openInvest
Repository-documented investment research framework combining separated analyst roles, cross-challenge and recorded decisions with a backtesting harness. Listed for studying decision processes, not as investment advice or a profitable strategy.
Workflow level n/a Source: Repository-documented Outcome: Not empirically evaluated here
Research applicability
Supports study of AI-assisted financial decision workflows, reasoning audits and backtest methodology. Actual predictive validity and bias control are not established by this review.
Getting started
Editorial, untested guidance: inspect the README, backtest limitations and configuration documentation first; use synthetic holdings in an isolated environment and have a researcher audit leakage and transaction assumptions before evaluating any strategy.
Maintenance
Mutable current README inspected; ongoing maintenance not independently assessed.
License
Not audited; inspect current license and dependency/data rights before reuse.
Workflow & human oversight
Resource-level automation unspecified. Researchers approve objectives and inspect outputs; documentation is not an executed workflow.
Workflow level is not an evidence score; higher is not better evidence.
Approach
The README describes macro, quantitative, risk and CIO roles, followed by rebuttal and persistent verdicts; it states that final action remains with a human and that no auto-order execution occurs.
Limitations
README-only source review by an AI editorial agent; no implementation execution, independent outcome evaluation, security audit or full linked-document review. HEAD is mutable; saved content and hashes preserve the inspected version. README contains negative author-reported tests and explicitly disclaims alpha; no quantitative outcome is included in the listing. Its cutoff explanation is not endorsed: historical backtesting can still suffer model-training leakage and requires independent analysis. Public state commits may disclose private finances; do not follow automatic deployment instructions without privacy review.
Reproducibility
Fresh README and identity metadata checked; no software or outcomes reproduced.
Adoption requirements
Python environment, agent or MCP/CLI client, market data and protected portfolio state; automated modes may require provider credentials. Verify data rights, model costs and permissions before adoption.
Comments
No comments yet.
Add a comment
Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.