Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
Text preprocessing, representation and visualization from zero to hero.
- text-preprocessing
- text-representation
- text-visualization
- nlp
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Claude code for everything except coding
The repository host gives no description.
Read and analyze SEC EDGAR filings in Python. 10-K, 8-K, XBRL financials, Form 3/4/5, 13F, ADV — clean API, well-typed, MIT-licensed.
- 10-k
- 10-q
- balance-sheet
- edgar
Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.
Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets.
Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码,读不动?用 ~5000 行 TypeScript / Python 从零复现核心架构,11 章分步教程带你理解 coding agent 精髓
A Python library for reading and writing PDF, powered by QPDF
A Pythonic framework to simplify AI service building
Social reading and reviewing, decentralized with ActivityPub
Images to inference with no labeling (use foundation models to train supervised models).
A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
ThetaGang is an IBKR bot for collecting money
A command-line app for downloading Apple Music songs, albums, playlists, music videos, and uploaded videos.
- apple-music
- apple-music-downloader
- aac
- downloader
💰 Cryptocurrency Trading Bot for Binance (Experimental)
基金投资管理回测引擎
- finance
- quantitative-trading
- backtest
- investment
Apache Ossie, industry wide specification effort to standardize how we exchange semantic metadata across analytics, AI and BI platforms, providing a vendor neutral, single source of truth for semantic data
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.
YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
- low-precision
- pruning
- sparsity
- auto-tuning
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp