LangAlpha docs
Research the market. Build the thesis. Trade within your rules.
Open-source AI agents that research the market, build the thesis, and trade your own brokerage account within the permissions you set. Hosted at langalpha.ai or on your own machine.

Start here
New to LangAlpha
- 01What is LangAlphaLangAlpha is an open-source harness for AI agents that research markets, keep an investment thesis in a workspace and trade within limits you set.
- 02Hosted or self-hostedCompare the hosted LangAlpha platform with a self-hosted install, covering sign-in, market data, price triggers, chat apps, models and operations.
- 03Self-hosting quickstartRun 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.
- 04How LangAlpha fits togetherThe LangAlpha hierarchy of user, computer, workspace, thread and turn, the two agent roles, and which data lives where and follows you across computers.
What's new
Recently in LangAlpha
- LangAlpha in your terminalLangAlpha has a command line, langalpha (la for short). Sign in through your browser, then start and follow threads, answer approvals, and manage workspaces, computers and automations from a terminal or a script. Install the release candidate with npm install -g langalpha@next.
- Claude Code on your own plan and computersPreview: Claude Haiku, Sonnet and Opus 5.5 can run through Claude Code on your own Claude plan. A thread in a workspace on your own computer runs Claude Code on that machine, signed in per computer from Settings. Turn it on with features.claude_code_runtime.enabled: true in config.yaml, then in Settings under Experiments.
- Connect models the way you pay for themOne list connects a ChatGPT, Claude or Grok sign-in, a provider key, a coding plan (Kimi, GLM, MiniMax or OpenCode Go), a local server or your own endpoint, and each connection reads its model list for you. The model picker has search and Favorites, and tags each model with the key or plan it runs on.
Concepts
The parts and how they connect
Computers, workspaces, threads and the agents that work in them.
- ComputersA 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 computersThe 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.
- WorkspacesA 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 turnsA 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 AnalystsLangAlpha 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 persistsHow 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 scratchpadHow LangAlpha remembers you (agent-written memory), grounds answers in your documents (memos) and keeps per-thread working files (scratchpad).
- SkillsSkills 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 callingWhat 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 keysHow 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.
- Claude Code modeRun your Claude threads through Claude Code on your Claude plan. How and where it runs, how to set it up, its statuses and moving from the Claude sign-in.
- Brokerages and ordersConnect 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 commandsFour ways LangAlpha works later: automations you set, wakeups the agent sets, background commands that report back, and workflows that fan out subagents.
- Chat appsOn the hosted platform, talk to LangAlpha from Slack, Discord, Telegram, Feishu and iMessage. How messages route, the commands, and how self-hosting differs.
- SharingShare 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
Questions people ask
Similar choices side by side, and when to pick which.
- Chief of Staff or Analyst?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?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?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?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?Compare Docker, Daytona, E2B, your own SSH machine and Mac Remote control for LangAlpha, and learn when a second computer is worth creating.
Explore
What you can do
Real requests, what the agent does with them, and what comes back.
- Write an initiation reportAsk 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 earningsAsk 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 modelsAsk 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 moveAsk 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 portfolioAsk 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 chartsAsk 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 appsHave LangAlpha send reports and automation results to Slack, Discord, Telegram, Feishu or iMessage, and see what a self-hosted install does instead.
Best practices
Get better results
How to structure workspaces, hand off work, write skills and get output you can use.
- Structure your workspacesHow 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 wellWhen 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 skillsHow 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 outputPractical ways to get sourced, decision-ready research from LangAlpha: give context, name the deliverable, check Sources, choose model effort and steer mid-run.
Command line and API
Drive it from a terminal or a script
langalpha, or la for short, runs threads, workspaces, computers and automations against the same server the web app talks to.
For agents
Every page is also served as Markdown at its URL plus .md, and the whole site is indexed for language models.