---|---| | 1 · Serve | Serve agent requests and record interactions. | service/ — agent requests and interaction records
runtime/ — inference and artifact updates | | 2 · Observe | Match feedback to recorded interactions. | storage/records.py — stored interactions and feedback
train/processors/ — feedback matching and eligibility | | 3 · Grow | Produce an update from eligible records. | recipe/ — recipe integration
train/ — batches and update jobs | | 4 · Commit | Apply the configured selection policy and publish accepted updates. | train/evaluation/ — candidate evaluation
artifact/ — version history
surface/ — artifact delivery |

📦 Installation

💡 Note

> Reef's artifact and checkpoint functionality requires the git-lfs system

package. Reef initializes Git LFS locally for its artifact repositories.

We recommend uv for managing packages, and the commands below use it.

From PyPI

uv venv && source .venv/bin/activate
uv pip install reef-infra
python3 -c "import reef; print(reef.__version__)"

From source

git lfs install
git clone https://github.com/Human-Agent-Society/reef.git
cd reef
uv venv && source .venv/bin/activate
uv pip install -e .
python3 -c "import reef; print(reef.__version__)"

Use the source checkout for development and for the training examples below.

🔧 Using Reef

Reef supports two learning surfaces: model weights and agent harnesses. The deployment's recipe determines which surface its scenarios update.

As a minimal example, start Reef as a pure inference server:

uv run reef serve --inference.model-path Qwen/Qwen2.5-1.5B-Instruct

Weight-training deployment

Start the deployment

The following example starts the SAO (arXiv:2607.07508) example deployment. Run it from a Reef checkout in an environment that satisfies the GPU requirements in Evolve your model.

uv pip install -e ".[slime]" && uv pip install --no-deps --group runtime
export MODEL_PATH="Qwen/Qwen2.5-1.5B-Instruct"
export REEF_TOKEN="reef-local"
reef serve -c recipes/sao/examples/imo_answerbench/serve.yaml \
  --inference.model-path "$MODEL_PATH" \
  --reef.port "8900"
curl -f http://127.0.0.1:8900/healthz          # ready to serve

Send an inference request and report feedback

Send inference requests through Reef and report a score for each response. The SAO recipe uses each eligible scored rollout to run a training step.

Reef's inference endpoint is OpenAI- and Anthropic-compatible: /v1/chat/completions and /v1/messages take the provider's own request body. A request includes the x-reef-scenario header; a new name creates a scenario using the deployment's configured recipe. Requests do not select recipes.

The response body uses the provider's OpenAI-compatible format. Reef adds the x-reef-agent-record-id response header. Its value is the receipt that a later report uses to identify this interaction. A report can contain a numeric score, textual or structured feedback, and the receipts it evaluates. This example reports both a score and a short explanation.

import os
import httpx
reef = httpx.Client(
    base_url="http://127.0.0.1:8900",
    headers={"Authorization": f"Bearer {os.environ['REEF_TOKEN']}", "x-reef-scenario": "hello-reef"},
    timeout=300,
)
Send a provider-compatible inference request
response = reef.post(
    "/v1/chat/completions",
    json={
        "model": os.environ["MODEL_PATH"],
        "messages": [{"role": "user", "content": "Return exactly: reef is ready"}],
    },
)
response.raise_for_status()
receipt = response.headers["x-reef-agent-record-id"]
answer = response.json()["choices"][0]["message"]["content"]
Sending report about the inference
matched = answer.strip() == "reef is ready"
reef.post(
    "/reef/report",
    json={"score": float(matched), "feedback": "matched" if matched else "wrong answer", "references": [receipt]},
).raise_for_status()

feedback carries the richer signal, plain text or a structured object, for recipes that read more than a scalar. The endpoint will validate the report schema (reef/core/reports/).

Watch it learn and grow

Once the recipe has enough feedback, it runs a training step and synchronizes the updated weights to the serving runtime. Later inference requests use the current version without restarting Reef.

Harness-evolving deployment

Refine a coding harness from plain-language asks, using a model API instead of GPUs.

Reefine is the built-in harness-refinement recipe and includes a deployment configuration; specify the provider URL and model. From your Reef checkout and activated Python environment:

reef serve --recipe reefine \
  --inference.upstream-url http://127.0.0.1:11434 \
  --inference.upstream-model gemma4:26b

The example connects to a local Ollama server. For another provider, change --inference.upstream-url and --inference.upstream-model, and set REEF_UPSTREAM_API_KEY if authentication is required. With this configuration, Reef listens on 127.0.0.1:8901 with token reef-local and keeps its state under .reef/reefine/ (--recipe harness-evolve, the former name, starts the same configuration). To change anything else, copy the deployment configuration and pass your copy with -c.

