# LangAlpha

> LangAlpha is an open-source harness for AI agents that research markets, build investment theses and trade your brokerage account within the permissions you set. Use it in the web app, or drive it from the langalpha command line (la for short) and its HTTP API.

- LangAlpha runs as a hosted platform and as a self-hosted open-source stack. Pages mark where the two behave differently with a "Hosted and self-hosted" note.
- The hierarchy is User, Computer, Workspace, Thread, Turn.
- Every page is also available as Markdown by appending .md to its URL, for example /concepts/computers.md.
- The langalpha CLI (la for short) starts and follows threads, answers approvals, and manages workspaces, computers and automations from a terminal, a script or the agent inside a computer. Its reference is under /cli/, and the HTTP API and how to authenticate to it under /api/.

**Get started**

- [What is LangAlpha](https://docs.langalpha.ai/get-started/what-is-langalpha.md): LangAlpha is an open-source harness for AI agents that research markets, keep an investment thesis in a workspace and trade within limits you set.
- [Hosted or self-hosted](https://docs.langalpha.ai/get-started/hosted-or-self-hosted.md): Compare the hosted LangAlpha platform with a self-hosted install, covering sign-in, market data, price triggers, chat apps, models and operations.
- [Self-hosting quickstart](https://docs.langalpha.ai/get-started/self-hosting-quickstart.md): Run LangAlpha on your own machine with Docker. Clone the repository, answer the make config wizard, start the stack with make up and open the web app.

**Concepts**

- [How LangAlpha fits together](https://docs.langalpha.ai/concepts/overview.md): The LangAlpha hierarchy of user, computer, workspace, thread and turn, the two agent roles, and which data lives where and follows you across computers.
- [Computers](https://docs.langalpha.ai/concepts/computers.md): A computer is the machine your LangAlpha workspaces run on. How the primary computer, sizes, the shared disk, idle stop, always-on and moving workspaces work.
- [Sandboxes and SSH computers](https://docs.langalpha.ai/concepts/sandboxes-and-ssh.md): The four kinds of LangAlpha computer (Docker, Daytona, E2B and your own SSH machine), how to add a Linux server or Mac, Remote control, and what is sent to it.
- [Workspaces](https://docs.langalpha.ai/concepts/workspaces.md): A workspace is a folder on one of your computers with its own threads, files, notes, memory, skills and tools. How naming, layout, Home and trust work.
- [Threads and turns](https://docs.langalpha.ai/concepts/threads-and-turns.md): A thread is one conversation in a LangAlpha workspace and a turn is one run of the agent answering it. How steering, cancelling, approvals and compaction work.
- [Chief of Staff and Analysts](https://docs.langalpha.ai/concepts/chief-of-staff-and-analysts.md): LangAlpha runs one agent in two roles. The Analyst works inside a workspace. The Chief of Staff works from Home across workspaces and hands off deep work.
- [Files and what persists](https://docs.langalpha.ai/concepts/files.md): How LangAlpha backs up workspace files after every turn, what a stop, archive or rebuild keeps, and how uploads, downloads and server-held files work.
- [Memory, memos and scratchpad](https://docs.langalpha.ai/concepts/memory-memos-scratchpad.md): How LangAlpha remembers you (agent-written memory), grounds answers in your documents (memos) and keeps per-thread working files (scratchpad).
- [Skills](https://docs.langalpha.ai/concepts/skills.md): Skills are SKILL.md instruction folders the agent loads on demand. Learn the three tiers, slash commands, uploads and the 35 built-in skills.
- [Plugins, MCP servers and programmatic tool calling](https://docs.langalpha.ai/concepts/plugins-mcp-ptc.md): What plugins and MCP servers are, how to install and switch them on, and how programmatic tool calling keeps bulk data in the sandbox.
- [Models and your own keys](https://docs.langalpha.ai/concepts/models-and-keys.md): How to connect a model to LangAlpha with a Claude or ChatGPT sign-in, a coding plan, an API key or a local server, and tune reasoning and compaction.
- [Brokerages and orders](https://docs.langalpha.ai/concepts/brokerages-and-orders.md): Connect Robinhood, Interactive Brokers, moomoo or Webull, choose what the agent may do, and see how every order is approved once and run exactly once.
- [Automations, wakeups and background commands](https://docs.langalpha.ai/concepts/automations-wakeups-commands.md): Four ways LangAlpha works later: automations you set, wakeups the agent sets, background commands that report back, and workflows that fan out subagents.
- [Chat apps](https://docs.langalpha.ai/concepts/chat-apps.md): On the hosted platform, talk to LangAlpha from Slack, Discord, Telegram, Feishu and iMessage. How messages route, the commands, and how self-hosting differs.
- [Sharing](https://docs.langalpha.ai/concepts/sharing.md): Share a LangAlpha thread or a single file with a link anyone can open without signing in, what visitors can see, what is removed, and how to turn a link off.

