LangAlpha

A vibe investing agent harness
LangAlpha is built to help interpret financial markets and support investment decisions.

English ｜ 简体中文 ｜ 日本語

Getting Started • API Docs • Agent Core • Backend • Web • TUI • Plugins

Pin a curated news brief from the dashboard, kick off idea generation, and dispatch parallel subagents to screen the market — then get five long/short pair-trade ideas in an inline interactive dashboard, calibrated to your book.

Why LangAlpha

Every AI finance tool today treats investing as one-shot: ask a question, get an answer, move on. But real investing is Bayesian — you start with a thesis, new data arrives daily, and you update your conviction accordingly. It's an iterative process that unfolds over weeks and months: refining theses, revisiting positions, layering new analysis on top of old. No single prompt captures that.

From vibe coding to vibe investing

Inspired by software engineering: a codebase persists, and every commit builds on what came before. Code agent harnesses like Claude Code and OpenCode succeeded by building agents that embrace this pattern, exploring existing context and building on prior work. LangAlpha brings that same insight: give the agent a persistent workspace, and research naturally compounds.

In practice, you create a workspace per research goal ("Q2 rebalance", "data center demand deep dive", "energy sector rotation"). The agent interviews you about your goals and style, produces its first deliverable, and saves everything to the workspace filesystem. Come back tomorrow and your files, threads, and accumulated research are still there.

Features Highlights

• Progressive Tool Discovery — Any MCP tools loaded as summary in context and full documentation dumped into the workspace, allowing the agent to discover and use tools truly on demand. Also supports binding json tools with skills and only expose to agent when skill is activated.
• Programmatic Tool Calling (PTC) — The agent writes and executes Python to process financial data from mcp servers instead of pouring raw data into the LLM context window, enabling complex multi-step analysis while dramatically reducing token waste.
• Financial data ecosystem — Multi-tier provider hierarchy with native tools for quick lookups and MCP servers for bulk data processing, charting, and multi-year analysis in sandboxes.
• Persistent workspaces — Each workspace maps to a dedicated sandbox with structured directories and a workspace notes file (agent.md) that compounds research across sessions and threads. A separate long-term memory store (.agents/user/memory/, .agents/workspace/memory/) persists durable user preferences and cross-sandbox knowledge, and a user-managed memo store (.agents/user/memo/) lets you upload PDFs and markdown research notes that the agent can read on demand.
• Skills for Financial Research — Pre-built workflows for DCF models, initiating coverage reports, earnings analysis, morning notes, document generation, and more — activatable by slash command or auto-detection.
• Finance Research Workbench — Web UI with inline financial charts, multi-format file viewer, TradingView charting, real-time WebSocket market data, agent-drawn chart annotations, a per-turn source-provenance panel, shareable conversations, and subagent monitoring.
• Multi-provider model layer — Provider-agnostic LLM abstraction and automatic failover on error.
• Automations — Schedule recurring or one-shot tasks, or set price-triggered automations that fire when a stock or index hits a real-time price condition.
• Secretary — Flash agent doubles as a secretary: create and manage workspaces, dispatch deep PTC analyses in the background, monitor running tasks, and retrieve results — all through conversational commands with human-in-the-loop approval.
• Agent swarm — Parallel async subagents with isolated context windows, preloaded toolset/skills, mid-execution steering, checkpoint-based resume, and live progress monitoring in the UI.
• Live steering — Send follow-up messages while the agent/subagent is working to course-correct, clarify, or redirect without waiting for it to finish.
• Middleware stack — a deep, composable middleware stack handling skill loading, plan mode, multimodal input, auto-compaction, and context management to support long-running agent sessions.
• Security & vault — Encryption at rest via pgcrypto, automatic credential leak detection and redaction, sandboxed execution, and per-account secret storage for safe agent access
• Channel integrations — Use LangAlpha from Slack, Discord, Feishu, and Telegram, plus email delivery for scheduled results.
• Production-ready infrastructure — SSE-streamed agent activity with Redis-buffered reconnection replay, background execution decoupled from HTTP connections, and PostgreSQL-backed state persistence.

What Powers It

System Architecture

%%{init: {'theme': 'neutral'}}%%

flowchart TB
    Web["Web UI<br/>React 19 · Vite · Tailwind"] -- "REST · SSE" --> API
    Web -- "WebSocket" --> WSP
    CLI["CLI / TUI"] -- "REST · SSE" --> API

    subgraph Server ["FastAPI Backend"]
        API["API Routers<br/>Threads · Workspaces · Market Data<br/>OAuth · Automations · Skills"]
        WSP["WebSocket Proxy"]
        API --> ChatHandler["Chat Handler<br/>LLM Resolution · Workflow Dispatch"]
        ChatHandler --> BTM["Background Task Manager<br/>Decoupled Execution · Workflow Lifecycle"]
    end

    subgraph PostgreSQL ["PostgreSQL — Dual Pool"]
        AppPool[("App Data<br/>Users · Workspaces · Threads<br/>Turns · BYOK Keys · Automations")]
        CheckPool[("LangGraph Checkpointer<br/>Agent State · Checkpoints")]
    end

    subgraph Redis ["Redis"]
        EventBuf[("SSE Event Buffer<br/>150K events · Reconnect Replay")]
        DataCache[("API Cache<br/>Market Data · SWR")]
        Steering[("Steering Queue<br/>User Messages Mid-workflow")]
    end

    BTM --> AppPool
    BTM --> CheckPool
    BTM --> EventBuf
    BTM --> Steering
    API --> DataCache

    BTM -. "Sandbox API" .-> Daytona["Daytona<br/>Cloud Sandboxes"]
    API -. "REST" .-> FinAPIs["Financial APIs<br/>FMP · SEC EDGAR"]
    WSP -. "WebSocket" .-> GData["ginlix-data<br/>Polygon.io · Massive"]

Multi-Provider Model Layer