The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the The Neural Ledger Intelligence listing page.
Open-source developer tools for The Neural Ledger intelligence API.
TNL Intelligence gives AI agents and quantitative research systems structured, source-linked global event intelligence. It is an evidence and research layer, not a broker, an order router, or a source of trading-grade prices.
| Package | Purpose |
|---|---|
@theneuralledger/sdk | Typed TypeScript client for the TNL /v1 API |
@theneuralledger/mcp | Read-only MCP server over stdio or Streamable HTTP |
@theneuralledger/gateway | Hosted OAuth, tenant policy, quota, and audit MCP gateway |
@theneuralledger/onboarding | Developer credentials, static sample API, and explorer |
@theneuralledger/events | Webhook contracts, signed delivery, and verification helpers |
@theneuralledger/research | Evidence-first skills, orchestration, MCP App, and web UI |
@theneuralledger/adapters | Shared Cursor and OpenAI workflow contracts and rendering |
@theneuralledger/connectors | Shared n8n, Pipedream, and Zapier action/trigger contracts |
@theneuralledger/cli | tnl CLI, watch command, local cache, and foreground daemon |
tnl-intelligence | Python SDK and optional point-in-time quant research toolkit |
Set a member API key in the environment:
Run the MCP server over stdio:
Or run its localhost Streamable HTTP endpoint:
Use the CLI:
Use the TypeScript SDK:
Use the Python SDK:
127.0.0.1 by default.See SECURITY.md and the build plan. Research deployment boundaries and staged rollout are documented in Research operations.
Python development uses the project under python/tnl_intelligence.
MIT