**Compare**

- [Chief of Staff or Analyst?](https://docs.langalpha.ai/compare/chief-of-staff-or-analyst.md): Ask the Chief of Staff for quick answers and questions about past work. Open a workspace and use its Analyst for hands-on work you want to keep in one place.
- [Automation or wakeup?](https://docs.langalpha.ai/compare/automation-or-wakeup.md): Compare automations, wakeups, background commands and workflows in LangAlpha: who creates each, where it runs, how it reports back, and its limits.
- [Memory, memo or scratchpad?](https://docs.langalpha.ai/compare/memory-memo-or-scratchpad.md): Which of LangAlpha's three stores to use: memory for what the agent should always know, memos for documents it should cite, scratchpad for one thread's work.
- [Skill, plugin or MCP server?](https://docs.langalpha.ai/compare/skill-plugin-or-mcp-server.md): Choose between a skill (instructions), an MCP server (new tools) and a plugin (a package of both). Learn how they nest and when to write each one.
- [Which computer should I use?](https://docs.langalpha.ai/compare/which-computer.md): Compare Docker, Daytona, E2B, your own SSH machine and Mac Remote control for LangAlpha, and learn when a second computer is worth creating.

**Explore**

- [Write an initiation report](https://docs.langalpha.ai/explore/initiation-report.md): Ask LangAlpha for an initiation report on a stock, with research, an Excel model, a valuation and charts, delivered as a Word report, PDF or HTML page.
- [Prepare for earnings](https://docs.langalpha.ai/explore/earnings-preview.md): Ask LangAlpha for an earnings preview, a catalyst calendar and automations that run before each report, then a post-print update once the numbers are out.
- [Build valuation models](https://docs.langalpha.ai/explore/valuation-models.md): Ask LangAlpha for a DCF, a comps table, a three-statement model or a model audit, built as live Excel workbooks with a Cover sheet, a Checks sheet and sources.
- [Watch a stock and act on a price move](https://docs.langalpha.ai/explore/price-move-automation.md): Ask LangAlpha to watch a stock and run an analysis when its price crosses a level or moves by a percentage, as an automation or as a wakeup in a thread.
- [Review your portfolio](https://docs.langalpha.ai/explore/portfolio-review.md): Ask LangAlpha to check your holdings for concentration, exposure and risk against your investing profile, and keep it current with a weekly review.
- [Build dashboards and annotate charts](https://docs.langalpha.ai/explore/dashboards-and-charts.md): Ask LangAlpha for a chart in the chat, an HTML report, a live dashboard or drawings on a price chart, and see which output fits each request.
- [Get results in Slack and other chat apps](https://docs.langalpha.ai/explore/deliver-to-slack.md): Have LangAlpha send reports and automation results to Slack, Discord, Telegram, Feishu or iMessage, and see what a self-hosted install does instead.

