#3636th of 80 in Agent platformsFor finance and business, trading, stocks and crypto, finance and accounting
openalice
Local workspace that connects coding agents to market data and brokers
- Stars
- 7.4k
- License
- AGPL-3.0
- Last commit
- Nov 2026
- Last release
- Sep 2026
- Language
- TypeScript
3,582 on 20 Apr 20267,443 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
OpenAlice is a desktop and CLI app that lets agents such as Claude Code, Codex, OpenCode and Pi use market data, fundamentals and news tools inside Git-backed research Workspaces. It adds scheduled recurring tasks (Issues), an Inbox for reports, and a Unified Trading Account layer where agents stage trades that the user approves. State is stored under ~/.openalice.
Who it is for: Self-directed traders and researchers who already use coding agents
Strengths
- Reuses existing agent CLIs (Claude Code, Codex, OpenCode, Pi) instead of a custom agent loop
- Workspaces are plain directories and Git repos you can inspect and back up
- Scheduled Issues rerun research using the Workspace's agent and context
- Trade proposals are staged and need human approval before execution
Weaknesses
- Trading execution is marked beta; README advises simulator or paper accounts first
- Source installs require a host agent CLI plus model credentials or login
- Available market data depends on the providers you configure
- Desktop builds listed only for macOS and Windows; no Docker image detected
What it needs
- no GPU
- Needs Host agent CLI (Claude Code, Codex, OpenCode, Pi), Model credentials or login, Market data providers, Broker account (optional), pnpm (source install)
- Models: Via host agents: Claude Code, Codex, OpenCode, Pi, Oh My Pi
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Quick answers
Is openalice open source?
Yes. Its code is on GitHub under the AGPL-3.0 license.
Does openalice need a GPU?
No, it runs without one.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |