An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
- ai
- amd-gpu
- apple-silicon
- asr
97,836 visible repositories in the index
49–72 of 145 · Most stars
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
AdalFlow: The library to build & auto-optimize LLM applications.
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
Task-Aware Agent-driven Prompt Optimization Framework
External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.
Modern, secure, portable, multiprotocol bootloader and boot manager.
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
Local-first desktop widget for tracking token usage, costs, limits, and session activity across 54+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, OpenClaw, and more—with multi-device sync.
OpenDeepWiki is the open-source version of the DeepWiki project, aiming to provide a powerful knowledge management and collaboration platform. The project is mainly developed using C# and TypeScript, supporting modular design, and is easy to expand and customize.
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
All-in-one AI desktop app: one-click install for Claude Code, Codex CLI, DeepSeek and more, manage AI accounts and quotas, smart model routing with auto-failover, voice input, and run local LLMs. Bonus: a Token Pet that grows as you use AI.
Hit your Claude Code usage limit? Keep going free and offline on a local model: Qwen 3.8, Gemma 4, and Qwen 4 the day it ships. Runs on Apple Silicon Macs (MLX), Linux and Windows (llama.cpp) with no API key. Your code stays home.
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
TokenSpeed is a speed-of-light LLM inference engine.
Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time
Reference implementation for DPO (Direct Preference Optimization)
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.