Superintelligence layer for founders.
Website · Documentation · Discord
Lightfast is the operating system that runs your startup. Your tools, your agents, your entire operation — orchestrated in one place. Strategy, ops, execution. Lightfast runs all of it.
Your tools don't share memory. Something breaks in production and you're switching between Sentry, GitHub, Vercel, and Linear — manually connecting dots that the system should already know. Lightfast builds the memory layer your stack never had.
Every event across every connected tool flows into a living graph that understands causality, ownership, and relationships — not just stores them. The PR that caused the incident. The engineer who owns the system. The Linear ticket tracking the fix. The deployment that shipped it. Ask one question, get the full picture with cited sources. The longer Lightfast runs, the more it understands about your team, your patterns, and your stage.
The operating layer is what acts on that memory. Agents don't call twelve different APIs — they express intent to Lightfast, and Lightfast resolves it: right tool, right context, every time. Define a rule — "every production release needs an approved review and a closed ticket" — and the OS enforces it continuously, not on a schedule.
As the number of agents in your company grows, you don't want twelve agents calling twelve tools independently. You want one system they all operate through — with shared memory, shared context, and your rules enforced at the kernel level. That's where Lightfast is going.
Available now:
| Source | Events |
|---|---|
| GitHub | Push, pull requests, issues, code reviews |
| Vercel | Deployments, project activity |
| Sentry | Errors, issues, alerts |
| Linear | Issues, comments, projects, cycles |
Coming soon:
- Dev & ops: Slack, Notion, Confluence, PagerDuty
- Business: Stripe, HubSpot, Apollo
- Request an integration →
npm install lightfastimport { Lightfast } from "lightfast";
const lightfast = new Lightfast({ apiKey: process.env.LIGHTFAST_API_KEY });
// Search your workspace
const results = await lightfast.search({
query: "how does authentication work",
limit: 10,
});
// Get full document content
const content = await lightfast.contents({
ids: ["doc_abc123"],
});
// Find similar documents
const similar = await lightfast.findSimilar({
id: "doc_abc123",
threshold: 0.7,
});Connect AI assistants directly to your workspace via Model Context Protocol.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"lightfast": {
"command": "npx",
"args": ["-y", "@lightfastai/mcp"],
"env": {
"LIGHTFAST_API_KEY": "sk-lf-..."
}
}
}
}Claude Code (CLI)
Add to .mcp.json in your project root (or ~/.claude.json for global):
{
"mcpServers": {
"lightfast": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@lightfastai/mcp"],
"env": {
"LIGHTFAST_API_KEY": "sk-lf-..."
}
}
}
}Or use the CLI: claude mcp add lightfast --scope project -- npx -y @lightfastai/mcp
Cursor
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"lightfast": {
"command": "npx",
"args": ["-y", "@lightfastai/mcp"],
"env": {
"LIGHTFAST_API_KEY": "sk-lf-..."
}
}
}
}OpenAI Codex
Add to ~/.codex/config.toml:
[mcp_servers.lightfast]
command = "npx"
args = ["-y", "@lightfastai/mcp"]
[mcp_servers.lightfast.env]
LIGHTFAST_API_KEY = "sk-lf-..."Available tools:
lightfast_search— Search your workspacelightfast_contents— Fetch full document contentlightfast_find_similar— Find semantically similar documents
- Your data stays yours — We never train on your data. Complete tenant isolation.
- Encrypted at rest and in transit — Industry-standard security practices
- Role-based access — Workspace permissions mirror your source permissions
- Self-hosted option — Coming soon for enterprises with strict data residency requirements
- Node.js >= 18
- A Lightfast API key — get started
- API Reference — Full endpoint documentation
- SDK Guide — TypeScript SDK usage
- MCP Setup — Configure AI assistants
- Changelog — Latest updates and releases
- Blog — Tutorials, announcements, and deep dives
We welcome contributions! See CONTRIBUTING.md for guidelines.
git clone https://github.com/lightfastai/lightfast.git
cd lightfast
pnpm install
pnpm dev- Discord — Chat with the team and community
- GitHub Issues — Report bugs and request features
- Twitter — Follow for updates
Lightfast is licensed under the Functional Source License, Version 1.1 (FSL-1.1-ALv2) — a source-available license that automatically converts to Apache 2.0 after 2 years.
For Users: You can use Lightfast freely for internal business purposes, education, and research. Each version becomes fully open source (Apache 2.0) two years after release.
See LICENSING.md for complete details.
