Axond

Axond is a stateless, single-binary, self-hosted AI gateway. Point OpenAI or Anthropic clients at Axond to centralize provider credentials, stable model aliases, failover, usage metering, budgets, rate limits, and telemetry.

Status: beta. The supported routes and stability promises are explicit in the compatibility contract. Patch releases are upgrade-safe within 0.x; documented breaking configuration changes require a minor release.

What it provides

Area	Capabilities
Provider wires	OpenAI chat completions, Responses, and embeddings; native Anthropic Messages; buffered and streamed requests.
Routing	Stable aliases, ordered target failover, per-target circuits, and weighted or round-robin credential pools.
Tenancy	Namespace-isolated provider credentials, explicit platform fallback, and bring-your-own-key deployments.
Inbound identity	Required static gateway keys, scoped minted tokens, optional in-gateway minting, issuance epochs, and precise JTI revocation.
Controls	Per-subject budgets, exact namespace-wide Redis/Postgres caps, and local or Redis-backed in-flight rate limits.
Operations	Atomic config reload, replica-local credential status, JSON logs, OTLP traces/metrics/logs, and durable Postgres usage.
Distribution	crates.io packages, signed release binaries, and a public signed and attested OCI image.

Axond is passthrough-first: it rewrites only model, then forwards the caller's native wire. It does not translate OpenAI payloads into Anthropic payloads or vice versa. A mismatched alias is rejected before dispatch with a typed unsupported_wire error.

Run it in two minutes

The default Compose path pulls the public release image and runs without Redis or Postgres. Placeholder provider credentials are sufficient for health, readiness, catalogue, authentication, and typed-error checks.

git clone https://github.com/Litvue/axond.git
cd axond
cp ops/compose/env.example .env
docker compose up -d

curl http://localhost:8080/healthz
curl -H 'Authorization: Bearer quickstart-platform-key' \
  http://localhost:8080/v1/models

Expected probes:

ok
{"data":[{"id":"gpt-4o",...}],"object":"list"}

To make a real provider request, replace the corresponding placeholder in .env, restart the container, and call the gateway:

curl http://localhost:8080/v1/chat/completions \
  -H 'Authorization: Bearer quickstart-platform-key' \
  -H 'content-type: application/json' \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Say hello in one word."}]}'

With placeholders, the request deliberately returns a typed provider or transport error; it still proves the complete authenticated gateway path. Keep .env until after teardown because Compose validates its required values before every command:

docker compose down -v

See Getting started for source builds, the stateful Compose profile, and SDK examples.

Install

The recommended path installs the checksum-verified prebuilt binary; it does not download the repository or invoke the Rust compiler:

# Linux x86-64 or macOS Apple Silicon
curl --proto '=https' --tlsv1.2 -LsSf \
  https://raw.githubusercontent.com/Litvue/axond/main/install.sh | sh

PowerShell on Windows x86-64:

irm https://raw.githubusercontent.com/Litvue/axond/main/install.ps1 | iex

The installers select the latest release, verify its SHA-256 sidecar, and put axond under the current user's local application directory. Download and inspect either script first if your policy forbids piped installers.

Other distribution paths:

# Cargo installs from source and compiles locally by design.
cargo install axond --locked

# Pull the current release image. There is intentionally no `latest` tag.
AXOND_VERSION=0.3.17 # x-release-please-version
docker pull "ghcr.io/litvue/axond:${AXOND_VERSION}"

Signed prebuilt archives are published for Linux (x86_64 GNU and static musl), macOS (aarch64), and Windows (x86_64). The OCI image is currently linux/amd64. Production deployments should verify the attestations and pin an image digest. See Installation and verification.

Point a client at Axond

Use http://localhost:8080/v1 as the OpenAI base URL and an Axond gateway key as the API key:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8080/v1",
    api_key="quickstart-platform-key",
)
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "hello"}],
)

Anthropic clients use the same host and their native x-api-key behavior. Detailed Python, TypeScript, streaming, Responses, embeddings, and Messages examples are in the client guides.

Choose a deployment

Environment	Start here
Local evaluation	Getting started
Docker Compose	Compose guide
Docker or Podman	Container guide
Linux VM / bare metal	systemd guide
Kubernetes	Kubernetes guide
ECS, Cloud Run, Container Apps, Nomad	Managed-container contract
Redis/Postgres-backed fleet	Stateful backends

Axond does not terminate inbound TLS. Put it behind a trusted reverse proxy or load balancer, preserve streaming responses, and disable response buffering. Use the production checklist before exposing it outside a development network.

State tiers

State tiers describe Axond's own dependencies, not provider egress.

Tier	What it adds	Operational consequence
0 — config only	Namespaces, aliases, provider keys, failover, credential pools, static/minted identity, stdout usage, hot reload, and optional per-replica controls.	No datastore. Health, circuits, and in-memory limits are replica-local.
1 — Redis	Exact shared budgets, namespace caps, cross-replica in-flight limiting, and precise token revocation.	Redis participates in admission. The default outage policy fails closed.
2 — Postgres	Durable usage rows, shared budgets/namespace caps, and precise revocation.	Requires schema ownership, migrations, backups, and boot-time connectivity.

Configuration-owned namespaces, providers, aliases, prices, and credentials are never overridden by a datastore. See the stateful deployment guide and ADR 0017.

Tiers describe dependencies; operating modes describe ownership. Stateful bootstrap configuration is shipped, but the durable control plane is not. Stateless remains the default, where TOML is the authority. The accepted design for an opt-in stateful mode — durable resources in Postgres, /admin/v1 administration, and inference still served from one immutable in-memory snapshot — is ADR 0027. The stateful bootstrap currently validates its references and then refuses to start until the control-plane implementation is available.

Security model

Every route except /healthz and /readyz requires an Axond credential.
Provider keys, inbound keys, and DSNs are referenced by environment-variable name or an explicitly supported mounted file; secret values do not belong in TOML.
At least one static gateway key is mandatory as a breakglass path even when minted-token verification is enabled.
Configuration and dependencies are validated before the listener binds.
Release binaries and the OCI image carry provenance and SBOM attestations; the image is signed keylessly and verified in the release workflow.

Read the deployment security model, minted-token guide, and latest security review.

To report a vulnerability, follow SECURITY.md — privately, not in an issue. It also states which releases receive fixes.

Documentation

The documentation index is organized by task:

Development

The Rust toolchain is pinned in rust-toolchain.toml. Run the core code, package, and supply-chain gate with:

just check

Useful focused checks:

just quickstart-smoke  # build current source and exercise the Compose path
just compat            # OpenAI and Anthropic SDKs against a real local axond
just tier0              # prove config-only boot in a network-denied namespace
just soak               # long streaming soak, also available on demand in CI

See CONTRIBUTING.md for contribution and compatibility-lock guidance.

Releases

Release-please maintains the changelog and workspace version. A release builds four binary targets, publishes the linux/amd64 OCI image, signs and attests artifacts, and publishes gateway-core, gateway-transport, and axond to crates.io in dependency order. Maintainer procedures are in the release runbook.

License

Dual-licensed under either Apache-2.0 or MIT at your option.

gateway-core 0.3.17