A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.
GitHub repository with 1,320 stars and 221 forks.
Language: C++
Topics: deepseek, inference, inference-engine, llm-inference, qwen, large-language-models, glm
2026-06-05: 1,320 stars and 221 forks.
:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.
GitHub repository with 1,494 stars and 480 forks.
Trending score: 1.82; stars gained: +7; forks gained: +5.
Language: C++
Topics: accelerator, ai, cuda, deepseek, gpu, img-gen
Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
GitHub repository with 1,429 stars and 98 forks.
Trending score: 1.04; stars gained: +1; forks gained: +0.
Language: C++
Topics: amd, deepseek, llama, llm, npu
LLM inference in C/C++
GitHub repository with 114,701 stars and 19,193 forks.
Trending score: 4.40; stars gained: +304; forks gained: +99.
Language: C++
Topics: ggml
DuckDB is an analytical in-process SQL database management system
GitHub repository with 38,618 stars and 3,299 forks.
Trending score: 3.50; stars gained: +40; forks gained: +6.
Language: C++
Topics: analytics, database, embedded-database, olap, sql
Community maintained hardware plugin for vLLM on Ascend
GitHub repository with 2,198 stars and 1,347 forks.
Trending score: 3.25; stars gained: +16; forks gained: +22.
Language: C++
Topics: ascend, inference, llm, llm-serving, llmops, mlops
:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS
GitHub repository with 121,541 stars and 17,235 forks.
Trending score: 3.02; stars gained: +16; forks gained: +2.
Language: C++
Topics: c-plus-plus, chrome, css, electron, html, javascript
ClickHouse® is a real-time analytics database management system
GitHub repository with 47,826 stars and 8,467 forks.
Trending score: 2.96; stars gained: +53; forks gained: +10.
Language: C++
Topics: ai, analytics, big-data, clickhouse, cloud-native, cpp
Truly independent web browser
GitHub repository with 63,755 stars and 3,075 forks.
Trending score: 2.89; stars gained: +52; forks gained: +5.
Language: C++
Topics: browser, browser-engine
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
GitHub repository with 18,191 stars and 1,083 forks.
Trending score: 5.71; stars gained: +1,388; forks gained: +87.
Language: Go
Topics: agent, agent-framework, ai-agent, ai-coding, cli, coding-agent
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
GitHub repository with 16,362 stars and 2,458 forks.
Trending score: 5.17; stars gained: +581; forks gained: +85.
Language: JavaScript
Topics: claude-code, cursor, ai-agents, ai-gateway, anthropic, chatgpt
DeepSeek + MiMo coding agent in terminal
GitHub repository with 37,102 stars and 3,192 forks.
Trending score: 4.80; stars gained: +393; forks gained: +32.
Language: Rust
Topics: cli, deepseek, llm, rust, terminal, tui
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
GitHub repository with 78,210 stars and 15,374 forks.
Trending score: 4.03; stars gained: +79; forks gained: +2.
Language: TypeScript
Topics: agent, agent-collaboration, agent-harness, ai, cao, chatgpt
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
GitHub repository with 173,212 stars and 16,447 forks.
Trending score: 3.96; stars gained: +222; forks gained: +40.
Language: Go
Topics: deepseek, gemma, gemma3, glm, go, golang
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 81,978 stars and 17,668 forks.
Trending score: 3.75; stars gained: +79; forks gained: +46.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt