Skip to main content

Eval Protocol

PyPI - Version Ask DeepWiki

Eval Protocol (EP) is an open solution for doing reinforcement learning fine-tuning on existing agents — across any language, container, or framework.

Eval Protocol overview

Most teams already have complex agents running in production — often across remote services with heavy dependencies, Docker containers, or TypeScript backends deployed on Vercel. When they try to train or fine-tune these agents with reinforcement learning, connecting them to a trainer quickly becomes painful.

Eval Protocol makes this possible in two ways:

  1. Expose your agent through a simple API Wrap your existing agent (Python, TypeScript, Docker, etc.) in a simple HTTP service using EP’s rollout interface. EP handles the rollout orchestration, metadata passing, and trace storage automatically.
  2. Connect with any trainer Once your agent speaks the EP standard, it can be fine-tuned or evaluated with any supported trainer — Fireworks RFT, TRL, Unsloth, or your own — with no environment rewrites.

The result: RL that works out-of-the-box for existing production agents.

Who This Is For

  • Applied AI teams adding RL to existing production agents.
  • Research engineers experimenting with fine-tuning complex, multi-turn or tool-using agents.
  • MLOps teams building reproducible, language-agnostic rollout pipelines.

Quickstart

Resources

License

MIT

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

eval_protocol-0.3.32.tar.gz (2.2 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

eval_protocol-0.3.32-py3-none-any.whl (2.2 MB view details)

Uploaded Python 3

File details

Details for the file eval_protocol-0.3.32.tar.gz.

File metadata

  • Download URL: eval_protocol-0.3.32.tar.gz
  • Upload date:
  • Size: 2.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for eval_protocol-0.3.32.tar.gz
Algorithm Hash digest
SHA256 637d2458e3998536c0d6bd9894e1ae85aa337acff701f1f1110edd292da76844
MD5 b7150e3e14c3ab1aed094fbf824c13a1
BLAKE2b-256 b03d7451d744c14c2752c654e82c28409f5e52c259e4d93678b2e9c8c3463b6b

See more details on using hashes here.

Provenance

The following attestation bundles were made for eval_protocol-0.3.32.tar.gz:

Publisher: release.yml on eval-protocol/python-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file eval_protocol-0.3.32-py3-none-any.whl.

File metadata

  • Download URL: eval_protocol-0.3.32-py3-none-any.whl
  • Upload date:
  • Size: 2.2 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for eval_protocol-0.3.32-py3-none-any.whl
Algorithm Hash digest
SHA256 193cb4a29682eefb517b708d149b4d79d400a81e420cf26888301c9ad3fa0353
MD5 ea26acb1d0a3655fd6baf5fad121847c
BLAKE2b-256 f8c965e256f616c4c28825a2acb3d22991004f94ae832cffd525c6028dc09446

See more details on using hashes here.

Provenance

The following attestation bundles were made for eval_protocol-0.3.32-py3-none-any.whl:

Publisher: release.yml on eval-protocol/python-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page