Skip to content

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

NameLast commit date
..
__init__.py
actors.py
agentic_probe.py
anthropic_refusal.py
anthropic_sse.py
anthropic_thinking.py
asgi.py
async_server.py
aws_control_plane.py
bedrock_discovery.py
bedrock_realtime_peer.py
bedrock_runtime_peer.py
browser_state.py
budget.py
claude_code.py
client.py
codex_vendor.py
daily_activity.py
daily_spend_rows.py
database_relay.py
database.py
deepseek_tokens.py
device_login.py
forward_proxy.py
generation.py
hook_count_probe.py
hook_counts.py
idle_gateway.py
interception_vendor.py
mail.py
manifest.py
mcp_e2e_upstream_server.py
mcp_grants.py
mcp_stdio_peer.py
mcp.py
oauth_server.py
openai_wire.py
ordering.py
otlp_sink.py
pdf_document.py
ports.py
prisma_clients.py
process.py
prometheus_series.py
prompt_cache_breakpoint.py
provider.py
proxy.py
redaction_probe.py
redis_breaker_worker.py
redis_process.py
responses_stream.py
responses_vendor.py
responses_ws_peer.py
routing.py
runtime.py
safeguards_rig.py
sagemaker_embedding.py
scim.py
sdk_models.py
sharding.py
sigv4.py
timing.py
tls.py
tool_rows.py
tool_search.py
upstream.py
vertex.py
wire.py
worker_readiness.py
workers.py