55,140 visible repositories in the index
1–13 of 13 · Most stars
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
Translated斑海豹 (Spotted Seal) — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions.
Learn a codebase by re-deriving its design decisions yourself. A Claude Code skill.
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
Laya typed decisions on Linux x86_64 via ONNX Runtime
Agent skills for Codex and Claude Code that preserve project context, decisions and next steps across AI sessions in plain Markdown.
AI-assisted Windows and Chrome GUI delegation for Codex: task contracts, local execution, Jev semantic decisions, recovery and outcome verification.
JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.
Forecast what will happen, including outcomes of your decisions.