https://github.com/statespace-tech/statespace
Interactive web apps for AI agents
https://github.com/statespace-tech/statespace
agent analytics artificial-intelligence context-engineering data-engineering data-science database information-retrieval machine-learning markdown mcp rust sql webapp
Last synced: 28 days ago
JSON representation
Interactive web apps for AI agents
- Host: GitHub
- URL: https://github.com/statespace-tech/statespace
- Owner: statespace-tech
- License: mit
- Created: 2025-06-11T05:50:09.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2026-03-02T05:15:49.000Z (30 days ago)
- Last Synced: 2026-03-02T05:17:07.831Z (30 days ago)
- Topics: agent, analytics, artificial-intelligence, context-engineering, data-engineering, data-science, database, information-retrieval, machine-learning, markdown, mcp, rust, sql, webapp
- Language: Rust
- Homepage: https://statespace.com/
- Size: 2.89 MB
- Stars: 820
- Watchers: 12
- Forks: 64
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
- Support: SUPPORT.md
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-mcp - statespace-tech/statespace - ToolFront by statespace-tech is a declarative framework that enables rapid creation and sharing of modular LLM-powered RAG applications using pure Markdown with zero boilerplate code. (MCP Frameworks and libraries / Python)
README
# Statespace
**Turn your data into shareable LLM apps in minutes. All in pure Markdown. Zero boilerplate.**
[](https://github.com/statespace-tech/statespace/actions/workflows/test.yml)
[](https://github.com/statespace-tech/statespace/blob/main/LICENSE)
[](https://discord.gg/rRyM7zkZTf)
[](https://x.com/statespace_tech)
---
**Documentation: [docs.statespace.com](https://docs.statespace.com/)**
**Source code: [https://github.com/statespace-tech/statespace](https://github.com/statespace-tech/statespace)**
---
_Statespace is a declarative framework for building modular LLM applications in Markdown._
## Installation
Install the CLI:
```bash
curl -fsSL https://statespace.com/install.sh | bash
```
## Example
### Create it
Start with one file: `README.md`
```yaml
---
tools:
- [date]
---
# Instructions
- Run `date` to check today's date
```
### Serve it
Run your app locally (no account required):
```bash
statespace serve .
```
> **Note**: Runs on `http://127.0.0.1:8000`
### Ask it
Include the app URL in your prompts:
Claude Code
```bash
claude "Get today's date from http://127.0.0.1:8000"
```
GitHub Copilot
```bash
copilot "Get today's date from http://127.0.0.1:8000"
```
Codex
```bash
codex "Get today's date from http://127.0.0.1:8000"
```
For custom agents, add an HTTP request tool:
TypeScript
```typescript
import { execFileSync } from 'child_process';
/**
* Execute curl commands to interact with Statespace apps.
*/
function curlTool(url: string, args: string[]): string {
const result = execFileSync('curl', [...args, url], {
encoding: 'utf-8'
});
return result.toString();
}
```
Rust
```rust
use std::process::Command;
/// Execute curl commands to interact with HTTP endpoints.
fn curl_tool(url: &str, args: Vec<&str>) -> String {
let output = Command::new("curl")
.args(&args)
.arg(url)
.output()
.unwrap();
String::from_utf8_lossy(&output.stdout).to_string()
}
```
## Complex example
### Upgrade it
Your app can grow into a full project:
```bash
project/
├── README.md
├── data/
│ ├── log1.txt
│ ├── log2.txt
│ └── log3.txt
└── src/
├── agentic_rag.md
├── text2sql.md
└── vector_search.md
3 directories, 9 files
```
Update `README.md` with CLI tools to progressively discover and read other files:
```yaml
---
tools:
- [date]
- [ls]
- [cat]
---
# Instructions
- Run `date` to check today's date
- Use `ls` and `cat` to discover and read other files
```
### Compose it
Add pages and CLI tools for different workflows:
Vector Search
```yaml
---
tools:
- [curl, -X, POST, https://host.pinecone.io/records/namespaces/user/search]
---
# Vector search instructions:
- Query documents with your vector database API
```
> **Note**: replace the API with your own (e.g., Pinecone, Weaviate, Qdrant)
Text-to-SQL
```yaml
---
tools:
- [psql, -U, $USER, -d, $DB, -c, { regex: "^SELECT\b.*" }]
---
# Text-to-SQL instructions:
- Use `psql` for read-only PostgreSQL queries
```
> **Note**: use your own database CLI (e.g., `mysql`, `sqlite3`, `mongosh`).
Agentic RAG
```yaml
---
tools:
- [grep, -r, -i, { }, ../data/]
---
# Document search instructions:
- Use `grep` to search documents in `../data/`
```
> **Note**: apps can include any file type (e.g. `.csv`, `.sqlite`, `.json`)
### Deploy it
Create a free [Statespace account](https://statespace.com/) to deploy authenticated private apps:
```bash
statespace app create . --visibility private
```
Alternatively, share public apps with the community:
```bash
statespace app create . --visibility public
```
> **Note** Statespace gives you app URLs you can paste in prompts and instructions.
## Community & Contributing
- **Discord**: Join our [community server](https://discord.gg/rRyM7zkZTf) for real-time help and discussions
- **X**: Follow us [@statespace_tech](https://x.com/statespace_tech) for updates and news
- **Issues**: Report bugs or request features on [GitHub Issues](https://github.com/statespace-tech/statespace/issues)
## License
This project is licensed under the terms of the MIT license.