dash

Name: dash
Author: agno-agi

byagno-agi· 4 MCP servers

Stars

2.2k

Forks

250

How to install dash?

agno-agi/dash

$git clone https://github.com/agno-agi/dash

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install dash by running `git clone https://github.com/agno-agi/dash`, then use it for the current task and follow its documentation at https://github.com/agno-agi/dash.

Files · 1

View on GitHub

README.md

1	# Dash
2
3	A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every query.
4
5	Chat with Dash via Slack, the terminal, or the [AgentOS](https://os.agno.com?utm_source=github&utm_medium=example-repo&utm_campaign=agent-example&utm_content=dash&utm_term=agentos) web UI.
6
7	## Quick Start
8
9	```sh
10	# Clone the repo
11	git clone https://github.com/agno-agi/dash.git && cd dash
12
13	cp example.env .env
14	# Edit .env and add your OPENAI_API_KEY
15
16	# Start the system
17	docker compose up -d --build
18
19	# Generate sample data and load knowledge
20	docker exec -it dash-api python scripts/generate_data.py
21	docker exec -it dash-api python scripts/load_knowledge.py
22	```
23
24	Confirm Dash is running at [http://localhost:8000/docs](http://localhost:8000/docs).
25
26	### Connect to the Web UI
27
28	1. Open [os.agno.com](https://os.agno.com?utm_source=github&utm_medium=example-repo&utm_campaign=agent-example&utm_content=dash&utm_term=agentos) and login
29	2. Add OS → Local → `http://localhost:8000`
30	3. Click "Connect"
31
32	Try it (SaaS metrics dataset):
33
34	- What's our current MRR?
35	- Which plan has the highest churn rate?
36	- Show me revenue trends by plan over the last 6 months
37	- Which customers are at risk of churning?
38
39	## Deploy to Railway
40
41	Railway deployment uses `.env.production` to keep production credentials separate from local dev.
42
43	```sh
44	cp example.env .env.production
45	# Edit .env.production — set OPENAI_API_KEY
46	```
47
48	### Step 1: Deploy infrastructure
49
50	This creates the Railway project, database, and app service. The app will crash-loop until the JWT key is added in the next step — that's expected.
51
52	```sh
53	railway login
54	./scripts/railway_up.sh
55	```
56
57	### Step 2: Get your JWT key
58
59	Production requires a `JWT_VERIFICATION_KEY` from [AgentOS](https://os.agno.com?utm_source=github&utm_medium=example-repo&utm_campaign=agent-example&utm_content=dash&utm_term=agentos). You need the Railway domain from step 1 to set this up.
60
61	1. Copy your Railway domain from the output of step 1 (e.g. `dash-production-xxxx.up.railway.app`)
62	2. Open [os.agno.com](https://os.agno.com?utm_source=github&utm_medium=example-repo&utm_campaign=agent-example&utm_content=dash&utm_term=agentos) and login
63	3. Add OS → Live → paste your Railway URL
64	4. Go to Settings and generate a key pair
65	5. Add the public key to `.env.production` (wrap in single quotes):
66
67	```bash
68	JWT_VERIFICATION_KEY='-----BEGIN PUBLIC KEY-----
69	MIIBIjANBgkq...
70	-----END PUBLIC KEY-----'
71	```
72
73	### Step 3: Push environment and redeploy
74
75	```sh
76	./scripts/railway_env.sh
77	./scripts/railway_redeploy.sh
78	```
79
80	`railway_env.sh` reads `.env.production` and sets each variable on the Railway service. Safe to run repeatedly. Handles multiline values (PEM keys) correctly.
81
82	### Production operations
83
84	Database scripts must run inside Railway's network (the internal hostname `pgvector.railway.internal` isn't reachable from your local machine). Use SSH to connect to the running container:
85
86	```sh
87	railway ssh --service dash
88	# Inside the container:
89	python scripts/generate_data.py
90	python scripts/load_knowledge.py
91	```
92
93	Other operations run locally:
94
95	```sh
96	railway logs --service dash
97	railway open
98	```
99
100	## Why Dash Exists
101
102	Ask a question in English, get a correct, meaningful answer. That's the goal. But raw LLMs writing SQL hit a wall fast: schemas lack meaning, types are misleading, tribal knowledge is missing, there's no way to learn from mistakes, and results lack interpretation.
103
104	The root cause is missing context and missing memory. Dash solves this with six layers of grounded context, a self-learning loop that improves with every query, and a focus on delivering insights you can act on.
105
106	## Architecture: Five Layers, One System
107
108	Agentic software is just software with the business logic replaced by agents. Everything else is systems engineering. Dash is built across five layers that reinforce each other.
109
110	```
111	Agent Engineering → dash/team.py + dash/agents/
112	Data Engineering → knowledge/ + A

6 picks

Type

dash

byagno-agi· 4 MCP servers

Stars

2.2k

Forks

250

How to install dash?

agno-agi/dash

$git clone https://github.com/agno-agi/dash

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install dash by running `git clone https://github.com/agno-agi/dash`, then use it for the current task and follow its documentation at https://github.com/agno-agi/dash.

Files · 1

View on GitHub

README.md

1	# Dash
2
3	A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every query.
4
5	Chat with Dash via Slack, the terminal, or the [AgentOS](https://os.agno.com?utm_source=github&utm_medium=example-repo&utm_campaign=agent-example&utm_content=dash&utm_term=agentos) web UI.
6
7	## Quick Start
8
9	```sh
10	# Clone the repo
11	git clone https://github.com/agno-agi/dash.git && cd dash
12
13	cp example.env .env
14	# Edit .env and add your OPENAI_API_KEY
15
16	# Start the system
17	docker compose up -d --build
18
19	# Generate sample data and load knowledge
20	docker exec -it dash-api python scripts/generate_data.py
21	docker exec -it dash-api python scripts/load_knowledge.py
22	```
23
24	Confirm Dash is running at [http://localhost:8000/docs](http://localhost:8000/docs).
25
26	### Connect to the Web UI
27
28	1. Open [os.agno.com](https://os.agno.com?utm_source=github&utm_medium=example-repo&utm_campaign=agent-example&utm_content=dash&utm_term=agentos) and login
29	2. Add OS → Local → `http://localhost:8000`
30	3. Click "Connect"
31
32	Try it (SaaS metrics dataset):
33
34	- What's our current MRR?
35	- Which plan has the highest churn rate?
36	- Show me revenue trends by plan over the last 6 months
37	- Which customers are at risk of churning?
38
39	## Deploy to Railway
40
41	Railway deployment uses `.env.production` to keep production credentials separate from local dev.
42
43	```sh
44	cp example.env .env.production
45	# Edit .env.production — set OPENAI_API_KEY
46	```
47
48	### Step 1: Deploy infrastructure
49
50	This creates the Railway project, database, and app service. The app will crash-loop until the JWT key is added in the next step — that's expected.
51
52	```sh
53	railway login
54	./scripts/railway_up.sh
55	```
56
57	### Step 2: Get your JWT key
58
59	Production requires a `JWT_VERIFICATION_KEY` from [AgentOS](https://os.agno.com?utm_source=github&utm_medium=example-repo&utm_campaign=agent-example&utm_content=dash&utm_term=agentos). You need the Railway domain from step 1 to set this up.
60
61	1. Copy your Railway domain from the output of step 1 (e.g. `dash-production-xxxx.up.railway.app`)
62	2. Open [os.agno.com](https://os.agno.com?utm_source=github&utm_medium=example-repo&utm_campaign=agent-example&utm_content=dash&utm_term=agentos) and login
63	3. Add OS → Live → paste your Railway URL
64	4. Go to Settings and generate a key pair
65	5. Add the public key to `.env.production` (wrap in single quotes):
66
67	```bash
68	JWT_VERIFICATION_KEY='-----BEGIN PUBLIC KEY-----
69	MIIBIjANBgkq...
70	-----END PUBLIC KEY-----'
71	```
72
73	### Step 3: Push environment and redeploy
74
75	```sh
76	./scripts/railway_env.sh
77	./scripts/railway_redeploy.sh
78	```
79
80	`railway_env.sh` reads `.env.production` and sets each variable on the Railway service. Safe to run repeatedly. Handles multiline values (PEM keys) correctly.
81
82	### Production operations
83
84	Database scripts must run inside Railway's network (the internal hostname `pgvector.railway.internal` isn't reachable from your local machine). Use SSH to connect to the running container:
85
86	```sh
87	railway ssh --service dash
88	# Inside the container:
89	python scripts/generate_data.py
90	python scripts/load_knowledge.py
91	```
92
93	Other operations run locally:
94
95	```sh
96	railway logs --service dash
97	railway open
98	```
99
100	## Why Dash Exists
101
102	Ask a question in English, get a correct, meaningful answer. That's the goal. But raw LLMs writing SQL hit a wall fast: schemas lack meaning, types are misleading, tribal knowledge is missing, there's no way to learn from mistakes, and results lack interpretation.
103
104	The root cause is missing context and missing memory. Dash solves this with six layers of grounded context, a self-learning loop that improves with every query, and a focus on delivering insights you can act on.
105
106	## Architecture: Five Layers, One System
107
108	Agentic software is just software with the business logic replaced by agents. Everything else is systems engineering. Dash is built across five layers that reinforce each other.
109
110	```
111	Agent Engineering → dash/team.py + dash/agents/
112	Data Engineering → knowledge/ + A

6 picks

Type

dash

How to install dash?

Related

dash

How to install dash?

Related