**Best practices**

- [Structure your workspaces](https://docs.langalpha.ai/best-practices/structuring-workspaces.md): How to split research into workspaces and threads, when a separate computer helps, and how to keep a workspace rebuildable after a move or restore.
- [Delegate work well](https://docs.langalpha.ai/best-practices/when-to-delegate.md): When to hand work to subagents, workflows or a workspace Analyst, what each built-in subagent can do, and the limits on custom subagents and workflows.
- [Write your own skills](https://docs.langalpha.ai/best-practices/writing-skills.md): How to write a skill LangAlpha loads at the right time: SKILL.md format, slash command rules, upload limits, tiers, GitHub install and plugin packaging.
- [Get good research output](https://docs.langalpha.ai/best-practices/research-output.md): Practical ways to get sourced, decision-ready research from LangAlpha: give context, name the deliverable, check Sources, choose model effort and steer mid-run.

**CLI**

- [The LangAlpha CLI](https://docs.langalpha.ai/cli/overview.md): langalpha, or la for short, runs your threads, workspaces, computers and automations from a terminal, a script, or the agent inside a computer. How to install it and how its commands behave.
- [Signing in](https://docs.langalpha.ai/cli/signing-in.md): How the LangAlpha CLI picks a server and a credential, signs in through the browser, including on a remote machine with no browser, and where it keeps your sign-in.
- [Sign-in commands](https://docs.langalpha.ai/cli/auth.md): Reference for langalpha login, logout and whoami, the CLI commands that sign you in to a LangAlpha server, sign you out, and show who the server takes you for.
- [Computer commands](https://docs.langalpha.ai/cli/computers.md): Reference for langalpha computers list, add, start, stop and remove, the CLI commands that manage the machines your LangAlpha workspaces run on, SSH machines included.
- [Workspace commands](https://docs.langalpha.ai/cli/workspaces.md): Reference for langalpha workspaces list, create, archive and delete, the CLI commands that manage LangAlpha workspaces from a terminal or script.
- [Thread commands](https://docs.langalpha.ai/cli/threads.md): Reference for langalpha threads, the CLI commands that start, follow, answer, retry, cancel, archive and delete LangAlpha threads and their turns.
- [Automation commands](https://docs.langalpha.ai/cli/automations.md): Reference for langalpha automations list, create, edit, trigger, pause, resume and delete, the CLI commands that schedule LangAlpha's agent on a cron schedule or once.
- [Model commands](https://docs.langalpha.ai/cli/models.md): Reference for langalpha models list, the CLI command that lists the models you can pick for a turn or automation and who each one bills to.
- [Using the CLI inside a computer](https://docs.langalpha.ai/cli/inside-a-computer.md): Every LangAlpha computer has the CLI on the agent's command path with a token of its own. What the agent can do with it there, and what that token is never allowed to do.
- [Scripting recipes](https://docs.langalpha.ai/cli/scripting.md): Recipes for scripting the LangAlpha CLI. Start a thread and wait for the answer, follow a turn as JSON events, create a cron automation, answer an approval, and retry a failed turn.

**API**

- [HTTP API](https://docs.langalpha.ai/api/overview.md): An overview of LangAlpha's HTTP API. The base URL, JSON requests and errors, turns streamed as server-sent events, resuming a stream, and safe retries with a request key.
- [Authentication](https://docs.langalpha.ai/api/authentication.md): How callers outside the LangAlpha web app authenticate to its API. Bearer tokens from a browser sign-in, scopes, the CLI sign-in discovery route, and self-hosted servers with no sign-in.

## Documentation Sets

- [Abridged documentation](https://docs.langalpha.ai/llms-small.txt): a compact version of the documentation for LangAlpha, with non-essential content removed
- [Complete documentation](https://docs.langalpha.ai/llms-full.txt): the full documentation for LangAlpha

## Notes

- The complete documentation includes all content from the official documentation
- The content is automatically generated from the same source as the official documentation