Trending Repos

Passkey-first authentication built in Rust on SableDB.

Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI alternative (MIT).

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.

The fast Usenet downloader. One self-contained executable: line-rate downloads, one-pass verify and extract, poster wall, built-in indexer. Speaks the SABnzbd and NZBGet APIs, so Sonarr and Radarr connect unmodified

CCswitch的全面升级，支持官方订阅和第三方模型混用，自动路由，支持v2subagent使用第三方模型

Distributed, peer-to-peer, decentralized network for LLM inference — peers seed & leech completions, metered by BitTorrent-protocol-style upload/download ratios. OpenAI-compatible · Rust · libp2p.

Distributed peer-to-peer LLM inference. Your prompt never leaves your device in clear text.

Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-checked by an SMT solver (cvc5), every decision independently verifiable offline. Pure Rust.

Performance-first local AI for Apple Silicon. Run LLMs and vision-language models beyond RAM limits with adaptive RAM + SSD streaming.

Verification-native coding agent harness in Rust: isolated edits, evidence receipts, durable traces, and model portability.

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

Instant file-search engine for Windows NTFS. A fast, open-source alternative to voidtools Everything.