studio

Name: studio
Author: decocms

391stars48forks

How to install studio?

decocms/studio

$git clone https://github.com/decocms/studio

Installs into the current project.

Summary

> TL;DR: Your team needs a secure internal vibecoding platform. You just found it. Configure agents with team context. Connect private MCPs once — share capabilities, not credentials. Keep the model layer interchangeable. Roll out across the organization with SSO, RBAC, audit

Files · 1

View on GitHub

README.md

1	<h1 align="center">deco Studio</h1>
2
3	<p align="center">
4	<em>Open-source · TypeScript-first · Deploy anywhere</em><br/><br/>
5	<b>Open-source private AI workspace for organizations.</b>
6	</p>
7
8	<p align="center">
9	<a href="https://docs.decocms.com/">Docs</a> ·
10	<a href="https://decocms.com/discord">Discord</a> ·
11	<a href="https://decocms.com/studio">decocms.com/studio</a>
12	</p>
13
14	> TL;DR: Your team needs a secure internal vibecoding platform. You just found it. Configure agents with team context. Connect private MCPs once — share capabilities, not credentials. Keep the model layer interchangeable. Roll out across the organization with SSO, RBAC, audit logs, and cost controls — all through one MCP endpoint. Local-first. Self-host or use the cloud.
15
16	---
17
18	## What is deco Studio?
19
20	Studio packages the infrastructure behind an internal AI rollout: model routing, MCP authentication, agent configuration, SSO, RBAC, audit logs, and usage accounting. Your teams get chat. You keep control.
21
22	Under the hood it's one control plane for your AI agents — one MCP endpoint for all your agents, tools, and models. Agents package context, tools, and policy into something you publish to the organization. Connections give them governed access to your systems — GitHub, Slack, Postgres, Sentry, anything that speaks MCP — with tokens stored in an encrypted vault. Models stay interchangeable: OpenRouter or direct providers, chosen per agent and per tool.
23
24	Start with one team. Standardize approved models, tools, and context. Expand across the organization without copying secrets or rebuilding the platform. Install locally and it stays private; sync to the cloud for remote access, team roles, and shared billing.
25
26	```
27	┌─────────────────────────────────────────────────────────────────┐
28	│ Clients │
29	│ Cursor · Claude · VS Code · Custom Agents │
30	└───────────────────────────┬─────────────────────────────────────┘
31	│
32	▼
33	┌─────────────────────────────────────────────────────────────────┐
34	│ DECO STUDIO │
35	│ Agents · Connections · Models · Vault · Observability │
36	└───────────────────────────┬─────────────────────────────────────┘
37	│
38	▼
39	┌─────────────────────────────────────────────────────────────────┐
40	│ Tools & MCP Servers │
41	│ GitHub · Slack · Postgres · OpenRouter · Your APIs │
42	└─────────────────────────────────────────────────────────────────┘
43	```
44
45	---
46
47	## Quick Start
48
49	```bash
50	bunx decostudio
51	```
52
53	Or clone and run from source:
54
55	```bash
56	git clone https://github.com/decocms/studio.git
57	bun install
58	bun run dev
59	```
60
61	> runs at [http://localhost:4000](http://localhost:4000) (client) with API routes proxied to the Bun server
62
63	---
64
65	## What you get
66
67	### Agents
68
69	Package context, tools, and policy into an agent. Define instructions, add skills and files, grant approved MCP access, choose a model policy, then publish the agent to the organization. Each agent is its own MCP endpoint — callable from Cursor, Claude Desktop, your own code, or another agent. Agents compose, and every action is tracked with cost attribution.
70
71	### Connections
72
73	Connect private systems once, securely. Register MCP servers at the organization level through a web UI with one-click OAuth — no JSON configs. Tokens live in the encrypted vault, and you grant tool-level access by organization, role, or agent. Share MCP capabilities — not credentials.
74
75	As tool surfaces grow, Studio exposes Virtual MCPs — one endpoint, different strategies for which tools to surface:
76
77	- Full-context: expose everything (simple, deterministic, good for small toolsets)
78	- Smart selection: narrow the toolset before execution
79	- Code execution: load tools on demand in a sandbox
80
81	### Models
82
83	Keep the AI layer interchangeable.

