Agent-native investment research workspace for evidence-tracked theses.
Turn multi-source material into traceable, reviewable, and refreshable investment judgments.
Mira is an AI investment research system designed for agents and research users. It helps you manage equities, earnings, macro, and portfolio reviews through explicit source-backed claims and time boundaries.
The system constrains AI model output into evidence-tracked, refreshable, and falsifiable research work. It structures everything from earnings reports and SEC filings to ETF analysis and portfolio position reviews.
It suits investment professionals, venture capitalists, and equity researchers who want rigorous, auditable AI workflows. It does not suit casual traders looking for a trade bot, automated portfolio manager, or instant market-data daemon.
Separates facts, claims, assumptions, and opinions with clear source trails.
Directs queries through specific loops for research, monitoring, and briefing.
Enforces staleness policies so outdated conclusions are flagged before reuse.
Brings in public APIs and user files without bypassing source and calculation controls.
Mira is free under its open-source license. The only cost is running it yourself within your supported code agent environment.
880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
No, Mira is strictly a research workflow design and documentation system, not a trade bot or portfolio manager.
You can update the workspace safely by running the scripts/mira_update.sh script.
See Zekai first in Google