gepa-adk
Evolutionary optimization for Google ADK agents.
What is this?
gepa-adk evolves AI agent instructions automatically. Give it an agent and training examples, and it finds better prompts through iterative improvement using genetic algorithms and Pareto frontier selection.
Supports single-agent evolution, multi-agent co-evolution, workflow optimization (Sequential, Loop, Parallel agents), output schema evolution, generation config tuning, and multimodal inputs including video.
Requirements
- Python 3.12 or 3.13 (
>=3.12,<3.14) - Ollama with a local model (recommended for development), or any model supported by LiteLLM
Installation
pip install gepa-adk
For database-backed ADK sessions (DatabaseSessionService, used by
examples/app_runner_integration.py), install the db extra:
pip install "gepa-adk[db]"
The extra forwards to google-adk[db]. On ADK 1.x, which has no db extra,
pip prints a harmless unknown-extra warning and installs normally.
# For local models (recommended)
export OLLAMA_API_BASE=http://localhost:11434
Quick Start
Evolve a greeting agent to produce formal, Dickens-style greetings:
from google.adk.agents import LlmAgent
from google.adk.models.lite_llm import LiteLlm
from gepa_adk import evolve, run_sync, EvolutionConfig, SimpleCriticOutput
model = LiteLlm(model="ollama_chat/llama3.2:latest")
agent = LlmAgent(
name="greeter",
model=model,
instruction="Greet the user appropriately.",
)
critic = LlmAgent(
name="critic",
model=model,
instruction="Score for formal, Dickens-style greetings. 0.0-1.0.",
output_schema=SimpleCriticOutput,
)
trainset = [
{"input": "I am His Majesty, the King."},
{"input": "I am your mother."},
{"input": "I am a close friend."},
]
config = EvolutionConfig(
max_iterations=5,
patience=1,
reflection_model="ollama_chat/llama3.2:latest",
)
result = run_sync(evolve(agent, trainset, critic=critic, config=config))
print(f"Score: {result.original_score:.2f} -> {result.final_score:.2f}")
print(result.evolved_components["instruction"])
When you have labelled examples, score with plain code instead of a critic
agent. LabelAgreementScorer scores 1.0 when the output (or one JSON field
of it) equals the row's expected label after stripping whitespace, else
0.0. Any object with score and async_score methods (the
Scorer protocol, from gepa_adk import Scorer) also works as scorer=. critic= and
scorer= are mutually exclusive:
from gepa_adk import LabelAgreementScorer
trainset = [{"input": "I am your mother.", "expected": "Dearest Mother, how fare you?"}]
# For JSON output, LabelAgreementScorer(field="label") compares that one field
# instead of the whole output.
result = run_sync(evolve(agent, trainset, scorer=LabelAgreementScorer(), config=config))
Examples
Getting started:
- basic_evolution.py — Single agent with critic
- basic_evolution_adk_reflection.py — Single agent evolution with an ADK reflection agent
- critic_agent.py — Story generation with dedicated critic
- custom_reflection_prompt.py — Custom reflection prompts
Multi-agent & workflows:
- multi_agent.py — Multi-agent co-evolution
- loop_agent_evolution.py — LoopAgent workflow evolution
- parallel_agent_evolution.py — ParallelAgent workflow evolution
- nested_workflow_evolution.py — Nested workflow evolution
- multi_agent_component_demo.py — Per-agent component evolution in a multi-agent pipeline
- sandwich_evolution.py — Nested workflow evolution that preserves the workflow structure
Advanced:
- schema_evolution_example.py — Output schema evolution
- schema_evolution_critic.py — Output schema evolution via critic feedback
- schema_reflection_demo.py — Schema reflection with validation
- config_evolution_demo.py — Generation config evolution
- video_transcription_evolution.py — Video input evolution
- app_runner_integration.py — ADK App/Runner integration
Documentation
Getting Started · Guides · API Reference
Credits
Based on GEPA (source). Built on Google ADK (source).
License
1 maintainer
Metadata
1 maintainer
Release files for gepa-adk 2.7.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| gepa_adk-2.7.0.tar.gz | 256.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| gepa_adk-2.7.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 553.7 kB
Release files / gepa_adk-2.7.0.tar.gz
| Download URL | gepa_adk-2.7.0.tar.gz |
|---|---|
| Size | 256.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
434a303d1a343fa773c608355eeb07054c4adb57c6a54b82cf0e936fe1f673fb
|
|
BLAKE2b-256 checksum How to use checksums |
644fba3808b93b5ca82918ed2aa6deafbe158b94639336c6df398e7bb3bb6932
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.21 {"installer":{"name":"uv","version":"0.12.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / gepa_adk-2.7.0-py3-none-any.whl
| Download URL | gepa_adk-2.7.0-py3-none-any.whl |
|---|---|
| Size | 297.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e47d6e2b10e0498fa90cf13efc97a990b5c32fe031e76f062f6536aad7874f35
|
|
BLAKE2b-256 checksum How to use checksums |
e2d28fe920b4f70022f2129321c1753abef666de484eae4703ab4faa64105c5a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.21 {"installer":{"name":"uv","version":"0.12.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for gepa-adk 2.7.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
