⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
GitHub repository with 5,382 stars and 511 forks.
Language: Rust
Topics: llama, llamacpp, llm-inference, ollama-api, command-line-tool, gguf, inference-server, local-ai, machine-learning, api-server
2026-06-10: 5,382 stars and 511 forks.
Camelid: a Rust-native local inference backend with evidence-gated model compatibility.
GitHub repository with 67 stars and 10 forks.
Trending score: 1.10; stars gained: +2; forks gained: +0.
Language: Rust
Topics: apple-silicon, gguf, inference, llama, llm, local-first
Instant, controllable, local pre-trained AI models in Rust
GitHub repository with 2,203 stars and 129 forks.
Trending score: 0.92; stars gained: +3; forks gained: -1.
Language: Rust
Topics: ai, llm, rust, llamacpp, kalosm, candle
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
GitHub repository with 99,563 stars and 6,565 forks.
Trending score: 5.90; stars gained: +1,878; forks gained: +140.
Language: Rust
Topics: ai-tools, claude-code, desktop-app, open-source, rust, tauri
An enhanced tool for CodexApp, striving to make Codex better to use and more comfortable 一个CodexApp的增强工具，努力让Codex变得更好用更舒服
GitHub repository with 17,956 stars and 1,125 forks.
Trending score: 5.29; stars gained: +841; forks gained: +61.
Language: Rust
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
GitHub repository with 73,524 stars and 9,811 forks.
Trending score: 4.76; stars gained: +605; forks gained: +70.
Language: Rust
Topics: awesome, claude, densepose, esp32, firmware, home-assistant
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
GitHub repository with 49,142 stars and 5,187 forks.
Trending score: 4.48; stars gained: +331; forks gained: +50.
Language: Rust
Topics: acp, ai, ai-agents, mcp
15MB, lightweight, cross-platform database client. Supports MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, ClickHouse, SQL Server and more.15MB，轻量级跨平台数据库客户端、数据库管理工具。支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、DuckDB、ClickHouse、SQL Server 等。
GitHub repository with 5,170 stars and 422 forks.
Trending score: 4.36; stars gained: +280; forks gained: +26.
Language: Rust
Topics: clickhouse, database, database-client, database-management, gui, mongodb
The headless browser for AI agents and web scraping
GitHub repository with 15,600 stars and 1,057 forks.
Trending score: 4.30; stars gained: +354; forks gained: +37.
Language: Rust
Topics: antidetect, antidetect-browser, browser, browser-automation, cdp, headless
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
GitHub repository with 34,573 stars and 2,373 forks.
Trending score: 3.94; stars gained: +271; forks gained: +18.
Language: Python
Topics: agent, ai, chatbot, chatgpt, discord, docker
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 82,746 stars and 18,006 forks.
Trending score: 3.88; stars gained: +133; forks gained: +41.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
GitHub repository with 66,398 stars and 5,945 forks.
Trending score: 3.69; stars gained: +155; forks gained: +11.
Language: Python
Topics: agent, deepseek, fine-tuning, gemma, gemma3, gpt-oss
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
GitHub repository with 72,123 stars and 8,825 forks.
Trending score: 3.26; stars gained: +62; forks gained: +12.
Language: Python
Topics: fine-tuning, llama, llm, peft, transformers, rlhf
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
GitHub repository with 26,229 stars and 1,365 forks.
Trending score: 3.26; stars gained: +103; forks gained: +5.
Language: TypeScript
Topics: ai, anthropic, artificial-intelligence, chatbot, chatgpt, claude
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
GitHub repository with 14,491 stars and 1,475 forks.
Trending score: 3.05; stars gained: +28; forks gained: +8.
Language: Python
Topics: deepseek-r1, embedding, grpo, internvl, liger, llama