55,140 visible repositories in the index
1–24 of 28 · 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.
NocoBase is the open-source platform for building, running, and evolving business systems with AI. Agents write the code and do the work, NocoBase provides the foundation and governance, and people make the decisions.
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
Architecture decision record (ADR) examples for software planning, IT leadership, and template documentation
One shared memory for every coding agent on your team. Claude Code, Cursor and Codex get a map of your code and your team's past decisions, so they pick up where you left off.
A collection of inspiring resources related to engineering management and tech leadership
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Log analyser / visualiser for Java HotSpot JIT compiler. Inspect inlining decisions, hot methods, bytecode, and assembly. View results in the JavaFX user interface.
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.
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.
A self-hosted dashboard for CrowdSec: investigate alerts, manage decisions, monitor runtime metrics, and send notifications from one responsive UI.
Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.
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.
TranslatedA mobile web app where the hamster Mugi (むぎ) practices Japanese conversation with you one-on-one. Core idea: the LLM outputs structured replies using a JSON Schema, with the Japanese lines and the Chinese tips in separate fields, and the frontend uses partial JSON parsing to display the reply as it streams in; prompt caching and voice caching are maintained even during long chats. Kanji readings are annotated by the LLM, and any that it misses are filled in by kuromoji on the server side. Corrections are automatically saved into a tips notebook, so you can practice speaking until you have mastered them. For voice, you can choose local VOICEVOX or cloud Google/Azure, and the keys stay only on the local server. Developed in collaboration with Claude Code (Opus 5.5); originally for personal use, it was released as open source with a brand-new git history that contains no personal data or third-party assets. Records of each decision are in docs/decisions/.