In another terminal with the same Python environment activated (the install bakes that terminal's python3 into reef-pi), create a scenario, install the harness, and ask for a change:

export REEF_TOKEN=reef-local
curl -fsS -H "Authorization: Bearer $REEF_TOKEN" -H "Content-Type: application/json" \
  -d '{"name": "my-harness"}' http://127.0.0.1:8901/reef/scenarios
curl -fsS -H "Authorization: Bearer $REEF_TOKEN" -H "x-reef-scenario: my-harness" \
  'http://127.0.0.1:8901/reef/harness/install?adapter=pi' | bash
reef-pi harness "when I ask you to fix a bug, reproduce it with a failing test first"

Inside a reef-pi session, /reef-harness files the same ask. The served model writes the change as a skill, a rules entry, an agent command, or a pi extension, and the next session's update notice offers the install; review the versions with /reef-versions, and promote an extension with /reef-versions promote before it is offered. To change the model, restart reef serve with another --inference.upstream-model and rerun the install command: installation writes the model ID into the local harness configuration. See the Reefine tutorial for scripted bug-fix and research demos and the Reefine guide for configuration.

📚 Recipes and examples

Pick a recipe by the task type of your workload and by what it should evolve, model weights or the agent harness. Weight recipes need the GPU training stack, while harness recipes need only a model endpoint. Each recipe below links to its guide and each measured benchmark links to its results page, and the recipe catalog adds the code and example for every recipe. Reefine ships with reef-infra, and the other implementations live in this repository's recipes/ cookbook, selected by dotted class reference and not shipped in the Reef wheel.

| Task type | Task shape | Evolves the model | Evolves the harness | Standard benchmarks | |---|---|---|---|---| | Scientific discovery | Repeated attempts at one hard problem with a measurable objective | TTT-Discover, Guidance-TTT | None yet | Measured: TriMul, circle packing, Erdős minimum overlap. | | Continual learning on a task stream | A stream of independent tasks that a verifier scores one by one | SAO | Meta-Harness, GEPA | Measured: AIME 2025, IMOAnswerBench, CEO-Bench, Terminal-Bench. | | Learning from usage | Real interaction where no one reports a score or feedback arrives late | OpenClaw-RL | SkillClaw, Reefine | Measured: simulated student with GSM8K task stream, WildClawBench. |

recipes/basic/ is the record-only starting stack and stays outside the catalog. For a small walkthrough of feedback, candidate edits, and publication, start with the coding harness tutorial. Each result page documents its task, evaluation setup, measurements, and limitations.

📐 Architecture

📖 Learn more

The documentation is organized in the following order:

• Quickstart: install Reef, connect a client, and inspect the version history
• HTTP API: use the HTTP API and report feedback
• Write a recipe: configure how Reef processes data and produces updates
• Evolve your harness: evolve a harness instead of model weights
• Evolve your model: configure and operate a training deployment
• Recipes: the catalog of cookbook

recipes by task type, with code, docs, example, and results for each

• The core loop: The core loop of Reef
• Glossary: Explanation of the terminologies used

🤝 Community & Contributing

Working on continual self-improving agent?

• Join Discord to share your recipes, ask implementation questions, and discuss new features.
• Join the WeChat group: the group is full, so add the assistant and it will invite you.
• Join the GitHub Discussions to ask questions, share ideas, and connect with the community.
• Start contributing with the contribution guide.
• Propose designs through an RFC issue.
• Report suspected vulnerabilities privately by following the security policy.

If Reef looks useful to you, please give it a ⭐ — it helps the community to discover and contribute to the project.

👥 The Team

Reef brings together people exploring how agents can learn from experience and improve over time. The people below help turn that idea into working infrastructure.

This list is non-exhaustive, with team members listed alphabetically by last name:

Wenhao Chai, Shuangrui Ding, Hao He, Haoze He, Chonghe Jiang, Nan Jiang, Xuan Jiang, Xiaochen Li, Paul Liang, Bo Liu, Boyuan Long, Qiuyang Mang, Zhenting Qi, Ao Qu, Mingruo Qu, Zhaokai Wang, Xuezhi Yan, Hanfei Yu, Haofei Yu, Simon Yu, Han Zheng, Kaichen Zhou, Zijian Zhou, Jiacheng Zhu, Dingyi Zhuang.

⭐ Star History

🙏 Acknowledgements

We are particularly grateful to these projects which power important parts of Reef:

• SGLang — high-performance inference
• slime — model weight training
• cordis — harness evolution