Lists (2)
Stars
Input-Dependent Gating Liquid Mixer and Length-Adaptive Attention for Fast, Long-Context Bidirectional Encoders
ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
Safe default settings for Claude Code with agentic multi-model architecture
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
音声ファイルからLive2Dモデルの口パク・表情・ジェスチャを自動演出するブラウザアプリ。Whisper文字起こし＋Claude感情解析対応。
Open format and AI-assisted toolkit for versioned, safety-aware work instructions
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
An agentic skills framework & software development methodology that works.
A light and Elegant theme for Slidev
Pipeline for training a LoRA adapter that writes in a specific person's voice — corpus growth + penetration strategy, systemd-managed continuous training on a single GPU
ナルエビが乗り移ったStackChan - NullEvi possesses StackChan (レリクスシステム)
Orchestrate local evi agent runtimes and shared memory
MCP gateway for StackChan (xiaozhi-esp32): bridge any MCP client to a CoreS3 + servo + camera robot
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
Int4-quantized FLUX.2-klein inference runtime (GemLite / fused Triton / eager backends)
A straightforward method for training your LLM, from downloading data to generating text.
Unofficial Python API and agentic skill for Google Gemini Notebook. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents…
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies