diff --git a/README.md b/README.md
index eb2928b..032abf1 100644
--- a/README.md
+++ b/README.md
@@ -33,6 +33,7 @@ Forge is built directly on the **MIT-licensed LangChain v1 + LangGraph v1** fram
 - [Run with Docker](#run-with-docker-production-shaped)
 - [Documentation](#documentation)
 - [Tech stack](#tech-stack)
+- [Local modifications](#local-modifications)
 - [Contributing](#contributing)
 - [License](#license)
 
@@ -228,6 +229,26 @@ With `FORGE_ENVIRONMENT=production`, Forge enables a hardening guard and **refus
 | **Data (prod)** | Postgres 16 + pgvector · Redis 7 · Fernet/Vault secrets |
 | **Observability** | Built-in tracer + cost accounting · OpenTelemetry / Langfuse export |
 
+## Local modifications
+
+This repository is a **fork with local customizations** of the upstream [Forge](https://github.com/nihalashetty/Forge) project. It is hosted by the **Gitinbox** organization for internal AI-agent platform use.
+
+### Changes vs upstream ([`nihalashetty/Forge`](https://github.com/nihalashetty/Forge/tree/main))
+
+| Area | Upstream | This fork |
+|---|---|---|
+| **Model catalog** (`apps/api/forge/model_catalog.py`) | OpenAI / Anthropic / Google / local fake models only | **Added DeepSeek** `deepseek-chat` (128k, $0.28/$0.42) and `deepseek-reasoner` (128k, $0.55/$2.19), registered as OpenAI-compatible endpoints |
+| **DeepSeek runtime** | N/A | Base URL is injected at runtime via `OPENAI_BASE_URL` env (no engine change, `resolve_model` works end-to-end) |
+
+All other engine, frontend, and packaging code is identical to upstream. To stay in sync with upstream:
+
+```bash
+git remote add upstream https://github.com/nihalashetty/Forge.git   # once
+git fetch upstream && git merge upstream/main
+```
+
+**Upstream repository:** <https://github.com/nihalashetty/Forge>
+
 ## Contributing
 
 Contributions are welcome. Forge is MIT-licensed and built to be extended.