flux/open-source-coding-agent
github.com
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation. - tensorzero/tensorzero
github.com
A list of free LLM inference resources accessible via API. - cheahjs/free-llm-api-resources
github.com
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x - ag2ai/ag2
github.com
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps. I mainly use it as an xcodebuild wrapper to save context. - conorluddy/ios-...
github.com
Wrap Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Qwen Code, iFlow as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 2.5 Pro, GPT 5, Claude, Qwe...
github.com
QVAC - Local AI SDK and libraries for building private, cross-platform, peer-to-peer AI applications. Run LLMs, speech-to-text, translation, and more locally on Linux, macOS, Windows, Android, and ...
github.com
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers....
github.com
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk - lemonade-sdk/lemonade
firethering.com
IBM just released Granite 4.1, a family of open source language models built specifically for enterprise use. Three sizes, Apache 2.0 licensed and trained on 15 trillion tokens with a level of pipeline obsession that’s worth understanding. But there’s one result in the benchmarks I keep coming back to. The 8B model. Dense architecture, no MoE tricks, no extended reasoning chains. It matches or beats Granite 4.0-H-Small across basically every benchmark they ran. That older model has 32B parameters with 9B active. This one has 8 billion. Full stop. That result is either very impressive or it means the old model was underbuilt. Probably both. Here’s how they built it, what the numbers actually say, and whether any of it matters for your use case.
github.com
Find, benchmark and install in CLI 200+ FREE coding LLM models across 20+ providers in real time - vava-nessa/free-coding-models