Experiential

gateway latency

Experiential is an open source gateway and router for agent workflows:

  1. Use hosted, BYOK, and local models through one OpenAI-compatible API.
  2. Control which users and agents can use which models, for which use cases, and how much they can spend.
  3. Turn production traffic into a custom router or model optimized for quality, speed, and cost.

Experiential workspace usage dashboard showing model traffic, identities, and spend

🌐 Platform | 📚 Docs | Discord

Getting Started

Start a local OpenAI-compatible gateway. On first run, the setup wizard uses the shared provider, model, and reasoning-effort selectors, persists every selected provider connection, then shows defaults for the public alias, identity, and $50.00 command budget before printing a one-time key:

pip install experiential
exp

Choose a public alias such as opus-5, capture the issued key, and send a request:

export EXP_GATEWAY_KEY=...
curl http://127.0.0.1:8000/v1/chat/completions \
  -H "Authorization: Bearer $EXP_GATEWAY_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"opus-5","messages":[{"role":"user","content":"Help me"}]}'

Setup / get started with the hosted gateway

Prefer a managed gateway to running one locally? The hosted platform at platform.experientiallabs.ai serves the same OpenAI-compatible (and Anthropic Messages) API at https://api.experientiallabs.ai/v1. See SETUP.md for copy-paste prompts you hand to your coding agent (Claude Code, Cursor, Codex, and similar); the agent runs the setup for you. It collects four prompts:

  • Upload your LLM traces as telemetry: create an account instantly from your email, then pull or upload your existing LLM traces onto the platform as telemetry.
  • Connect your inference provider keys (BYOK): create an account, then connect your own OpenAI, Anthropic, Gemini, Azure, Bedrock, Fireworks, or OpenRouter keys for free pass-through.
  • Start calling models on the gateway: make your first /v1 call with the OpenAI and Anthropic SDKs using an xpl_ key, and optionally repoint your existing coding agents.
  • Full onboarding: create an account instantly from your email, connect your keys, import your spend, then repoint every coding agent (Claude Code, Cursor, Codex, Aider, and similar) or Conductor at the gateway.

Using the API

Start the local gateway with exp (or exp run); the compiled native data plane serves every route on loopback. From Python, load a fitted project router as an official OpenAI client backed by its own private gateway:

import exp

with exp.load_router("my-project") as client:
    response = client.chat.completions.create(
        model="my-project",
        messages=[{"role": "user", "content": "hello"}],
    )

Optimize from Traffic

First, collect OpenTelemetry traces from your current agent. If you just want to try it out, grab the public terminal-tasks OTLP dataset:

curl -L -o traces.otel.jsonl \
  https://huggingface.co/datasets/experiential-labs/wmo-terminal-tasks-traces/resolve/540883e451dc13d34fb50fdd36b143cb0f1fb0db/traces.otel.jsonl

Then build a project. The build command walks you through providers, models, and budget, and asks for your trace file:

# Build simulation from your agent traces and optimize a router against it
exp build support-agent

After collecting traces from your router, fine-tune an open source model you own using Tinker.

exp optimize model support-agent

Telemetry

Anonymous aggregate PostHog product telemetry is enabled by default. It never includes prompts, traces, actions, observations, paths, model names, credentials, or raw customer content.

exp config telemetry status
exp config telemetry disable
exp config telemetry enable

The preference is stored locally in .exp/settings.toml.

Development

uv sync --extra dev
uv run ruff format --check .
uv run ruff check .
uv run ty check
uv run pytest -q

Repository and documentation conventions live in AGENTS.md.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.7.41)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for kfallah15 from gravatar.com kfallah15

License

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR U...

Requires

Python >=3.12

Provides Extra

dev sft

Report project as malware

Download files

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

Source Distribution

experiential-0.7.11.tar.gz (2.4 MB view details)

Uploaded Source

Built Distribution

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

experiential-0.7.11-py3-none-any.whl (1.5 MB view details)

Uploaded Python 3

File details

Details for the file experiential-0.7.11.tar.gz.

File metadata

  • Download URL: experiential-0.7.11.tar.gz
  • Upload date:
  • Size: 2.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","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}

File hashes

Hashes for experiential-0.7.11.tar.gz
Algorithm Hash digest
SHA256 f802b88527ada93f79826478102dde410475a5a30e811d3f1ee97034db695fb1
MD5 bf6a51449b8d30ed35713e37b93ac03a
BLAKE2b-256 57c55b2211a84e17f8e4e678ec56026ca8c11e12b83974ab669985943193c050

See more details on using hashes here.

File details

Details for the file experiential-0.7.11-py3-none-any.whl.

File metadata

  • Download URL: experiential-0.7.11-py3-none-any.whl
  • Upload date:
  • Size: 1.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","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}

File hashes

Hashes for experiential-0.7.11-py3-none-any.whl
Algorithm Hash digest
SHA256 0c27cb6270cf3ebd6e2b975006cf453f635c223ab0c8ed13544b2289dfc3e0e4
MD5 b3c2f5f3ef41933b5009f8f1da287ddc
BLAKE2b-256 0a1d93ad7e068ce8b4add37fb23475c98d109a424f94e9a83bd327c4d264ecc4

See more details on using hashes here.

Release history Release notifications | RSS feed

0.7.41

2 files

0.7.40

2 files

0.7.39

2 files

0.7.38

2 files

0.7.37

2 files

0.7.36

2 files

0.7.35

2 files

0.7.34

2 files

0.7.33

2 files

0.7.32

2 files

0.7.31

2 files

0.7.30

2 files

0.7.29

2 files

0.7.28

2 files

0.7.25

2 files

0.7.24

2 files

0.7.23

2 files

0.7.22

2 files

0.7.21

2 files

0.7.20

2 files

0.7.19

2 files

0.7.18

2 files

0.7.17

2 files

0.7.16

2 files

0.7.15

2 files

0.7.14

2 files

0.7.13

2 files

0.7.12

2 files

This release

0.7.11 This release

2 files

0.7.10

2 files

0.7.9

2 files

0.7.8

2 files

0.7.7

2 files

0.7.6

2 files

0.7.5

2 files

0.7.4

2 files

0.7.3

2 files

0.7.2

2 files

0.7.1

2 files

0.7.0

2 files

0.6.1

2 files

0.6.0

2 files

0.5.7

2 files

0.5.6

2 files

0.5.5

2 files

0.5.4

2 files

0.5.3

2 files

0.5.2

2 files

0.5.1

2 files

0.5.0

2 files

0.4.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page