#1313th of 32 in Gateways and observability
experiential
OpenAI-compatible LLM gateway with per-user budgets and traffic-trained routers
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 10k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
25 on 23 Jun 20269,981 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Experiential runs a local gateway that exposes hosted, BYOK and local models through one OpenAI-compatible API, with access rules and spend budgets per user and agent. It can also build a custom router from OpenTelemetry traces and fine-tune an open model on them through Tinker. A hosted platform serves the same API, including Anthropic Messages.
Who it is for: Teams routing agent traffic across LLM providers with budget control
Ranked among open-source alternatives to OpenRouter (#7 of 10).
Strengths
- Install with pip and start with `exp`; local gateway listens on 127.0.0.1:8000
- Per-identity model access and budgets (setup wizard defaults to a $50.00 budget)
- Builds a router from OTLP traces and can fine-tune a model from them
- Hosted option accepts BYOK keys for OpenAI, Anthropic, Gemini, Azure, Bedrock, Fireworks, OpenRouter
Weaknesses
- Traffic capture is experimental, macOS only, needs Python 3.13+, and has reliability issues
- Model fine-tuning depends on the external Tinker service
- Anonymous PostHog telemetry is on by default and must be disabled manually
- No Docker or compose files detected
What it needs
- no GPU
- Needs Tinker (for model fine-tuning), Provider API keys (OpenAI, Anthropic, Gemini, Azure, Bedrock, Fireworks, OpenRouter)
- Models: OpenAI-compatible API, Anthropic Messages API (hosted), hosted models, BYOK models, local models
- port 8000
Also in Gateways and observability
See all 32| Rank | Project | Score |
|---|---|---|
| 1 | LiteLLMOpenAI-format gateway and Python SDK for calling 100+ LLM providers | 90 out of 100 |
| 2 | OmniRouteLLM gateway routing one OpenAI-compatible endpoint across 372 providers | 87 out of 100 |
| 3 | new-apiGateway that unifies LLM providers behind OpenAI, Anthropic and Gemini APIs | 83 out of 100 |
| #4 | freellmapiOpenAI-compatible router that pools free LLM provider tiers behind one endpoint | 79 out of 100 |
| #5 | LangfuseTracing, prompt management and evals for LLM apps on ClickHouse | 74 out of 100 |