User repository on GitHub
Polymarket trading bot driven by Jev (TypeSafe AI) via OpenRouter
- Forks
- 4
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Agents & MCP
Jevymarket
Polymarket bot that pairs a web-search researcher brief with Jev pricing, trading only where Jev probability clears the order book by a set edge.
- Stars
- 14
- Language
- Python
- License
- MIT
- Published by
- Community
- Author
- markusbug
- Last verified
- Oct 2026
About this project
A Polymarket trading bot whose pricing oracle is Jev, TypeSafe AI's "System One" decision model, called through OpenRouter's Decisions API.
Quoted from the project's README. Read the full README.
Used inJev for Software & DevTools
- Languages
- Python
Highlights
- Gamma scan filters by liquidity, volume, time to resolution, spread, and price band.
- Researcher brief holds dated facts, for and against considerations, and sources as JSON.
- Jev state precomputes days to resolution because date math is a known weak spot.
- GTC limit orders with per-trade, exposure, count, and one-position caps plus SQLite logging.
Watch out
Experimental software that places real orders with real money; positions are held to resolution with no exits, and edge estimates do not equal profit. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
Jev has no browsing and handles news poorly alone, so a chat researcher with web search writes a dated, sourced evidence brief into the state. Odds sites are excluded so market prices never leak in as evidence.
One call asks resolves_yes for P(YES), answerable for information sufficiency, and clarity for resolution objectivity. Pure code then gates on answerable, clarity, price band, edge over ask, and fractional Kelly sizing.
Scan, research, decide, and dry-run commands evaluate and log without ordering, and run is live by default. Start with decide and run --dry-run, watch stats and calibration, then trade small with caps in place.
Longshot bias can fake edge on very cheap contracts so the price band is the guard, taker fills and stale briefs eat into thresholds, and the decisions endpoint is beta so re-run jev-test after version bumps.
A dated, sourced evidence brief returned as strict JSON: key facts with dates, the latest development, considerations for and against YES, and sources, with odds sites excluded so Jev never sees market prices as evidence.
It skips unless answerable and clear, only buys contracts priced inside the configured band, requires the edge over the best ask to meet MIN_EDGE, and sizes with fractional Kelly under hard caps.
A per-trade dollar cap, a total open exposure in dollars, a maximum number of trades per run, and one position per market, placing a GTC limit order at the best ask only if every cap passes.
More Jev resources like this
25GitHub stars
Agent-oriented playbook for using Jev as a cheap, fast decision layer that triages, classifies, scores, and gates work before expensive browser, research, retry, or subagent steps.
Jev Agents & MCP#community#awesomejev#catalog-import
Community
Bodila51/muse-jev-playbookPython
Bodila51/muse-jev-playbookPython23GitHub stars
Coding-agent plugin that routes prompt classification, subagent tiering, edit rule checks, and fast Jev-backed compaction through small typed judgments.
Jev Agents & MCP#community#jevbest#catalog-import
Community
0x7067/claude-jevTypeScript
0x7067/claude-jevTypeScript14GitHub stars
Opt-in Hermes plugin that routes each turn to one skill: a wide Jev Choice plus request checks gate a narrow fits round, injecting a single ignorable hint line.
Jev Agents & MCP#community#jevbest#catalog-import
5GitHub stars
CLI that routes a task to one specialist skill from a Tink library using TypeSafe Jev, verifies the winner with tink mount, then prints it inline or as a mounted path.
Jev Agents & MCP#community#awesomejev#catalog-import
Community
jon-devlapaz/tink-routePython
jon-devlapaz/tink-routePython9GitHub stars
Hermes Agent plugin exposing Jev as four coding-workflow tools for parallel judgments, binary checks, option routing and rubric scoring, with a bundled question-design skill.
Jev Agents & MCP#community#jevbest#catalog-import
Community
ajensenwaud/hermes-jev-pluginPython
ajensenwaud/hermes-jev-pluginPython6GitHub stars
LangChain deepagents middleware that replaces SkillsMiddleware with per-turn judging, loading only the SKILL.md files a turn needs so large catalogs stay out of the prompt.
Jev Agents & MCP#community#jevbest#catalog-import
From the Jev community
Posts from builders shipping with Jev right now.