diff --git a/.env.template b/.env.template
deleted file mode 100644
index 06422a6c..00000000
--- a/.env.template
+++ /dev/null
@@ -1,20 +0,0 @@
-# Supabase
-SUPABASE_URL
-SUPABASE_KEY
-MEMORY_TABLE
-CONVERSATION_TABLE
-VECTOR_TABLE
-MATCH_FUNCTION
-
-# OpenAI
-OPENAI_API_KEY=
-OPENAI_API_TYPE=
-OPENAI_API_BASE=
-OPENAI_API_VERSION=
-OPENAI_API_DEPLOYMENT_NAME=
-
-# Sentry
-SENTRY_DSN=
-SENTRY_ENVIRONMENT=
-SENTRY_RELEASE=
-
diff --git a/README.md b/README.md
index f4e47c6f..2a549aed 100644
--- a/README.md
+++ b/README.md
@@ -76,6 +76,20 @@ docker build -t honcho-api .
 docker run --env-file .env -p 8000:8000 honcho-api:latest
 ```
 
+#### Deploy on Fly
+
+The API can also be deployed on fly.io with the following commands:
+
+```bash
+cd honcho/api
+fly launch
+```
+
+You can also add your secrets with the following shortcut command:
+```bash
+cat .env | fly secrets import
+```
+
 ### Client SDK
 
 Install the honcho client sdk from a python project with the following command:
diff --git a/fly.toml b/api/fly.toml
similarity index 63%
rename from fly.toml
rename to api/fly.toml
index d36e890b..d0629718 100644
--- a/fly.toml
+++ b/api/fly.toml
@@ -1,18 +1,19 @@
-# fly.toml app configuration file generated for honcho on 2023-09-11T10:58:33-04:00
+# fly.toml app configuration file generated for honcho-restless-dew-484 on 2024-01-18T08:20:57-08:00
 #
 # See https://fly.io/docs/reference/configuration/ for information about how to use this file.
 #
 
 app = "honcho"
-primary_region = "bos"
 kill_signal = "SIGINT"
 kill_timeout = "5s"
 
 [experimental]
   auto_rollback = true
 
+[build]
+
 [processes]
-api = "python -m uvicorn main:app --host 0.0.0.0 --port 8000"
+  api = "python -m uvicorn src.main:app --host 0.0.0.0 --port 8000"
 
 [http_service]
   internal_port = 8000
@@ -22,5 +23,11 @@ api = "python -m uvicorn main:app --host 0.0.0.0 --port 8000"
   processes = ["api"]
   [http_service.concurrency]
     type = "requests"
-    soft_limit = 200
     hard_limit = 250
+    soft_limit = 200
+
+[[vm]]
+  cpu_kind = "shared"
+  cpus = 1
+  memory_mb = 512
+  processes = ["api"]