Luce-Org/lucebox 2,953
llm-as-a-verifier/llm-as-a-verifier 3,342
LLM-as-a-Verifier: pairwise scoring for agent trajectories, and where it stops being free
latitude-dev/latitude-llm 4,740
Latitude: Trace-Level Observability That Hands Failures to Your Coding Agent
langfengQ/verl-agent 2,414
verl-agent: Step-Independent Rollouts for Long-Horizon Agent RL
kyutai-labs/unmute 1,521
Unmute: Kyutai's Websocket Bridge Between Text LLMs and Real-Time Speech
KouriChat/KouriChat 3,299
KouriChat 1.5: an LLM companion bot that talks through OneBot, not Tencent apps
karthink/gptel 3,552
gptel: an LLM client that lives inside your Emacs buffers
jax-ml/scaling-book 1,503
jax-ml/scaling-book: A Jekyll Book About TPU Scaling, Not a Library
jamesob/local-llm 1,869
jamesob/local-llm: a hardware build log for running 594B models on four RTX PRO 6000s
itayinbarr/little-coder 2,700
little-coder: a pi-based agent harness tuned for small local models
intel/neural-compressor 2,713
Intel Neural Compressor: a quantization layer that sits on PyTorch, TensorFlow and JAX
ianarawjo/ChainForge 3,034
ChainForge: A Visual Flow Editor for Comparing Prompts Across LLM Providers
huohuoer/wechat-cli 2,649
wechat-cli: reading local WeChat data from a shell prompt
huggingface/lighteval 2,574
Lighteval: Hugging Face's Backend-Agnostic Harness for 1000+ LLM Benchmarks
Hoper-J/AI-Guide-and-Demos-zh_CN 4,768
Hoper-J/AI-Guide-and-Demos-zh_CN: A Chinese-Language Path from LLM API Calls to Local Fine-Tuning
hexiecs/talk-normal 1,866
talk-normal: a system prompt that strips AI filler from LLM answers
haykgrigo3/TimeCapsuleLLM 2,003
TimeCapsuleLLM: Training a Language Model on 1800-1875 London Text Alone
harbor-framework/terminal-bench-1 2,606
Terminal-Bench: A Task Suite and Sandbox Harness for Command-Line Agents
gnehs/subtitle-translator-electron 1,688
Subtitle Translator (gnehs/subtitle-translator-electron): an Electron front end for LLM subtitle translation
gkamradt/needle-in-a-haystack 2,401