People who liked this also viewed

6 picks

Type

studio

391stars48forks

View on GitHub

How to install studio?

decocms/studio

$git clone https://github.com/decocms/studio

Installs into the current project.

Summary

Files · 1

View on GitHub

README.md

1	<h1 align="center">deco Studio</h1>
2
3	<p align="center">
4	<em>Open-source · TypeScript-first · Deploy anywhere</em><br/><br/>
5	<b>Open-source private AI workspace for organizations.</b>
6	</p>
7
8	<p align="center">
9	<a href="https://docs.decocms.com/">Docs</a> ·
10	<a href="https://decocms.com/discord">Discord</a> ·
11	<a href="https://decocms.com/studio">decocms.com/studio</a>
12	</p>
13
14	> TL;DR: Your team needs a secure internal vibecoding platform. You just found it. Configure agents with team context. Connect private MCPs once — share capabilities, not credentials. Keep the model layer interchangeable. Roll out across the organization with SSO, RBAC, audit logs, and cost controls — all through one MCP endpoint. Local-first. Self-host or use the cloud.
15
16	---
17
18	## What is deco Studio?
19
20	Studio packages the infrastructure behind an internal AI rollout: model routing, MCP authentication, agent configuration, SSO, RBAC, audit logs, and usage accounting. Your teams get chat. You keep control.
21
22	Under the hood it's one control plane for your AI agents — one MCP endpoint for all your agents, tools, and models. Agents package context, tools, and policy into something you publish to the organization. Connections give them governed access to your systems — GitHub, Slack, Postgres, Sentry, anything that speaks MCP — with tokens stored in an encrypted vault. Models stay interchangeable: OpenRouter or direct providers, chosen per agent and per tool.
23
24	Start with one team. Standardize approved models, tools, and context. Expand across the organization without copying secrets or rebuilding the platform. Install locally and it stays private; sync to the cloud for remote access, team roles, and shared billing.
25
26	```
27	┌─────────────────────────────────────────────────────────────────┐
28	│ Clients │
29	│ Cursor · Claude · VS Code · Custom Agents │
30	└───────────────────────────┬─────────────────────────────────────┘
31	│
32	▼
33	┌─────────────────────────────────────────────────────────────────┐
34	│ DECO STUDIO │
35	│ Agents · Connections · Models · Vault · Observability │
36	└───────────────────────────┬─────────────────────────────────────┘
37	│
38	▼
39	┌─────────────────────────────────────────────────────────────────┐
40	│ Tools & MCP Servers │
41	│ GitHub · Slack · Postgres · OpenRouter · Your APIs │
42	└─────────────────────────────────────────────────────────────────┘
43	```
44
45	---
46
47	## Quick Start
48
49	```bash
50	bunx decostudio
51	```
52
53	Or clone and run from source:
54
55	```bash
56	git clone https://github.com/decocms/studio.git
57	bun install
58	bun run dev
59	```
60
61	> runs at [http://localhost:4000](http://localhost:4000) (client) with API routes proxied to the Bun server
62
63	---
64
65	## What you get
66
67	### Agents
68
69	Package context, tools, and policy into an agent. Define instructions, add skills and files, grant approved MCP access, choose a model policy, then publish the agent to the organization. Each agent is its own MCP endpoint — callable from Cursor, Claude Desktop, your own code, or another agent. Agents compose, and every action is tracked with cost attribution.
70
71	### Connections
72
73	Connect private systems once, securely. Register MCP servers at the organization level through a web UI with one-click OAuth — no JSON configs. Tokens live in the encrypted vault, and you grant tool-level access by organization, role, or agent. Share MCP capabilities — not credentials.
74
75	As tool surfaces grow, Studio exposes Virtual MCPs — one endpoint, different strategies for which tools to surface:
76
77	- Full-context: expose everything (simple, deterministic, good for small toolsets)
78	- Smart selection: narrow the toolset before execution
79	- Code execution: load tools on demand in a sandbox
80
81	### Models
82
83	Keep the AI layer interchangeable.

People who liked this also viewed

6 picks

Type