The open-source agent harness - the runtime layer that turns an LLM into a working agent.
docs(readme): add real screenshots and fix stale copy (#113)
shubhamagarwal-create029ea5ff6438
diff --git a/README.md b/README.mdindex f56bd7c1e..5f404d551 100644--- a/README.md+++ b/README.md@@ -11,8 +11,6 @@ TrueForge runs the agent execution loop for you — model calls, tool use, conte[Documentation](#) · [Quickstart Guide](#) · [API Reference](#) · [Community](#)-<!-- TODO: hero screenshot of the chat UI -->-## Why TrueForge?@@ -21,7 +19,7 @@ Building an agent is easy. Running one in production is not — you need streami- **Multi-turn sessions with streaming** — resumable turn streams that survive reconnects and server restarts.- **MCP tool servers** — connect any [Model Context Protocol](https://modelcontextprotocol.io) server, including ones that require OAuth.-- **Any model provider** — OpenAI, Anthropic, Google, and OpenAI-compatible endpoints, configured from the UI or the API.+- **Any model provider** — OpenAI, Anthropic, Google Gemini, and a catalog of hosted and open-weight models, or any OpenAI-compatible endpoint — all configured from the UI or the API.- **Skills** — reusable instruction packs the agent loads on demand.- **Sandboxed code execution** — run agent-generated code in isolated sandboxes.- **Human-in-the-loop approvals** — pause the agent and wait for a person before sensitive tool calls.@@ -60,7 +58,7 @@ Then open [http://localhost:3000](http://localhost:3000) — Vite serves the UIRuns the full production topology on your machine: the server (UI + API), Postgres, and Redis. Clone the repo first:```bash-git clone <REPO_URL> trueforge && cd trueforge # TODO: repo URL+git clone https://github.com/truefoundry/trueforge.git trueforge && cd trueforgecp packages/server/.env.example packages/server/.envdocker compose up --build```@@ -98,15 +96,13 @@ See the [chart README](charts/truefoundry-utils/README.md) for Secrets, external## Getting started walkthrough-<!-- TODO: replace with real screenshots -->--1. **Add a model provider** — open **Settings → Model Providers**, pick a provider from the catalog, and paste your API key.+1. **Add a model provider** — open **Settings → Models**, pick a provider from the catalog, and paste your API key.2. **(Optional) Connect tools** — add MCP servers, skills, and a sandbox provider under **Settings**.- + 3. **Start a session** — create a chat and talk to your agent. Streaming, tool calls, and approvals all show up live in the UI.diff --git a/docs/assets/getting-started-chat.png b/docs/assets/getting-started-chat.pngnew file mode 100644index 000000000..45791a3f8Binary files /dev/null and b/docs/assets/getting-started-chat.png differdiff --git a/docs/assets/getting-started-connectors.png b/docs/assets/getting-started-connectors.pngnew file mode 100644index 000000000..b73624f77Binary files /dev/null and b/docs/assets/getting-started-connectors.png differdiff --git a/docs/assets/getting-started-provider.png b/docs/assets/getting-started-provider.pngnew file mode 100644index 000000000..749089b80Binary files /dev/null and b/docs/assets/getting-started-provider.png differdiff --git a/docs/assets/hero.png b/docs/assets/hero.pngnew file mode 100644index 000000000..365dc508cBinary files /dev/null and b/docs/assets/hero.png differ