#
ENJA

agents-starter

limitless-labs-group/agents-starter

An autonomous trading agent framework designed for prediction markets on Base, featuring built-in strategies like cross-venue market making, oracle arbitrage, and certainty closing.

7 6No licenseUpdated 2026-07-01

Overview

The Agents Starter repository provides a complete toolkit for AI agents to autonomously operate real-money trading strategies on the Limitless Exchange and Polymarket. It includes comprehensive safety protocols, a guided initialization bootstrap, multiple trading strategies ranging from delta-neutral market making to oracle arbitrage, and an agent-friendly operating manual that avoids handling private keys directly.

Capabilities

  • Autonomous trading loop execution with dry-run safety defaults
  • Guided credential and wallet setup bootstrap
  • Cross-venue risk management, delta calculation, and position tracking
  • Integration with Limitless Exchange API and Polymarket clob-client
  • Real-time monitoring and status emission for operator control panels

Best for

Setting up and running automated cross-market market making between Limitless Exchange and Polymarket, Executing oracle-based arbitrage using Pyth Network feeds against prediction market prices, Running automated certainty-closing strategies to trade near-resolution prediction market favorites

Works with

Claude CodeCursorGitHub CopilotCodexChatGPTGemini CLIOpenCode
Evoa Score breakdown= Σ (score × weight)
61
Task usefulness20%88 → +17.6

実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%85 → +12.8

リポジトリがどれだけ活発に保守されているか。 GitHub 最終push日時の新しさ

Documentation12%35 → +4.2

ドキュメントの充実度・分かりやすさ。 README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 AIによる独自性判定

Popularity8%33 → +2.6

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%100 → +5.0

対応AIエージェントの広さ。 AIによる対応エージェント判定

Weighted total71.7 / 100

ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

The skill enforces a strict security contract where the operator's private key remains strictly outside the AI agent's context and is never read or echoed by scripts. All live trading starts in a risk-free dry run mode and requires explicit human confirmation before spending gas or going live.

Categories

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.