65,764 visible repositories in the index
721–744 of 887 · Most stars
Oracle3: open-source trading engine and MCP server for prediction markets. Finds fee-adjusted no-arbitrage violations across related event contracts and trades them live on Kalshi, Polymarket and Solana, or on paper, under pre-trade risk limits. 13 MCP tools, JSON CLI, agent skills, 600+ tests.
The repository host gives no description.
TranslatedA completion of the landscape-format full character reference sheet based on the ZipZipPipe (胖次狐, "Panties Fox") AI girl character art: it is broken down into separate assets for three-view turnarounds / expressions / outfits / props, the side and back views are inferred and completed, and everything is stitched together at native pixels 1:1. CC BY-NC-SA 4.0, non-commercial.
HTML minifier for Python frameworks (not only Django, despite the name).
Official repository for MemT-1.0
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.
TranslatedA basic tutorial for getting started with AI Agents from zero background. It is not just a tutorial but also an Agent that can run locally: read and write files, execute commands, MCP, long-term memory, with a built-in web interface to see every step clearly. Starting from a minimal 100-line loop, each lesson adds one capability, and in the end it breaks down mainstream Agents such as Claude Code and Codex
Corpus legislativo brasileiro em larga escala e modelo Transformer causal treinado do zero em PyTorch puro.
Malcolm is a powerful, easily deployable network traffic analysis tool suite for full packet capture artifacts (PCAP files), Zeek logs and Suricata alerts.
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
🔥🔥 The extremely fast inference engine for decision model
Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
STE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical English), the method Andrej Karpathy shared.
A py.test plugin to validate Jupyter notebooks
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
RELATE is an Environment for Learning And TEaching
AI Agent Identity and Access Management and Inference Firewall
🧱 Experimental library for building inference engines
TranslatedAn AI avatar for real-time voice/text conversations with idols from "The iDOLM@STER Shiny Colors": original Japanese voice + Chinese subtitles, recalling the original story, memory shared across characters; supports Google/GitHub login and bring-your-own key, one-command deployment with Docker Compose (inspired by LAPLACE Eidolon)