Multi-agent LLM investment research assistant (paper/backtest only)
Jev ecosystem projects — page 175
4209 repositories with documented relationships and source evidence.
AIエージェントとの共創で学びを積む
Loopback gateway for Claude Code or OpenCode: automatic Anthropic → GLM → DeepSeek failover, breaker-driven, plus optional per-call model routing by Jev (TypeSafe System One) — capability-first across all three providers — with manual pinning, control UI and CLI
Mailbox cleanup CLI with AI — trash/move/label/route mail using Jev or chat model
Imperial/Metric conversion for Chrome. Smart detection with Jev.
Durable orchestration, delegation, evidence, evaluation, review, and recovery for coding-agent workflows.
Personal extensions for the Pi harness.
ai design system
Territory intelligence for a NetSuite AE: Jev (TypeSafe) interprets company evidence and guides research; Claude powers chat and cited account stories. Next.js + Supabase + Vercel.
A small, fast Go TUI for chatting with your starred GitHub repositories. It downloads your stars, stores structured metadata + READMEs in SQLite, creates embeddings, and runs a local RAG-style chat so you can ask things like *“I’m building a Go OAuth server—what libraries do I have starred?”*.
面向银行业监管制度与统计报表的可信 RAG 问答系统 — 第五届中国研究生金融科技创新大赛
Production-ready examples for consuming the AlgoVault Verifiable-Signal v1.0 spec across downstream execution platforms.
Curated Pi coding agent configuration with Jev compaction, LSP, subagents, plan mode, safety tools, and automatic updates.
Train a compact model to pick one option from a changing list in a single pass, no autoregressive generation needed.
LLM GATEWAY
Collection of custom skills for Claude Code.
MxN CAD pattern generator and parallel alignment tool