molecule-ai/docs
47
0
Fork 0
Code Issues Pull Requests 11 Actions Packages Projects Releases Wiki Activity

docs(architecture): replace hand-drawn ASCII System Boundaries with the real SVG #79

Merged
documentation-specialist merged 2 commits from docs/architecture-page-use-svg into main 2026-06-02 19:27:02 +00:00
Conversation 2 Commits 2 Files Changed 1
+12 -35
1 changed files with 12 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
content/docs/architecture/architecture.md → content/docs/architecture/architecture.mdx
+12 -35
View File
@@ -10,36 +10,13 @@ The platform is fully distributed — workspaces can run on different machines a
## System Boundaries
The platform consists of four distinct systems:
Operator surfaces reach a thin central control plane that provisions one isolated tenant per org; each tenant runs its own control core (the `workspace-server`, with its own Postgres + Redis) above a hierarchy of workspaces. Runtimes and model providers are pluggable:
```
+-----------------------------------------------------------+
| canvas/ Next.js 15 frontend |
| React Flow visual canvas, Zustand state, WebSocket |
+-----------------------------+-----------------------------+
| HTTP + WebSocket
+-----------------------------v-----------------------------+
| workspace-server/ Go (gin) backend |
| Registry, hierarchy, event log, provisioner, bundles |
+------+---------------------------------------+------------+
| Postgres | Redis
+------v------+ +---------v---------+
| Postgres | | Redis |
| (Docker) | | (Docker) |
+-------------+ +-------------------+
A2A HTTP (JSON-RPC 2.0) — direct workspace-to-workspace
+-----------------------------------------------------------+
| workspace/ pluggable workspace runtime |
| LangGraph / Claude Code / AutoGen / OpenClaw / Hermes |
| / Codex / Google ADK + a2a-sdk |
+-----------------------------------------------------------+
|
+------v----------------------------------------------------+
| Langfuse Observability (Docker) |
| Traces every LLM call across all workspaces |
+-----------------------------------------------------------+
```
<img
src="/diagrams/platform-architecture.svg"
alt="Molecule AI platform architecture: operator surfaces reach a thin central Control Plane (orgs, billing, tenant provisioning, LLM proxy, provider registry) that provisions one isolated tenant per org. Each tenant runs its own control core — the workspace-server with provisioner, registry/discovery, A2A proxy, WebSocket hub, scheduler, secrets, audit, and its own Postgres + Redis — above a hierarchy of workspaces, each one agent on its own machine, communicating peer-to-peer over A2A. Runtimes (claude-code, langgraph, autogen, openclaw, hermes, codex, google-adk) and model providers are pluggable."
style={{ width: '100%', height: 'auto', margin: '1rem 0' }}
/>
### Plugins
@@ -59,12 +36,12 @@ Plugins inject rules and skills into all agents automatically. Workspace-specifi
### Data Flow Summary
- **Canvas <-> Platform:** HTTP REST + WebSocket for real-time events
- **Platform <-> Postgres:** Source of truth for registry, hierarchy, events
- **Platform <-> Redis:** Ephemeral state — liveness, caching, pub/sub
- **Platform -> Workspace:** Provisioning (tiered Docker deployment), discovery
- **Workspace <-> Workspace:** Direct A2A (JSON-RPC 2.0) — platform not in path
- **Workspace -> Langfuse:** Automatic LLM tracing
- **Canvas ↔ Platform:** HTTP REST + WebSocket for real-time events
- **Platform ↔ Postgres:** Source of truth for registry, hierarchy, events
- **Platform ↔ Redis:** Ephemeral state — liveness, caching, pub/sub
- **Platform → Workspace:** Provisioning (tiered Docker deployment), discovery
- **Workspace ↔ Workspace:** Direct A2A (JSON-RPC 2.0) — platform not in path
- **Workspace → Langfuse:** Automatic LLM tracing
## Folder Structure