run-llama/llama_deploy 2,068
ROCm/FastFlowLM 1,981 +1 today
FastFlowLM: MIT for the orchestration, completely free for the kernels, and a credit line in between
Prism-Shadow/penguin-harness 2,916
PenguinHarness types itself against a generated file, and every push publishes an image
Player-YN/PawWork_ZhuaZhua 2,386
PawWork ZhuaZhua and the scope its documentation never bounds
pchalasani/claude-code-tools 2,022
claude-code-tools ships pytest and a chat client as runtime dependencies, and a 235 word README
Orkas-AI/Orkas 2,155 +4 today
Orkas: nine agents ship, twenty-one live on a website, and Linux gets no installer
Open-Curiosity/gini-agent 2,120 +20 today
Gini Agent: a headed browser on purpose, secrets kept out of the model and typed into it
onestardao/WFGY 1,800
WFGY tells your assistant what to say, in a block you cannot see
NVIDIA-NeMo/DataDesigner 2,365 +5 today
NeMo Data Designer: Column-Based Synthetic Data Generation with Samplers, LLM Columns and Validators
nottelabs/notte 2,043 +1 today
Notte: a Python web agent framework with a hosted browser tier behind it
nndeploy/nndeploy 1,887
nndeploy: A Workflow Graph Layer for Deploying AI Models Across Desktop, Mobile and Edge
NitroRCr/AIaW 1,839
AIaW Is Deprecated: What the Client Still Does and What Nya AI Replaces
nhaouari/obsidian-textgenerator-plugin 1,991
obsidian-textgenerator-plugin: AI text generation inside an Obsidian vault
neuron-core/neuron-ai 2,153
neuron-core/neuron-ai: a PHP agent framework that ships its own Workflow, MCP connector and Inspector hookup
mozilla-ai/any-llm 2,228
any-llm: One Python Completion Call Across Mistral, OpenAI, Anthropic and Ollama
microsoft/kernel-memory 2,234