Forge strategies. Trust only proof.
Forven is a local desktop lab for retail quant traders. Build, test, kill, and promote strategies through a walk-forward gauntlet before they touch live capital.
Local-first · your strategies and keys never leave your machine · bring your own LLM key
| Strategy | Stage | Status | Trades | OOS |
|---|---|---|---|---|
| S00731funding_skew_eth | candidate | pass | 64 | +1.3% |
| S00742liquidation_sweep_btc | gauntlet | fail | 156 | -0.6% |
| S00755basis_carry_sol | gauntlet | watch | 88 | +0.2% |
Sample lab snapshot for illustration — not real or projected returns.
A research process with hard gates.
Build the cohort
Collect strategy ideas, parameter sets, and agent-drafted variants in one local lab before anything graduates.
Run the gauntlet
Push each idea through screen, walk-forward gauntlet, candidate, and live-review stages with explicit gates.
Promote with evidence
Use out-of-sample metrics, audit trails, and paper-trade behavior to decide what survives and what gets retired.
Most strategies fail. Forven makes failure useful.
Fast filters remove fragile ideas before deeper testing.
Walk-forward windows test survival outside the fit period.
Paper trading and review catch behavior that backtests hide.
Only a small set earns live-routing consideration.
The point is not optimism.
The point is disciplined rejection. Forven helps you learn why an edge died before that lesson costs live capital.
Inspect the lab before you trust the output.
| ID | Strategy | Stage | Trades | OOS | Status |
|---|---|---|---|---|---|
| S00241 | rsi_mean_reversion_btc | live | 127 | +2.4% | pass |
| S00512 | vwap_reclaim_eth | candidate | 38 | +0.9% | pass |
| S00693 | volume_anomaly_sol | gauntlet | 212 | -1.1% | fail |
| S00718 | breakout_confirm_btc | gauntlet | 94 | +0.4% | watch |
Local by default
Strategies, data, and runs stay on your machine unless you choose to connect external services.
Bring your own keys
Use your own exchange and LLM keys. Forven does not need to resell model tokens to be useful.
Auditable gates
Every promotion has a stage, a metric trail, and a reason. No hidden signal feed, no black-box handwave.
Sample data for illustration — strategy names, metrics, and OOS figures are not real or projected returns.
Co-researchers, not co-pilots.
Agents are optional co-researchers included for everyone during beta. They can draft hypotheses, inspect failed runs, and explain drawdowns, but the gauntlet still decides what earns attention.
You bring your own LLM key for model calls. The lab, daemon, and agent layer are all part of the beta experience.
How the agent layer works →- Drafts hypothesesfrom natural-language research prompts
- Edits strategy codeagainst your actual repo, with diffs
- Inspects gauntlet resultsreasons about why edges died
- Writes post-mortemson live drawdowns and failed candidates
Start with the full beta.
Every Forven feature is included free during beta. Bring your own LLM key when you want agents to help draft, debug, and review.
The download is ungated — install first. A free account links the app to your device and keeps your beta access in sync; you can create one any time after installing.
- Local lab and daemon are free during beta.
- Agent features are included for beta users who bring their own LLM key.
- Installer is available for Windows now; macOS support follows the same desktop path.