Starred repositories
Repair malformed JSON from LLMs, APIs, logs, and user input in Python.
Multi-agent AI coding orchestration system designed to drive successful coding outcomes with a high level of transparency (think more light-factory than dark-factory).
AI watermark remover. CLI and Python library to strip visible and invisible AI watermarks (Gemini / Nano Banana sparkle, SynthID) and provenance metadata (C2PA, EXIF, IPTC) from images.
A Jellyfin plugin that bridges Jellyfin with Jellyseerr for seamless show discovery and download requests.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Monoscope lets you ingest and explore your logs, traces and metrics. We store these in S3 compatible buckets. Query in natural language via LLMs.
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
An open source multi-tool for exploring and publishing data
Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
A TDD-driven iterative feedback loop for software development. 16 cohesive Claude Code skills walk an idea from brainstorm → plan → execute → iterate, with checkpoints throughout.
Official inference framework for 1-bit LLMs
Desktop app to manage markdown knowledge bases
Lightweight Standalone DMARC and SMTP TLS Report Viewer with IMAP Client
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Adaptive Test-time Learning and Autonomous Specialization
A path query language for JSON, YAML, TOML, and other serialization formats.
The design language that makes your AI harness better at design.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command li…
Go with your own intelligence - Go applications that directly integrate llama.cpp for local inference using hardware acceleration.