Serverless Posttraining for Agents - Core AI functionality and tracing
Verified details
These details have been verified by PyPIProject links
GitHub Statistics
Maintainers
Project description
Synth
Build systems for OOMs more complexity.
Continual and offline optimization for prompts, context, skills, and long-horizon memory.
Use the SDK in Python (uv add synth-ai) and Rust (beta) (cargo add synth-ai), or call Synth endpoints from any language.
Synth Style
Synth is built for frontier builders first. We:
- push interface complexity inward (strong server contracts, simpler app surfaces)
- design online/offline parity with pause/resume as first-class controls
- meet production code where it is (no forced lock-in or rewrites)
- build general algorithmic foundations, then layer targeted affordances
For engineering principles and coding standards, see specs/README.md.
Average accuracy on LangProBe prompt optimization benchmarks.
Demo Walkthroughs
- GEPA Banking77 Prompt Optimization
- GEPA Crafter VLM Verifier Optimization
- GraphGen Image Style Matching
Benchmark and demo runner source files live in the Benchmarking repo (../Benchmarking in a sibling checkout).
Product Focus
- Continual Learning Sessions (MIPRO + GEPA): run online sessions that update prompts from reward feedback during live traffic, with first-class
pause/resume/cancelcontrols. - Discrete GEPA Optimization (Prompt + Context): run offline GEPA jobs for controlled batch optimization, compare artifacts, and promote the best candidates.
- Voyager for Skills + Long-Term Memory: optimize skill/context surfaces and use durable memory with retrieval and summarization for long-horizon agent systems.
- One Canonical Runtime Surface: use shared
systems,offline, andonlineprimitives across SDK and HTTP APIs. - Agent Infrastructure Built In: run with pools, containers, and tunnels for local or managed rollouts without forcing app rewrites.
- Graph + Verifier Workflows: train GraphGen pipelines and rubric-based verifiers for domain-specific evaluation loops.
Getting Started
Python SDK
uv add synth-ai
# or
pip install synth-ai==0.9.1
Rust SDK (beta)
cargo add synth-ai
API (any language)
Use your SYNTH_API_KEY and call Synth HTTP endpoints directly.
Docs: docs.usesynth.ai
Project details
Verified details
These details have been verified by PyPIProject links
GitHub Statistics
Maintainers
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file synth_ai-0.9.1.tar.gz.
File metadata
- Download URL: synth_ai-0.9.1.tar.gz
- Upload date:
- Size: 756.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cc8c00c0d151c0cb32af17637c875db06b07cd5fa033e94a573fd4c0fe41ed7e
|
|
| MD5 |
d8c97cf81a00d3e742654f548d3bc750
|
|
| BLAKE2b-256 |
f8d162c4890997beed5130cc27d102b8bd5330d6436e6cb1621538e90be5aaab
|
Provenance
The following attestation bundles were made for synth_ai-0.9.1.tar.gz:
Publisher:
publish-dev.yml on synth-laboratories/synth-ai
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
synth_ai-0.9.1.tar.gz -
Subject digest:
cc8c00c0d151c0cb32af17637c875db06b07cd5fa033e94a573fd4c0fe41ed7e - Sigstore transparency entry: 991438694
- Sigstore integration time:
-
Permalink:
synth-laboratories/synth-ai@c3d415e6fc7409757b85a5c1a5c83ee8d18b026b -
Branch / Tag:
refs/heads/main - Owner: https://github.com/synth-laboratories
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
self-hosted -
Publication workflow:
publish-dev.yml@c3d415e6fc7409757b85a5c1a5c83ee8d18b026b -
Trigger Event:
push
-
Statement type:
File details
Details for the file synth_ai-0.9.1-cp312-cp312-macosx_11_0_arm64.whl.
File metadata
- Download URL: synth_ai-0.9.1-cp312-cp312-macosx_11_0_arm64.whl
- Upload date:
- Size: 10.6 MB
- Tags: CPython 3.12, macOS 11.0+ ARM64
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f6946a1ca3f8f4da7c59213d8c8721b15d34a00fe05ce6d9a54f8842b6bb2f9e
|
|
| MD5 |
cc0a9d48fe6f8825c1f6ee753e045fe2
|
|
| BLAKE2b-256 |
2184c6b095fff65e38e2e7ecdf236074969e277ef0b4ad1291691f1879eb123c
|
Provenance
The following attestation bundles were made for synth_ai-0.9.1-cp312-cp312-macosx_11_0_arm64.whl:
Publisher:
publish-dev.yml on synth-laboratories/synth-ai
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
synth_ai-0.9.1-cp312-cp312-macosx_11_0_arm64.whl -
Subject digest:
f6946a1ca3f8f4da7c59213d8c8721b15d34a00fe05ce6d9a54f8842b6bb2f9e - Sigstore transparency entry: 991438698
- Sigstore integration time:
-
Permalink:
synth-laboratories/synth-ai@c3d415e6fc7409757b85a5c1a5c83ee8d18b026b -
Branch / Tag:
refs/heads/main - Owner: https://github.com/synth-laboratories
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
self-hosted -
Publication workflow:
publish-dev.yml@c3d415e6fc7409757b85a5c1a5c83ee8d18b026b -
Trigger Event:
push
-
Statement type:
File details
Details for the file synth_ai-0.9.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.
File metadata
- Download URL: synth_ai-0.9.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Upload date:
- Size: 11.6 MB
- Tags: CPython 3.8, manylinux: glibc 2.17+ x86-64
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
151e905d8958ae96c94e0bdf969d67c1513cde72caa679c3c6aca9cf86c48d18
|
|
| MD5 |
0d87c3d599f7c1e6dca6656e4a60b56a
|
|
| BLAKE2b-256 |
0564d8189be256b784ee8450194e6975b7fbe12f24279ab25c5213d738873fe9
|
Provenance
The following attestation bundles were made for synth_ai-0.9.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:
Publisher:
publish-dev.yml on synth-laboratories/synth-ai
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
synth_ai-0.9.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl -
Subject digest:
151e905d8958ae96c94e0bdf969d67c1513cde72caa679c3c6aca9cf86c48d18 - Sigstore transparency entry: 991438695
- Sigstore integration time:
-
Permalink:
synth-laboratories/synth-ai@c3d415e6fc7409757b85a5c1a5c83ee8d18b026b -
Branch / Tag:
refs/heads/main - Owner: https://github.com/synth-laboratories
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
self-hosted -
Publication workflow:
publish-dev.yml@c3d415e6fc7409757b85a5c1a5c83ee8d18b026b -
Trigger Event:
push
-
Statement type:
