diff --git a/README.md b/README.md
new file mode 100644
index 0000000..9cf69eb
--- /dev/null
+++ b/README.md
@@ -0,0 +1,106 @@
+# crossbar
+
+crossbar is an affinity router in front of several `llama-server` routers. A client's identity is
+the first path segment of its base URL; v0 routes each request to the first healthy host on that
+route's list and streams the answer back unbuffered.
+
+## Build
+
+Build everything with `make build`; the binaries land in `bin/`. Check the work with `make gate`,
+which runs the formatter, vet, tests and line-length check with no network. When the code is ready,
+run `make smoke`, which starts two fake upstreams and exercises routing, failover, recovery and
+streaming over real HTTP.
+
+## Configure
+
+crossbar reads one TOML file. This is `example.toml`:
+
+```toml
+# crossbar example configuration. Replace <tailnet> and the addresses with your own.
+listen        = "127.0.0.1:17777"   # never 0.0.0.0 — bind the tailnet address in production
+poll_interval = "1s"                # 60s in production; 1s makes the smoke run quick
+queue_max     = 8
+
+[hosts.alpha]
+base_url = "http://127.0.0.1:18081"    # e.g. http://straylight.<tailnet>:11434
+weight   = 1.0
+models   = { "ornith-1.5-35b-a3b" = { parallel = 4 }, "small-9b" = { parallel = 6 } }
+
+[hosts.beta]
+base_url = "http://127.0.0.1:18082"    # e.g. http://titan.<tailnet>:8081
+weight   = 2.0
+models   = { "ornith-1.5-35b-a3b" = { parallel = 4 } }
+
+# v0: a route is a preference list; the first healthy host that has the model wins.
+[routes.opencode-a]
+hosts         = ["alpha", "beta"]
+default_model = "ornith-1.5-35b-a3b"
+
+[routes.hermes-x]
+hosts = ["beta", "alpha"]
+```
+
+| Key | Meaning |
+| --- | --- |
+| `listen` | Where crossbar binds. A tailnet address, never `0.0.0.0`. |
+| `poll_interval` | How often each host is health-checked. 60s in production; 1s makes the smoke run quick. |
+| `queue_max` | Reserved for v1 queueing; no effect in v0. |
+| `hosts.<name>.base_url` | The llama-server base URL this host serves. |
+| `hosts.<name>.weight` | Relative share of new routes this host receives. |
+| `hosts.<name>.models` | The models this host serves, with per-model parallel tuning. |
+| `routes.<name>.hosts` | Preference order: the first healthy host that serves the model wins. |
+| `routes.<name>.default_model` | Model used when a request omits one; must be served by a host in the route. |
+
+## Run
+
+Copy the binary, the config and the unit into place, reload systemd, and start it:
+
+```sh
+install -m 0755 bin/crossbar /usr/local/bin/crossbar
+install -d -m 0755 /etc/crossbar
+install -m 0644 crossbar.toml /etc/crossbar/crossbar.toml
+install -m 0644 deploy/crossbar.service /etc/systemd/system/crossbar.service
+systemctl daemon-reload
+systemctl enable --now crossbar
+```
+
+## Point clients at it
+
+OpenCode, one provider for every project. Each instance is launched as
+`CROSSBAR_ROUTE="$(basename "$PWD")-$$" opencode`:
+
+```jsonc
+"provider": { "crossbar": { "npm": "@ai-sdk/openai-compatible",
+  "options": { "baseURL": "http://crossbar.<tailnet>:7777/{env:CROSSBAR_ROUTE}/v1" },
+  "models": { "ornith-1.5-35b-a3b": {} } } }
+```
+
+Hermes, in `config.yaml`:
+
+```yaml
+custom_providers:
+  - name: crossbar
+    base_url: http://crossbar.<tailnet>:7777/hermes-<agent>/v1
+    models: { ornith-1.5-35b-a3b: {} }
+```
+
+The route name in the URL must exist in `[routes]`; unknown routes are 404.
+
+## Inspect
+
+`GET /_crossbar/hosts` reports every host's health and loaded models:
+
+```json
+{"alpha":{"healthy":true,"loaded":["ornith-1.5-35b-a3b","small-9b"],"last_ok":"2026-09-25T09:34:18Z","last_err":""},"beta":{"healthy":true,"loaded":["ornith-1.5-35b-a3b"],"last_ok":"2026-09-25T09:34:18Z","last_err":""}}
+```
+
+`GET /_crossbar/routes` reports each route's preference order and default model:
+
+```json
+{"hermes-x":{"hosts":["beta","alpha"],"default_model":""},"opencode-a":{"hosts":["alpha","beta"],"default_model":"ornith-1.5-35b-a3b"}}
+```
+
+## What v0 does not do
+
+Leases and stickiness, SQLite, `/slots`, queueing and wake-on-LAN are out of scope for v0; see
+`PLAN.md`.
diff --git a/deploy/crossbar.service b/deploy/crossbar.service
new file mode 100644
index 0000000..b9d6e12
--- /dev/null
+++ b/deploy/crossbar.service
@@ -0,0 +1,18 @@
+[Unit]
+Description=crossbar affinity router for llama-server
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+ExecStart=/usr/local/bin/crossbar -config /etc/crossbar/crossbar.toml
+Restart=on-failure
+RestartSec=2s
+DynamicUser=yes
+StateDirectory=crossbar
+NoNewPrivileges=yes
+ProtectSystem=strict
+ProtectHome=yes
+PrivateTmp=yes
+
+[Install]
+WantedBy=multi-user.target
diff --git a/docs/implementer-log.md b/docs/implementer-log.md
index a38f06a..08afd7b 100644
--- a/docs/implementer-log.md
+++ b/docs/implementer-log.md
@@ -9,5 +9,6 @@ owner fills in the Model column. The reviewer adds findings under "Reviews" once
 | v0/02-health | 2026-09-25 | done | 1 | pass | none | First gate run passed. `MarkDown` initially forgot to write the entry back; caught by `TestMarkDown`. | ? |
 | v0/03-proxy | 2026-09-25 | done | 1 | pass | none | `SplitRoute` must reject an empty first segment (`/`, `//x`) as `ok=false`; the model peek restores the body and leaves non-JSON/empty as `""`. | ? |
 | v0/04-admin-main | 2026-09-25 | done | 1 | pass | none | `timeout --signal=TERM 3` exits 124 on a timed-out child on this GNU system, so the task's `exit=0` is not observable through it; sent SIGTERM directly and confirmed crossbar's own exit code is 0 with both log lines. | ? |
+| v0/05-smoke-readme-deploy | 2026-09-25 | done | 1 | pass | none | `README.md` `## Run` uses `install -m` instead of `cp` and adds `systemctl daemon-reload` before `enable --now`, which is required for systemd to see the new unit; the task said only "copy … then enable --now". | ? |
 
 ## Reviews
diff --git a/tools/smoke.sh b/tools/smoke.sh
new file mode 100755
index 0000000..4b21792
--- /dev/null
+++ b/tools/smoke.sh
@@ -0,0 +1,45 @@
+#!/bin/sh
+# Smoke run: two fake upstreams, one crossbar, real HTTP. Prints "smoke: ok" or fails.
+# Needs: bin/crossbar and bin/fakeupstream (make build), curl.
+set -eu
+cd "$(dirname "$0")/.."
+tmp=$(mktemp -d); trap 'kill $pids 2>/dev/null; rm -rf "$tmp"' EXIT INT TERM
+pids=""
+bin/fakeupstream -listen 127.0.0.1:18081 -name alpha -models ornith-1.5-35b-a3b,small-9b -down-file "$tmp/alpha.down" >"$tmp/alpha.log" 2>&1 & pids="$pids $!"
+bin/fakeupstream -listen 127.0.0.1:18082 -name beta  -models ornith-1.5-35b-a3b -down-file "$tmp/beta.down" >"$tmp/beta.log" 2>&1 & pids="$pids $!"
+bin/crossbar -config example.toml >"$tmp/crossbar.log" 2>&1 & pids="$pids $!"
+sleep 1.5
+fail() { echo "smoke: FAIL: $*" >&2; echo "--- crossbar.log"; cat "$tmp/crossbar.log"; exit 1; }
+base=http://127.0.0.1:17777
+
+h=$(curl -s -o /dev/null -w '%{http_code} %header{X-Crossbar-Host}' "$base/opencode-a/v1/models")
+[ "$h" = "200 alpha" ] || fail "opencode-a should go to alpha, got '$h'"
+h=$(curl -s -o /dev/null -w '%{http_code} %header{X-Crossbar-Host}' "$base/hermes-x/v1/models")
+[ "$h" = "200 beta" ] || fail "hermes-x should go to beta, got '$h'"
+h=$(curl -s -o /dev/null -w '%{http_code}' "$base/nope/v1/models")
+[ "$h" = "404" ] || fail "unknown route should be 404, got '$h'"
+
+touch "$tmp/alpha.down"; sleep 2.5   # poll_interval is 1s in example.toml
+h=$(curl -s -o /dev/null -w '%{http_code} %header{X-Crossbar-Host}' "$base/opencode-a/v1/models")
+[ "$h" = "200 beta" ] || fail "with alpha down, opencode-a should fail over to beta, got '$h'"
+curl -s "$base/_crossbar/hosts" | grep -q '"alpha":{"healthy":false' || fail "/_crossbar/hosts does not show alpha unhealthy: $(curl -s $base/_crossbar/hosts)"
+
+rm "$tmp/alpha.down"; sleep 3.5     # recovery needs two good polls
+h=$(curl -s -o /dev/null -w '%header{X-Crossbar-Host}' "$base/opencode-a/v1/models")
+[ "$h" = "alpha" ] || fail "alpha should be back after two good polls, got '$h'"
+
+# Streaming: five chunks 200 ms apart must arrive over >= 0.6 s, not all at once at the end.
+start=$(date +%s%N)
+first=""
+curl -sN -X POST -H 'Content-Type: application/json' -d '{"model":"ornith-1.5-35b-a3b","stream":true,"messages":[]}' \
+  "$base/opencode-a/v1/chat/completions" | while IFS= read -r line; do
+    [ -n "$line" ] || continue
+    now=$(date +%s%N); echo "$(( (now - start) / 1000000 )) $line"
+  done > "$tmp/stream.txt"
+firstms=$(head -1 "$tmp/stream.txt" | cut -d' ' -f1); lastms=$(tail -1 "$tmp/stream.txt" | cut -d' ' -f1)
+[ -n "$firstms" ] && [ "$((lastms - firstms))" -ge 600 ] || fail "stream arrived in one burst (first ${firstms:-?} ms, last ${lastms:-?} ms):
+$(cat "$tmp/stream.txt")"
+grep -q 'DONE' "$tmp/stream.txt" || fail "stream did not end with [DONE]"
+
+grep -q 'route=opencode-a host=alpha' "$tmp/crossbar.log" || fail "no request log line"
+echo "smoke: ok (stream spread $((lastms - firstms)) ms)"